Compare commits

..

1 Commits

Author SHA1 Message Date
c762d0de08 Dark theme, pdf meta, de-serialize bugfix 2019-10-30 21:48:58 -04:00
108 changed files with 4808 additions and 6025 deletions

View File

@@ -1,16 +0,0 @@
---
name: Issue template
about: General
title: ''
labels: ''
assignees: ''
---
sist2 version:
Platform (please indicate if you're using Docker):
Command with arguments: `ex: "scan ~/Documents -o ./i2 --threads 3 -q 1.0`
If the issue is related to the `scan` module, please attach the files necessary to reproduce the error or email them to me[at]simon987.net.

2
.gitignore vendored
View File

@@ -15,5 +15,3 @@ bundle*.css
bundle.js
*.a
vgcore.*
build/
third-party/

22
.gitmodules vendored
View File

@@ -1,6 +1,18 @@
[submodule "third-party/libscan"]
path = third-party/libscan
url = https://github.com/simon987/libscan
[submodule "third-party/argparse"]
path = third-party/argparse
[submodule "argparse"]
path = argparse
url = https://github.com/cofyc/argparse
[submodule "cJSON"]
path = cJSON
url = https://github.com/DaveGamble/cJSON
[submodule "lib/mupdf"]
path = lib/mupdf
url = git://git.ghostscript.com/mupdf.git
[submodule "lib/onion"]
path = lib/onion
url = https://github.com/davidmoreno/onion
[submodule "lib/ffmpeg"]
path = lib/ffmpeg
url = https://git.ffmpeg.org/ffmpeg.git
[submodule "lmdb"]
path = lmdb
url = https://github.com/LMDB/lmdb

View File

@@ -1,69 +0,0 @@
import jetbrains.buildServer.configs.kotlin.v2019_2.*
import jetbrains.buildServer.configs.kotlin.v2019_2.buildSteps.ExecBuildStep
import jetbrains.buildServer.configs.kotlin.v2019_2.buildSteps.exec
import jetbrains.buildServer.configs.kotlin.v2019_2.triggers.vcs
import jetbrains.buildServer.configs.kotlin.v2019_2.vcs.GitVcsRoot
/*
The settings script is an entry point for defining a TeamCity
project hierarchy. The script should contain a single call to the
project() function with a Project instance or an init function as
an argument.
VcsRoots, BuildTypes, Templates, and subprojects can be
registered inside the project using the vcsRoot(), buildType(),
template(), and subProject() methods respectively.
To debug settings scripts in command-line, run the
mvnDebug org.jetbrains.teamcity:teamcity-configs-maven-plugin:generate
command and attach your debugger to the port 8000.
To debug in IntelliJ Idea, open the 'Maven Projects' tool window (View
-> Tool Windows -> Maven Projects), find the generate task node
(Plugins -> teamcity-configs -> teamcity-configs:generate), the
'Debug' option is available in the context menu for the task.
*/
version = "2019.2"
project {
vcsRoot(HttpsGithubComSimon987sist2refsHeadsMaster)
buildType(Build)
}
object Build : BuildType({
name = "Build"
artifactRules = """
sist2
sist2_scan
""".trimIndent()
vcs {
root(HttpsGithubComSimon987sist2refsHeadsMaster)
}
steps {
exec {
name = "Build"
path = "./ci/build.sh"
dockerImage = "simon987/general_ci"
dockerImagePlatform = ExecBuildStep.ImagePlatform.Linux
dockerPull = true
}
}
triggers {
vcs {
}
}
})
object HttpsGithubComSimon987sist2refsHeadsMaster : GitVcsRoot({
name = "https://github.com/simon987/sist2#refs/heads/master"
url = "https://github.com/simon987/sist2"
})

View File

@@ -1,121 +1,230 @@
cmake_minimum_required(VERSION 3.7)
set(CMAKE_C_STANDARD 11)
option(WITH_SIST2 "Build main executable" ON)
option(WITH_SIST2_SCAN "Build scan executable" ON)
project(sist2 C)
list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_LIST_DIR}/CMakeModules")
option(SIST_DEBUG "Build a debug executable" on)
add_subdirectory(third-party/libscan)
set(ARGPARSE_SHARED off)
add_subdirectory(third-party/argparse)
add_executable(
sist2
src/main.c
src/sist.h
src/io/walk.h src/io/walk.c
src/io/store.h src/io/store.c
src/tpool.h src/tpool.c
src/parsing/parse.h src/parsing/parse.c
src/io/serialize.h src/io/serialize.c
src/parsing/mime.h src/parsing/mime.c src/parsing/mime_generated.c
src/index/web.c src/index/web.h
src/web/serve.c src/web/serve.h
src/index/elastic.c src/index/elastic.h
src/util.c src/util.h
src/ctx.h src/types.h
src/log.c src/log.h
# argparse
third-party/argparse/argparse.h third-party/argparse/argparse.c
src/cli.c src/cli.h
)
target_link_directories(sist2 PRIVATE BEFORE ${_VCPKG_INSTALLED_DIR}/${VCPKG_TARGET_TRIPLET}/lib/)
set(CMAKE_FIND_LIBRARY_SUFFIXES .a .lib)
find_package(lmdb CONFIG REQUIRED)
find_package(cJSON CONFIG REQUIRED)
find_package(unofficial-glib CONFIG REQUIRED)
find_package(unofficial-mongoose CONFIG REQUIRED)
find_library(UUID_LIB NAMES uuid)
#find_package(OpenSSL REQUIRED)
target_include_directories(
sist2 PUBLIC
${CMAKE_SOURCE_DIR}/third-party/onion/src/
${CMAKE_SOURCE_DIR}/third-party/utf8.h/
${CMAKE_SOURCE_DIR}/third-party/libscan/
${CMAKE_SOURCE_DIR}/
)
target_compile_options(
sist2
PRIVATE
-fPIC
-Werror
)
if (SIST_DEBUG)
target_compile_options(
if (WITH_SIST2)
add_executable(
sist2
PRIVATE
-g
-fstack-protector
-fno-omit-frame-pointer
-fsanitize=address
)
target_link_options(
sist2
PRIVATE
-fsanitize=address
# -static
)
set_target_properties(
sist2
PROPERTIES
OUTPUT_NAME sist2_debug
)
else ()
target_compile_options(
sist2
PRIVATE
-Ofast
-fno-stack-protector
-fomit-frame-pointer
src/main.c
src/sist.h
src/io/walk.h src/io/walk.c
src/parsing/media.h src/parsing/media.c
src/parsing/pdf.h src/parsing/pdf.c
src/io/store.h src/io/store.c
src/tpool.h src/tpool.c
src/parsing/parse.h src/parsing/parse.c
src/io/serialize.h src/io/serialize.c
src/parsing/mime.h src/parsing/mime.c src/parsing/mime_generated.c
src/parsing/text.h src/parsing/text.c
src/index/web.c src/index/web.h
src/web/serve.c src/web/serve.h
src/index/elastic.c src/index/elastic.h
src/util.c src/util.h
src/ctx.h src/types.h src/parsing/font.c src/parsing/font.h
# argparse
argparse/argparse.h argparse/argparse.c
# cJSON
cJSON/cJSON.h cJSON/cJSON.c
# LMDB
lmdb/libraries/liblmdb/lmdb.h lmdb/libraries/liblmdb/mdb.c
lmdb/libraries/liblmdb/midl.h lmdb/libraries/liblmdb/midl.c
src/cli.c src/cli.h
)
endif ()
add_dependencies(
sist2
scan
argparse
)
if (WITH_SIST2_SCAN)
add_executable(
sist2_scan
src/main.c
src/sist.h
src/io/walk.h src/io/walk.c
src/parsing/media.h src/parsing/media.c
src/parsing/pdf.h src/parsing/pdf.c
src/io/store.h src/io/store.c
src/tpool.h src/tpool.c
src/parsing/parse.h src/parsing/parse.c
src/io/serialize.h src/io/serialize.c
src/parsing/mime.h src/parsing/mime.c src/parsing/mime_generated.c
src/parsing/text.h src/parsing/text.c
src/util.c src/util.h
src/ctx.h src/types.h src/parsing/font.c src/parsing/font.h
target_link_libraries(
sist2
# argparse
argparse/argparse.h argparse/argparse.c
z
lmdb
cjson
argparse
unofficial::glib::glib
unofficial::mongoose::mongoose
# OpenSSL::SSL OpenSSL::Crypto
# cJSON
cJSON/cJSON.h cJSON/cJSON.c
${UUID_LIB}
pthread
magic
# LMDB
lmdb/libraries/liblmdb/lmdb.h lmdb/libraries/liblmdb/mdb.c
lmdb/libraries/liblmdb/midl.h lmdb/libraries/liblmdb/midl.c
src/cli.c src/cli.h
)
endif ()
scan
)
find_package(PkgConfig REQUIRED)
set(ENV{PKG_CONFIG_PATH} "$ENV{PKG_CONFIG_PATH}:/usr/local/lib/pkgconfig/")
find_package(LibMagic REQUIRED)
find_package(FFmpeg REQUIRED)
find_package(OpenSSL REQUIRED)
find_package(Freetype REQUIRED)
pkg_check_modules(GLIB REQUIRED glib-2.0)
pkg_check_modules(GOBJECT REQUIRED gobject-2.0)
pkg_check_modules(UUID REQUIRED uuid)
add_definitions(${LIBMAGIC_CFLAGS_OTHER})
add_definitions(${UUID_CFLAGS_OTHER})
add_definitions(${GLIB_CFLAGS_OTHER})
add_definitions(${GOBJECT_CFLAGS_OTHER})
add_definitions(${FREETYPE_CFLAGS_OTHER})
list(REMOVE_ITEM GLIB_LIBRARIES pcre)
list(REMOVE_ITEM GOBJECT_LIBRARIES pcre)
list(REMOVE_ITEM UUID_LIBRARIES pcre)
if (WITH_SIST2)
target_include_directories(
sist2 PUBLIC
${LIBMAGIC_INCLUDE_DIRS}
${GOBJECT_INCLUDE_DIRS}
${OPENSSL_INCLUDE_DIR}
${FFMPEG_INCLUDE_DIRS}
${GLIB_INCLUDE_DIRS}
${FREETYPE_INCLUDE_DIRS}
${UUID_INCLUDE_DIRS}
${PROJECT_SOURCE_DIR}/
${PROJECT_SOURCE_DIR}/lmdb/libraries/liblmdb/
${PROJECT_SOURCE_DIR}/lib/onion/src/
${PROJECT_SOURCE_DIR}/lib/mupdf/include/
)
target_link_directories(
sist2 PUBLIC
${UUID_LIBRARY_DIRS}
${FFMPEG_LIBRARY_DIRS}
)
target_compile_options(sist2
PRIVATE
-O3
# -march=native
-fno-stack-protector
-fomit-frame-pointer
)
TARGET_LINK_LIBRARIES(
sist2
${GLIB_LIBRARIES}
${GOBJECT_LIBRARIES}
${UUID_LIBRARIES}
# ffmpeg
${PROJECT_SOURCE_DIR}/lib/libavcodec.a
${PROJECT_SOURCE_DIR}/lib/libavformat.a
${PROJECT_SOURCE_DIR}/lib/libavutil.a
${PROJECT_SOURCE_DIR}/lib/libswscale.a
${PROJECT_SOURCE_DIR}/lib/libswresample.a
# ${FFMPEG_LIBRARIES}
# swscale
# mupdf
${PROJECT_SOURCE_DIR}/lib/libmupdf.a
${PROJECT_SOURCE_DIR}/lib/libmupdf-third.a
# onion
${PROJECT_SOURCE_DIR}/lib/libonion_static.a
pthread
curl
m
bz2
magic
)
endif ()
if (WITH_SIST2_SCAN)
set_target_properties(
sist2_scan
PROPERTIES COMPILE_DEFINITIONS SIST_SCAN_ONLY
)
set_target_properties(
sist2_scan
PROPERTIES
COMPILE_DEFINITIONS SIST_SCAN_ONLY
LINK_FLAGS -static
)
target_include_directories(
sist2_scan PUBLIC
${LIBMAGIC_INCLUDE_DIRS}
${GOBJECT_INCLUDE_DIRS}
${OPENSSL_INCLUDE_DIR}
${FFMPEG_INCLUDE_DIRS}
${GLIB_INCLUDE_DIRS}
${UUID_INCLUDE_DIRS}
${FREETYPE_INCLUDE_DIRS}
${PROJECT_SOURCE_DIR}/
${PROJECT_SOURCE_DIR}/lmdb/libraries/liblmdb/
${PROJECT_SOURCE_DIR}/lib/onion/src/
${PROJECT_SOURCE_DIR}/lib/mupdf/include/
)
target_link_directories(
sist2_scan PUBLIC
${UUID_LIBRARY_DIRS}
${FFMPEG_LIBRARY_DIRS}
)
target_compile_options(sist2_scan
PRIVATE
-O3
# -march=native
-fno-stack-protector
-fomit-frame-pointer
)
TARGET_LINK_LIBRARIES(
sist2_scan
${GLIB_LIBRARIES}
${GOBJECT_LIBRARIES}
${UUID_LIBRARIES}
# ffmpeg
${PROJECT_SOURCE_DIR}/lib/libavcodec.a
${PROJECT_SOURCE_DIR}/lib/libavformat.a
${PROJECT_SOURCE_DIR}/lib/libavutil.a
${PROJECT_SOURCE_DIR}/lib/libswscale.a
${PROJECT_SOURCE_DIR}/lib/libswresample.a
# mupdf
${PROJECT_SOURCE_DIR}/lib/libmupdf.a
${PROJECT_SOURCE_DIR}/lib/libmupdf-third.a
${PROJECT_SOURCE_DIR}/lib/libbz2.a
${PROJECT_SOURCE_DIR}/lib/libmagic.a
pthread
m
)
endif ()
add_custom_target(
before_sist2
COMMAND ${CMAKE_CURRENT_SOURCE_DIR}/scripts/before_build.sh
)
add_dependencies(sist2 before_sist2)
IF (WITH_SIST2)
add_dependencies(sist2 before_sist2)
else ()
add_dependencies(sist2_scan before_sist2)
endif ()

80
CMakeModules/FindFFmpeg.cmake vendored Normal file
View File

@@ -0,0 +1,80 @@
# - Try to find ffmpeg libraries (libavcodec, libavformat and libavutil)
# Once done this will define
#
# FFMPEG_FOUND - system has ffmpeg or libav
# FFMPEG_INCLUDE_DIR - the ffmpeg include directory
# FFMPEG_LIBRARIES - Link these to use ffmpeg
# FFMPEG_LIBAVCODEC
# FFMPEG_LIBAVFORMAT
# FFMPEG_LIBAVUTIL
#
# Copyright (c) 2008 Andreas Schneider <mail@cynapses.org>
# Modified for other libraries by Lasse Kärkkäinen <tronic>
# Modified for Hedgewars by Stepik777
#
# Redistribution and use is allowed according to the terms of the New
# BSD license.
#
if (FFMPEG_LIBRARIES AND FFMPEG_INCLUDE_DIR)
# in cache already
set(FFMPEG_FOUND TRUE)
else (FFMPEG_LIBRARIES AND FFMPEG_INCLUDE_DIR)
# use pkg-config to get the directories and then use these values
# in the FIND_PATH() and FIND_LIBRARY() calls
find_package(PkgConfig)
if (PKG_CONFIG_FOUND)
pkg_check_modules(_FFMPEG_AVCODEC libavcodec)
pkg_check_modules(_FFMPEG_AVFORMAT libavformat)
pkg_check_modules(_FFMPEG_AVUTIL libavutil)
endif (PKG_CONFIG_FOUND)
find_path(FFMPEG_AVCODEC_INCLUDE_DIR
NAMES libavcodec/avcodec.h
PATHS ${_FFMPEG_AVCODEC_INCLUDE_DIRS} /usr/include /usr/local/include /opt/local/include /sw/include
PATH_SUFFIXES ffmpeg libav
)
find_library(FFMPEG_LIBAVCODEC
NAMES avcodec
PATHS ${_FFMPEG_AVCODEC_LIBRARY_DIRS} /usr/lib /usr/local/lib /opt/local/lib /sw/lib
)
find_library(FFMPEG_LIBAVFORMAT
NAMES avformat
PATHS ${_FFMPEG_AVFORMAT_LIBRARY_DIRS} /usr/lib /usr/local/lib /opt/local/lib /sw/lib
)
find_library(FFMPEG_LIBAVUTIL
NAMES avutil
PATHS ${_FFMPEG_AVUTIL_LIBRARY_DIRS} /usr/lib /usr/local/lib /opt/local/lib /sw/lib
)
if (FFMPEG_LIBAVCODEC AND FFMPEG_LIBAVFORMAT)
set(FFMPEG_FOUND TRUE)
endif()
if (FFMPEG_FOUND)
set(FFMPEG_INCLUDE_DIR ${FFMPEG_AVCODEC_INCLUDE_DIR})
set(FFMPEG_LIBRARIES
${FFMPEG_LIBAVCODEC}
${FFMPEG_LIBAVFORMAT}
${FFMPEG_LIBAVUTIL}
)
endif (FFMPEG_FOUND)
if (FFMPEG_FOUND)
if (NOT FFMPEG_FIND_QUIETLY)
message(STATUS "Found FFMPEG or Libav: ${FFMPEG_LIBRARIES}, ${FFMPEG_INCLUDE_DIR}")
endif (NOT FFMPEG_FIND_QUIETLY)
else (FFMPEG_FOUND)
if (FFMPEG_FIND_REQUIRED)
message(FATAL_ERROR "Could not find libavcodec or libavformat or libavutil")
endif (FFMPEG_FIND_REQUIRED)
endif (FFMPEG_FOUND)
endif (FFMPEG_LIBRARIES AND FFMPEG_INCLUDE_DIR)

100
CMakeModules/FindLibMagic.cmake vendored Normal file
View File

@@ -0,0 +1,100 @@
#-------------------------------------------------------------------------------
# Copyright (c) 2013-2013, Lars Baehren <lbaehren@gmail.com>
# All rights reserved.
#
# Redistribution and use in source and binary forms, with or without modification,
# are permitted provided that the following conditions are met:
#
# * Redistributions of source code must retain the above copyright notice, this
# list of conditions and the following disclaimer.
# * Redistributions in binary form must reproduce the above copyright notice,
# this list of conditions and the following disclaimer in the documentation
# and/or other materials provided with the distribution.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
# CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
#-------------------------------------------------------------------------------
# - Check for the presence of LIBMAGIC
#
# The following variables are set when LIBMAGIC is found:
# LIBMAGIC_FOUND = Set to true, if all components of LIBMAGIC have been
# found.
# LIBMAGIC_INCLUDES = Include path for the header files of LIBMAGIC
# LIBMAGIC_LIBRARIES = Link these to use LIBMAGIC
# LIBMAGIC_LFLAGS = Linker flags (optional)
if (NOT LIBMAGIC_FOUND)
if (NOT LIBMAGIC_ROOT_DIR)
set (LIBMAGIC_ROOT_DIR ${CMAKE_INSTALL_PREFIX})
endif (NOT LIBMAGIC_ROOT_DIR)
##____________________________________________________________________________
## Check for the header files
find_path (LIBMAGIC_FILE_H
NAMES file/file.h
HINTS ${LIBMAGIC_ROOT_DIR} ${CMAKE_INSTALL_PREFIX}
PATH_SUFFIXES include
)
if (LIBMAGIC_FILE_H)
list (APPEND LIBMAGIC_INCLUDES ${LIBMAGIC_FILE_H})
endif (LIBMAGIC_FILE_H)
find_path (LIBMAGIC_MAGIC_H
NAMES magic.h
HINTS ${LIBMAGIC_ROOT_DIR} ${CMAKE_INSTALL_PREFIX}
PATH_SUFFIXES include include/linux
)
if (LIBMAGIC_MAGIC_H)
list (APPEND LIBMAGIC_INCLUDES ${LIBMAGIC_MAGIC_H})
endif (LIBMAGIC_MAGIC_H)
list (REMOVE_DUPLICATES LIBMAGIC_INCLUDES)
##____________________________________________________________________________
## Check for the library
find_library (LIBMAGIC_LIBRARIES magic
HINTS ${LIBMAGIC_ROOT_DIR} ${CMAKE_INSTALL_PREFIX}
PATH_SUFFIXES lib
)
##____________________________________________________________________________
## Actions taken when all components have been found
#find_package_handle_standard_args (LIBMAGIC DEFAULT_MSG LIBMAGIC_LIBRARIES LIBMAGIC_INCLUDES)
if (LIBMAGIC_FOUND)
if (NOT LIBMAGIC_FIND_QUIETLY)
message (STATUS "Found components for LIBMAGIC")
message (STATUS "LIBMAGIC_ROOT_DIR = ${LIBMAGIC_ROOT_DIR}")
message (STATUS "LIBMAGIC_INCLUDES = ${LIBMAGIC_INCLUDES}")
message (STATUS "LIBMAGIC_LIBRARIES = ${LIBMAGIC_LIBRARIES}")
endif (NOT LIBMAGIC_FIND_QUIETLY)
else (LIBMAGIC_FOUND)
if (LIBMAGIC_FIND_REQUIRED)
message (FATAL_ERROR "Could not find LIBMAGIC!")
endif (LIBMAGIC_FIND_REQUIRED)
endif (LIBMAGIC_FOUND)
##____________________________________________________________________________
## Mark advanced variables
mark_as_advanced (
LIBMAGIC_ROOT_DIR
LIBMAGIC_INCLUDES
LIBMAGIC_LIBRARIES
)
endif (NOT LIBMAGIC_FOUND)

478
CMakeModules/FindOpenSSL.cmake vendored Normal file
View File

@@ -0,0 +1,478 @@
# Distributed under the OSI-approved BSD 3-Clause License. See accompanying
# file Copyright.txt or https://cmake.org/licensing for details.
macro(_OpenSSL_test_and_find_dependencies ssl_library crypto_library)
if((CMAKE_SYSTEM_NAME STREQUAL "Linux") AND
(("${ssl_library}" MATCHES "\\${CMAKE_STATIC_LIBRARY_SUFFIX}$") OR
("${crypto_library}" MATCHES "\\${CMAKE_STATIC_LIBRARY_SUFFIX}$")))
set(_OpenSSL_has_dependencies TRUE)
find_package(Threads)
else()
set(_OpenSSL_has_dependencies FALSE)
endif()
endmacro()
function(_OpenSSL_add_dependencies libraries_var library)
if(CMAKE_THREAD_LIBS_INIT)
list(APPEND ${libraries_var} ${CMAKE_THREAD_LIBS_INIT})
endif()
list(APPEND ${libraries_var} ${CMAKE_DL_LIBS})
set(${libraries_var} ${${libraries_var}} PARENT_SCOPE)
endfunction()
function(_OpenSSL_target_add_dependencies target)
if(_OpenSSL_has_dependencies)
set_property( TARGET ${target} APPEND PROPERTY INTERFACE_LINK_LIBRARIES Threads::Threads )
set_property( TARGET ${target} APPEND PROPERTY INTERFACE_LINK_LIBRARIES ${CMAKE_DL_LIBS} )
endif()
endfunction()
if (UNIX)
find_package(PkgConfig QUIET)
pkg_check_modules(_OPENSSL QUIET openssl)
endif ()
# Support preference of static libs by adjusting CMAKE_FIND_LIBRARY_SUFFIXES
if(OPENSSL_USE_STATIC_LIBS)
set(_openssl_ORIG_CMAKE_FIND_LIBRARY_SUFFIXES ${CMAKE_FIND_LIBRARY_SUFFIXES})
if(WIN32)
set(CMAKE_FIND_LIBRARY_SUFFIXES .lib .a ${CMAKE_FIND_LIBRARY_SUFFIXES})
else()
set(CMAKE_FIND_LIBRARY_SUFFIXES .a )
endif()
endif()
if (WIN32)
# http://www.slproweb.com/products/Win32OpenSSL.html
set(_OPENSSL_ROOT_HINTS
${OPENSSL_ROOT_DIR}
"[HKEY_LOCAL_MACHINE\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Uninstall\\OpenSSL (32-bit)_is1;Inno Setup: App Path]"
"[HKEY_LOCAL_MACHINE\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Uninstall\\OpenSSL (64-bit)_is1;Inno Setup: App Path]"
ENV OPENSSL_ROOT_DIR
)
file(TO_CMAKE_PATH "$ENV{PROGRAMFILES}" _programfiles)
set(_OPENSSL_ROOT_PATHS
"${_programfiles}/OpenSSL"
"${_programfiles}/OpenSSL-Win32"
"${_programfiles}/OpenSSL-Win64"
"C:/OpenSSL/"
"C:/OpenSSL-Win32/"
"C:/OpenSSL-Win64/"
)
unset(_programfiles)
else ()
set(_OPENSSL_ROOT_HINTS
${OPENSSL_ROOT_DIR}
ENV OPENSSL_ROOT_DIR
)
endif ()
set(_OPENSSL_ROOT_HINTS_AND_PATHS
HINTS ${_OPENSSL_ROOT_HINTS}
PATHS ${_OPENSSL_ROOT_PATHS}
)
find_path(OPENSSL_INCLUDE_DIR
NAMES
openssl/ssl.h
${_OPENSSL_ROOT_HINTS_AND_PATHS}
HINTS
${_OPENSSL_INCLUDEDIR}
PATH_SUFFIXES
include
)
if(WIN32 AND NOT CYGWIN)
if(MSVC)
# /MD and /MDd are the standard values - if someone wants to use
# others, the libnames have to change here too
# use also ssl and ssleay32 in debug as fallback for openssl < 0.9.8b
# enable OPENSSL_MSVC_STATIC_RT to get the libs build /MT (Multithreaded no-DLL)
# In Visual C++ naming convention each of these four kinds of Windows libraries has it's standard suffix:
# * MD for dynamic-release
# * MDd for dynamic-debug
# * MT for static-release
# * MTd for static-debug
# Implementation details:
# We are using the libraries located in the VC subdir instead of the parent directory even though :
# libeay32MD.lib is identical to ../libeay32.lib, and
# ssleay32MD.lib is identical to ../ssleay32.lib
# enable OPENSSL_USE_STATIC_LIBS to use the static libs located in lib/VC/static
if (OPENSSL_MSVC_STATIC_RT)
set(_OPENSSL_MSVC_RT_MODE "MT")
else ()
set(_OPENSSL_MSVC_RT_MODE "MD")
endif ()
# Since OpenSSL 1.1, lib names are like libcrypto32MTd.lib and libssl32MTd.lib
if( "${CMAKE_SIZEOF_VOID_P}" STREQUAL "8" )
set(_OPENSSL_MSVC_ARCH_SUFFIX "64")
else()
set(_OPENSSL_MSVC_ARCH_SUFFIX "32")
endif()
if(OPENSSL_USE_STATIC_LIBS)
set(_OPENSSL_PATH_SUFFIXES
"lib/VC/static"
"VC/static"
"lib"
)
else()
set(_OPENSSL_PATH_SUFFIXES
"lib/VC"
"VC"
"lib"
)
endif ()
find_library(LIB_EAY_DEBUG
NAMES
libcrypto${_OPENSSL_MSVC_ARCH_SUFFIX}${_OPENSSL_MSVC_RT_MODE}d
libcrypto${_OPENSSL_MSVC_RT_MODE}d
libcryptod
libeay32${_OPENSSL_MSVC_RT_MODE}d
libeay32d
cryptod
NAMES_PER_DIR
${_OPENSSL_ROOT_HINTS_AND_PATHS}
PATH_SUFFIXES
${_OPENSSL_PATH_SUFFIXES}
)
find_library(LIB_EAY_RELEASE
NAMES
libcrypto${_OPENSSL_MSVC_ARCH_SUFFIX}${_OPENSSL_MSVC_RT_MODE}
libcrypto${_OPENSSL_MSVC_RT_MODE}
libcrypto
libeay32${_OPENSSL_MSVC_RT_MODE}
libeay32
crypto
NAMES_PER_DIR
${_OPENSSL_ROOT_HINTS_AND_PATHS}
PATH_SUFFIXES
${_OPENSSL_PATH_SUFFIXES}
)
find_library(SSL_EAY_DEBUG
NAMES
libssl${_OPENSSL_MSVC_ARCH_SUFFIX}${_OPENSSL_MSVC_RT_MODE}d
libssl${_OPENSSL_MSVC_RT_MODE}d
libssld
ssleay32${_OPENSSL_MSVC_RT_MODE}d
ssleay32d
ssld
NAMES_PER_DIR
${_OPENSSL_ROOT_HINTS_AND_PATHS}
PATH_SUFFIXES
${_OPENSSL_PATH_SUFFIXES}
)
find_library(SSL_EAY_RELEASE
NAMES
libssl${_OPENSSL_MSVC_ARCH_SUFFIX}${_OPENSSL_MSVC_RT_MODE}
libssl${_OPENSSL_MSVC_RT_MODE}
libssl
ssleay32${_OPENSSL_MSVC_RT_MODE}
ssleay32
ssl
NAMES_PER_DIR
${_OPENSSL_ROOT_HINTS_AND_PATHS}
PATH_SUFFIXES
${_OPENSSL_PATH_SUFFIXES}
)
set(LIB_EAY_LIBRARY_DEBUG "${LIB_EAY_DEBUG}")
set(LIB_EAY_LIBRARY_RELEASE "${LIB_EAY_RELEASE}")
set(SSL_EAY_LIBRARY_DEBUG "${SSL_EAY_DEBUG}")
set(SSL_EAY_LIBRARY_RELEASE "${SSL_EAY_RELEASE}")
include(${CMAKE_CURRENT_LIST_DIR}/SelectLibraryConfigurations.cmake)
select_library_configurations(LIB_EAY)
select_library_configurations(SSL_EAY)
mark_as_advanced(LIB_EAY_LIBRARY_DEBUG LIB_EAY_LIBRARY_RELEASE
SSL_EAY_LIBRARY_DEBUG SSL_EAY_LIBRARY_RELEASE)
set(OPENSSL_SSL_LIBRARY ${SSL_EAY_LIBRARY} )
set(OPENSSL_CRYPTO_LIBRARY ${LIB_EAY_LIBRARY} )
elseif(MINGW)
# same player, for MinGW
set(LIB_EAY_NAMES crypto libeay32)
set(SSL_EAY_NAMES ssl ssleay32)
find_library(LIB_EAY
NAMES
${LIB_EAY_NAMES}
NAMES_PER_DIR
${_OPENSSL_ROOT_HINTS_AND_PATHS}
PATH_SUFFIXES
"lib/MinGW"
"lib"
)
find_library(SSL_EAY
NAMES
${SSL_EAY_NAMES}
NAMES_PER_DIR
${_OPENSSL_ROOT_HINTS_AND_PATHS}
PATH_SUFFIXES
"lib/MinGW"
"lib"
)
mark_as_advanced(SSL_EAY LIB_EAY)
set(OPENSSL_SSL_LIBRARY ${SSL_EAY} )
set(OPENSSL_CRYPTO_LIBRARY ${LIB_EAY} )
unset(LIB_EAY_NAMES)
unset(SSL_EAY_NAMES)
else()
# Not sure what to pick for -say- intel, let's use the toplevel ones and hope someone report issues:
find_library(LIB_EAY
NAMES
libcrypto
libeay32
NAMES_PER_DIR
${_OPENSSL_ROOT_HINTS_AND_PATHS}
HINTS
${_OPENSSL_LIBDIR}
PATH_SUFFIXES
lib
)
find_library(SSL_EAY
NAMES
libssl
ssleay32
NAMES_PER_DIR
${_OPENSSL_ROOT_HINTS_AND_PATHS}
HINTS
${_OPENSSL_LIBDIR}
PATH_SUFFIXES
lib
)
mark_as_advanced(SSL_EAY LIB_EAY)
set(OPENSSL_SSL_LIBRARY ${SSL_EAY} )
set(OPENSSL_CRYPTO_LIBRARY ${LIB_EAY} )
endif()
else()
find_library(OPENSSL_SSL_LIBRARY
NAMES
ssl
ssleay32
ssleay32MD
NAMES_PER_DIR
${_OPENSSL_ROOT_HINTS_AND_PATHS}
HINTS
${_OPENSSL_LIBDIR}
PATH_SUFFIXES
lib
)
find_library(OPENSSL_CRYPTO_LIBRARY
NAMES
crypto
NAMES_PER_DIR
${_OPENSSL_ROOT_HINTS_AND_PATHS}
HINTS
${_OPENSSL_LIBDIR}
PATH_SUFFIXES
lib
)
mark_as_advanced(OPENSSL_CRYPTO_LIBRARY OPENSSL_SSL_LIBRARY)
endif()
# compat defines
set(OPENSSL_SSL_LIBRARIES ${OPENSSL_SSL_LIBRARY})
set(OPENSSL_CRYPTO_LIBRARIES ${OPENSSL_CRYPTO_LIBRARY})
_OpenSSL_test_and_find_dependencies("${OPENSSL_SSL_LIBRARY}" "${OPENSSL_CRYPTO_LIBRARY}")
if(_OpenSSL_has_dependencies)
_OpenSSL_add_dependencies( OPENSSL_SSL_LIBRARIES "${OPENSSL_SSL_LIBRARY}" )
_OpenSSL_add_dependencies( OPENSSL_CRYPTO_LIBRARIES "${OPENSSL_CRYPTO_LIBRARY}" )
endif()
function(from_hex HEX DEC)
string(TOUPPER "${HEX}" HEX)
set(_res 0)
string(LENGTH "${HEX}" _strlen)
while (_strlen GREATER 0)
math(EXPR _res "${_res} * 16")
string(SUBSTRING "${HEX}" 0 1 NIBBLE)
string(SUBSTRING "${HEX}" 1 -1 HEX)
if (NIBBLE STREQUAL "A")
math(EXPR _res "${_res} + 10")
elseif (NIBBLE STREQUAL "B")
math(EXPR _res "${_res} + 11")
elseif (NIBBLE STREQUAL "C")
math(EXPR _res "${_res} + 12")
elseif (NIBBLE STREQUAL "D")
math(EXPR _res "${_res} + 13")
elseif (NIBBLE STREQUAL "E")
math(EXPR _res "${_res} + 14")
elseif (NIBBLE STREQUAL "F")
math(EXPR _res "${_res} + 15")
else()
math(EXPR _res "${_res} + ${NIBBLE}")
endif()
string(LENGTH "${HEX}" _strlen)
endwhile()
set(${DEC} ${_res} PARENT_SCOPE)
endfunction()
if(OPENSSL_INCLUDE_DIR AND EXISTS "${OPENSSL_INCLUDE_DIR}/openssl/opensslv.h")
file(STRINGS "${OPENSSL_INCLUDE_DIR}/openssl/opensslv.h" openssl_version_str
REGEX "^#[\t ]*define[\t ]+OPENSSL_VERSION_NUMBER[\t ]+0x([0-9a-fA-F])+.*")
if(openssl_version_str)
# The version number is encoded as 0xMNNFFPPS: major minor fix patch status
# The status gives if this is a developer or prerelease and is ignored here.
# Major, minor, and fix directly translate into the version numbers shown in
# the string. The patch field translates to the single character suffix that
# indicates the bug fix state, which 00 -> nothing, 01 -> a, 02 -> b and so
# on.
string(REGEX REPLACE "^.*OPENSSL_VERSION_NUMBER[\t ]+0x([0-9a-fA-F])([0-9a-fA-F][0-9a-fA-F])([0-9a-fA-F][0-9a-fA-F])([0-9a-fA-F][0-9a-fA-F])([0-9a-fA-F]).*$"
"\\1;\\2;\\3;\\4;\\5" OPENSSL_VERSION_LIST "${openssl_version_str}")
list(GET OPENSSL_VERSION_LIST 0 OPENSSL_VERSION_MAJOR)
list(GET OPENSSL_VERSION_LIST 1 OPENSSL_VERSION_MINOR)
from_hex("${OPENSSL_VERSION_MINOR}" OPENSSL_VERSION_MINOR)
list(GET OPENSSL_VERSION_LIST 2 OPENSSL_VERSION_FIX)
from_hex("${OPENSSL_VERSION_FIX}" OPENSSL_VERSION_FIX)
list(GET OPENSSL_VERSION_LIST 3 OPENSSL_VERSION_PATCH)
if (NOT OPENSSL_VERSION_PATCH STREQUAL "00")
from_hex("${OPENSSL_VERSION_PATCH}" _tmp)
# 96 is the ASCII code of 'a' minus 1
math(EXPR OPENSSL_VERSION_PATCH_ASCII "${_tmp} + 96")
unset(_tmp)
# Once anyone knows how OpenSSL would call the patch versions beyond 'z'
# this should be updated to handle that, too. This has not happened yet
# so it is simply ignored here for now.
string(ASCII "${OPENSSL_VERSION_PATCH_ASCII}" OPENSSL_VERSION_PATCH_STRING)
endif ()
set(OPENSSL_VERSION "${OPENSSL_VERSION_MAJOR}.${OPENSSL_VERSION_MINOR}.${OPENSSL_VERSION_FIX}${OPENSSL_VERSION_PATCH_STRING}")
endif ()
endif ()
set(OPENSSL_LIBRARIES ${OPENSSL_SSL_LIBRARIES} ${OPENSSL_CRYPTO_LIBRARIES} )
list(REMOVE_DUPLICATES OPENSSL_LIBRARIES)
foreach(_comp IN LISTS OpenSSL_FIND_COMPONENTS)
if(_comp STREQUAL "Crypto")
if(EXISTS "${OPENSSL_INCLUDE_DIR}" AND
(EXISTS "${OPENSSL_CRYPTO_LIBRARY}" OR
EXISTS "${LIB_EAY_LIBRARY_DEBUG}" OR
EXISTS "${LIB_EAY_LIBRARY_RELEASE}")
)
set(OpenSSL_${_comp}_FOUND TRUE)
else()
set(OpenSSL_${_comp}_FOUND FALSE)
endif()
elseif(_comp STREQUAL "SSL")
if(EXISTS "${OPENSSL_INCLUDE_DIR}" AND
(EXISTS "${OPENSSL_SSL_LIBRARY}" OR
EXISTS "${SSL_EAY_LIBRARY_DEBUG}" OR
EXISTS "${SSL_EAY_LIBRARY_RELEASE}")
)
set(OpenSSL_${_comp}_FOUND TRUE)
else()
set(OpenSSL_${_comp}_FOUND FALSE)
endif()
else()
message(WARNING "${_comp} is not a valid OpenSSL component")
set(OpenSSL_${_comp}_FOUND FALSE)
endif()
endforeach()
unset(_comp)
include(${CMAKE_CURRENT_LIST_DIR}/FindPackageHandleStandardArgs.cmake)
find_package_handle_standard_args(OpenSSL
REQUIRED_VARS
OPENSSL_CRYPTO_LIBRARY
OPENSSL_INCLUDE_DIR
VERSION_VAR
OPENSSL_VERSION
HANDLE_COMPONENTS
FAIL_MESSAGE
"Could NOT find OpenSSL, try to set the path to OpenSSL root folder in the system variable OPENSSL_ROOT_DIR"
)
mark_as_advanced(OPENSSL_INCLUDE_DIR OPENSSL_LIBRARIES)
if(OPENSSL_FOUND)
if(NOT TARGET OpenSSL::Crypto AND
(EXISTS "${OPENSSL_CRYPTO_LIBRARY}" OR
EXISTS "${LIB_EAY_LIBRARY_DEBUG}" OR
EXISTS "${LIB_EAY_LIBRARY_RELEASE}")
)
add_library(OpenSSL::Crypto UNKNOWN IMPORTED)
set_target_properties(OpenSSL::Crypto PROPERTIES
INTERFACE_INCLUDE_DIRECTORIES "${OPENSSL_INCLUDE_DIR}")
if(EXISTS "${OPENSSL_CRYPTO_LIBRARY}")
set_target_properties(OpenSSL::Crypto PROPERTIES
IMPORTED_LINK_INTERFACE_LANGUAGES "C"
IMPORTED_LOCATION "${OPENSSL_CRYPTO_LIBRARY}")
endif()
if(EXISTS "${LIB_EAY_LIBRARY_RELEASE}")
set_property(TARGET OpenSSL::Crypto APPEND PROPERTY
IMPORTED_CONFIGURATIONS RELEASE)
set_target_properties(OpenSSL::Crypto PROPERTIES
IMPORTED_LINK_INTERFACE_LANGUAGES_RELEASE "C"
IMPORTED_LOCATION_RELEASE "${LIB_EAY_LIBRARY_RELEASE}")
endif()
if(EXISTS "${LIB_EAY_LIBRARY_DEBUG}")
set_property(TARGET OpenSSL::Crypto APPEND PROPERTY
IMPORTED_CONFIGURATIONS DEBUG)
set_target_properties(OpenSSL::Crypto PROPERTIES
IMPORTED_LINK_INTERFACE_LANGUAGES_DEBUG "C"
IMPORTED_LOCATION_DEBUG "${LIB_EAY_LIBRARY_DEBUG}")
endif()
_OpenSSL_target_add_dependencies(OpenSSL::Crypto)
endif()
if(NOT TARGET OpenSSL::SSL AND
(EXISTS "${OPENSSL_SSL_LIBRARY}" OR
EXISTS "${SSL_EAY_LIBRARY_DEBUG}" OR
EXISTS "${SSL_EAY_LIBRARY_RELEASE}")
)
add_library(OpenSSL::SSL UNKNOWN IMPORTED)
set_target_properties(OpenSSL::SSL PROPERTIES
INTERFACE_INCLUDE_DIRECTORIES "${OPENSSL_INCLUDE_DIR}")
if(EXISTS "${OPENSSL_SSL_LIBRARY}")
set_target_properties(OpenSSL::SSL PROPERTIES
IMPORTED_LINK_INTERFACE_LANGUAGES "C"
IMPORTED_LOCATION "${OPENSSL_SSL_LIBRARY}")
endif()
if(EXISTS "${SSL_EAY_LIBRARY_RELEASE}")
set_property(TARGET OpenSSL::SSL APPEND PROPERTY
IMPORTED_CONFIGURATIONS RELEASE)
set_target_properties(OpenSSL::SSL PROPERTIES
IMPORTED_LINK_INTERFACE_LANGUAGES_RELEASE "C"
IMPORTED_LOCATION_RELEASE "${SSL_EAY_LIBRARY_RELEASE}")
endif()
if(EXISTS "${SSL_EAY_LIBRARY_DEBUG}")
set_property(TARGET OpenSSL::SSL APPEND PROPERTY
IMPORTED_CONFIGURATIONS DEBUG)
set_target_properties(OpenSSL::SSL PROPERTIES
IMPORTED_LINK_INTERFACE_LANGUAGES_DEBUG "C"
IMPORTED_LOCATION_DEBUG "${SSL_EAY_LIBRARY_DEBUG}")
endif()
if(TARGET OpenSSL::Crypto)
set_target_properties(OpenSSL::SSL PROPERTIES
INTERFACE_LINK_LIBRARIES OpenSSL::Crypto)
endif()
_OpenSSL_target_add_dependencies(OpenSSL::SSL)
endif()
endif()
# Restore the original find library ordering
if(OPENSSL_USE_STATIC_LIBS)
set(CMAKE_FIND_LIBRARY_SUFFIXES ${_openssl_ORIG_CMAKE_FIND_LIBRARY_SUFFIXES})
endif()

View File

@@ -0,0 +1,268 @@
# Distributed under the OSI-approved BSD 3-Clause License. See accompanying
# file Copyright.txt or https://cmake.org/licensing for details.
include(${CMAKE_CURRENT_LIST_DIR}/FindPackageMessage.cmake)
# internal helper macro
macro(_FPHSA_FAILURE_MESSAGE _msg)
set (__msg "${_msg}")
if (FPHSA_REASON_FAILURE_MESSAGE)
string(APPEND __msg "\n Reason given by package: ${FPHSA_REASON_FAILURE_MESSAGE}\n")
endif()
if (${_NAME}_FIND_REQUIRED)
message(FATAL_ERROR "${__msg}")
else ()
if (NOT ${_NAME}_FIND_QUIETLY)
message(STATUS "${__msg}")
endif ()
endif ()
endmacro()
# internal helper macro to generate the failure message when used in CONFIG_MODE:
macro(_FPHSA_HANDLE_FAILURE_CONFIG_MODE)
# <PackageName>_CONFIG is set, but FOUND is false, this means that some other of the REQUIRED_VARS was not found:
if(${_NAME}_CONFIG)
_FPHSA_FAILURE_MESSAGE("${FPHSA_FAIL_MESSAGE}: missing:${MISSING_VARS} (found ${${_NAME}_CONFIG} ${VERSION_MSG})")
else()
# If _CONSIDERED_CONFIGS is set, the config-file has been found, but no suitable version.
# List them all in the error message:
if(${_NAME}_CONSIDERED_CONFIGS)
set(configsText "")
list(LENGTH ${_NAME}_CONSIDERED_CONFIGS configsCount)
math(EXPR configsCount "${configsCount} - 1")
foreach(currentConfigIndex RANGE ${configsCount})
list(GET ${_NAME}_CONSIDERED_CONFIGS ${currentConfigIndex} filename)
list(GET ${_NAME}_CONSIDERED_VERSIONS ${currentConfigIndex} version)
string(APPEND configsText "\n ${filename} (version ${version})")
endforeach()
if (${_NAME}_NOT_FOUND_MESSAGE)
if (FPHSA_REASON_FAILURE_MESSAGE)
string(PREPEND FPHSA_REASON_FAILURE_MESSAGE "${${_NAME}_NOT_FOUND_MESSAGE}\n ")
else()
set(FPHSA_REASON_FAILURE_MESSAGE "${${_NAME}_NOT_FOUND_MESSAGE}")
endif()
else()
string(APPEND configsText "\n")
endif()
_FPHSA_FAILURE_MESSAGE("${FPHSA_FAIL_MESSAGE} ${VERSION_MSG}, checked the following files:${configsText}")
else()
# Simple case: No Config-file was found at all:
_FPHSA_FAILURE_MESSAGE("${FPHSA_FAIL_MESSAGE}: found neither ${_NAME}Config.cmake nor ${_NAME_LOWER}-config.cmake ${VERSION_MSG}")
endif()
endif()
endmacro()
function(FIND_PACKAGE_HANDLE_STANDARD_ARGS _NAME _FIRST_ARG)
# Set up the arguments for `cmake_parse_arguments`.
set(options CONFIG_MODE HANDLE_COMPONENTS)
set(oneValueArgs FAIL_MESSAGE REASON_FAILURE_MESSAGE VERSION_VAR FOUND_VAR)
set(multiValueArgs REQUIRED_VARS)
# Check whether we are in 'simple' or 'extended' mode:
set(_KEYWORDS_FOR_EXTENDED_MODE ${options} ${oneValueArgs} ${multiValueArgs} )
list(FIND _KEYWORDS_FOR_EXTENDED_MODE "${_FIRST_ARG}" INDEX)
if(${INDEX} EQUAL -1)
set(FPHSA_FAIL_MESSAGE ${_FIRST_ARG})
set(FPHSA_REQUIRED_VARS ${ARGN})
set(FPHSA_VERSION_VAR)
else()
cmake_parse_arguments(FPHSA "${options}" "${oneValueArgs}" "${multiValueArgs}" ${_FIRST_ARG} ${ARGN})
if(FPHSA_UNPARSED_ARGUMENTS)
message(FATAL_ERROR "Unknown keywords given to FIND_PACKAGE_HANDLE_STANDARD_ARGS(): \"${FPHSA_UNPARSED_ARGUMENTS}\"")
endif()
if(NOT FPHSA_FAIL_MESSAGE)
set(FPHSA_FAIL_MESSAGE "DEFAULT_MSG")
endif()
# In config-mode, we rely on the variable <PackageName>_CONFIG, which is set by find_package()
# when it successfully found the config-file, including version checking:
if(FPHSA_CONFIG_MODE)
list(INSERT FPHSA_REQUIRED_VARS 0 ${_NAME}_CONFIG)
list(REMOVE_DUPLICATES FPHSA_REQUIRED_VARS)
set(FPHSA_VERSION_VAR ${_NAME}_VERSION)
endif()
if(NOT FPHSA_REQUIRED_VARS)
message(FATAL_ERROR "No REQUIRED_VARS specified for FIND_PACKAGE_HANDLE_STANDARD_ARGS()")
endif()
endif()
# now that we collected all arguments, process them
if("x${FPHSA_FAIL_MESSAGE}" STREQUAL "xDEFAULT_MSG")
set(FPHSA_FAIL_MESSAGE "Could NOT find ${_NAME}")
endif()
list(GET FPHSA_REQUIRED_VARS 0 _FIRST_REQUIRED_VAR)
string(TOUPPER ${_NAME} _NAME_UPPER)
string(TOLOWER ${_NAME} _NAME_LOWER)
if(FPHSA_FOUND_VAR)
if(FPHSA_FOUND_VAR MATCHES "^${_NAME}_FOUND$" OR FPHSA_FOUND_VAR MATCHES "^${_NAME_UPPER}_FOUND$")
set(_FOUND_VAR ${FPHSA_FOUND_VAR})
else()
message(FATAL_ERROR "The argument for FOUND_VAR is \"${FPHSA_FOUND_VAR}\", but only \"${_NAME}_FOUND\" and \"${_NAME_UPPER}_FOUND\" are valid names.")
endif()
else()
set(_FOUND_VAR ${_NAME_UPPER}_FOUND)
endif()
# collect all variables which were not found, so they can be printed, so the
# user knows better what went wrong (#6375)
set(MISSING_VARS "")
set(DETAILS "")
# check if all passed variables are valid
set(FPHSA_FOUND_${_NAME} TRUE)
foreach(_CURRENT_VAR ${FPHSA_REQUIRED_VARS})
if(NOT ${_CURRENT_VAR})
set(FPHSA_FOUND_${_NAME} FALSE)
string(APPEND MISSING_VARS " ${_CURRENT_VAR}")
else()
string(APPEND DETAILS "[${${_CURRENT_VAR}}]")
endif()
endforeach()
if(FPHSA_FOUND_${_NAME})
set(${_NAME}_FOUND TRUE)
set(${_NAME_UPPER}_FOUND TRUE)
else()
set(${_NAME}_FOUND FALSE)
set(${_NAME_UPPER}_FOUND FALSE)
endif()
# component handling
unset(FOUND_COMPONENTS_MSG)
unset(MISSING_COMPONENTS_MSG)
if(FPHSA_HANDLE_COMPONENTS)
foreach(comp ${${_NAME}_FIND_COMPONENTS})
if(${_NAME}_${comp}_FOUND)
if(NOT DEFINED FOUND_COMPONENTS_MSG)
set(FOUND_COMPONENTS_MSG "found components:")
endif()
string(APPEND FOUND_COMPONENTS_MSG " ${comp}")
else()
if(NOT DEFINED MISSING_COMPONENTS_MSG)
set(MISSING_COMPONENTS_MSG "missing components:")
endif()
string(APPEND MISSING_COMPONENTS_MSG " ${comp}")
if(${_NAME}_FIND_REQUIRED_${comp})
set(${_NAME}_FOUND FALSE)
string(APPEND MISSING_VARS " ${comp}")
endif()
endif()
endforeach()
set(COMPONENT_MSG "${FOUND_COMPONENTS_MSG} ${MISSING_COMPONENTS_MSG}")
string(APPEND DETAILS "[c${COMPONENT_MSG}]")
endif()
# version handling:
set(VERSION_MSG "")
set(VERSION_OK TRUE)
# check with DEFINED here as the requested or found version may be "0"
if (DEFINED ${_NAME}_FIND_VERSION)
if(DEFINED ${FPHSA_VERSION_VAR})
set(_FOUND_VERSION ${${FPHSA_VERSION_VAR}})
if(${_NAME}_FIND_VERSION_EXACT) # exact version required
# count the dots in the version string
string(REGEX REPLACE "[^.]" "" _VERSION_DOTS "${_FOUND_VERSION}")
# add one dot because there is one dot more than there are components
string(LENGTH "${_VERSION_DOTS}." _VERSION_DOTS)
if (_VERSION_DOTS GREATER ${_NAME}_FIND_VERSION_COUNT)
# Because of the C++ implementation of find_package() ${_NAME}_FIND_VERSION_COUNT
# is at most 4 here. Therefore a simple lookup table is used.
if (${_NAME}_FIND_VERSION_COUNT EQUAL 1)
set(_VERSION_REGEX "[^.]*")
elseif (${_NAME}_FIND_VERSION_COUNT EQUAL 2)
set(_VERSION_REGEX "[^.]*\\.[^.]*")
elseif (${_NAME}_FIND_VERSION_COUNT EQUAL 3)
set(_VERSION_REGEX "[^.]*\\.[^.]*\\.[^.]*")
else ()
set(_VERSION_REGEX "[^.]*\\.[^.]*\\.[^.]*\\.[^.]*")
endif ()
string(REGEX REPLACE "^(${_VERSION_REGEX})\\..*" "\\1" _VERSION_HEAD "${_FOUND_VERSION}")
unset(_VERSION_REGEX)
if (NOT ${_NAME}_FIND_VERSION VERSION_EQUAL _VERSION_HEAD)
set(VERSION_MSG "Found unsuitable version \"${_FOUND_VERSION}\", but required is exact version \"${${_NAME}_FIND_VERSION}\"")
set(VERSION_OK FALSE)
else ()
set(VERSION_MSG "(found suitable exact version \"${_FOUND_VERSION}\")")
endif ()
unset(_VERSION_HEAD)
else ()
if (NOT ${_NAME}_FIND_VERSION VERSION_EQUAL _FOUND_VERSION)
set(VERSION_MSG "Found unsuitable version \"${_FOUND_VERSION}\", but required is exact version \"${${_NAME}_FIND_VERSION}\"")
set(VERSION_OK FALSE)
else ()
set(VERSION_MSG "(found suitable exact version \"${_FOUND_VERSION}\")")
endif ()
endif ()
unset(_VERSION_DOTS)
else() # minimum version specified:
if (${_NAME}_FIND_VERSION VERSION_GREATER _FOUND_VERSION)
set(VERSION_MSG "Found unsuitable version \"${_FOUND_VERSION}\", but required is at least \"${${_NAME}_FIND_VERSION}\"")
set(VERSION_OK FALSE)
else ()
set(VERSION_MSG "(found suitable version \"${_FOUND_VERSION}\", minimum required is \"${${_NAME}_FIND_VERSION}\")")
endif ()
endif()
else()
# if the package was not found, but a version was given, add that to the output:
if(${_NAME}_FIND_VERSION_EXACT)
set(VERSION_MSG "(Required is exact version \"${${_NAME}_FIND_VERSION}\")")
else()
set(VERSION_MSG "(Required is at least version \"${${_NAME}_FIND_VERSION}\")")
endif()
endif()
else ()
# Check with DEFINED as the found version may be 0.
if(DEFINED ${FPHSA_VERSION_VAR})
set(VERSION_MSG "(found version \"${${FPHSA_VERSION_VAR}}\")")
endif()
endif ()
if(VERSION_OK)
string(APPEND DETAILS "[v${${FPHSA_VERSION_VAR}}(${${_NAME}_FIND_VERSION})]")
else()
set(${_NAME}_FOUND FALSE)
endif()
# print the result:
if (${_NAME}_FOUND)
FIND_PACKAGE_MESSAGE(${_NAME} "Found ${_NAME}: ${${_FIRST_REQUIRED_VAR}} ${VERSION_MSG} ${COMPONENT_MSG}" "${DETAILS}")
else ()
if(FPHSA_CONFIG_MODE)
_FPHSA_HANDLE_FAILURE_CONFIG_MODE()
else()
if(NOT VERSION_OK)
_FPHSA_FAILURE_MESSAGE("${FPHSA_FAIL_MESSAGE}: ${VERSION_MSG} (found ${${_FIRST_REQUIRED_VAR}})")
else()
_FPHSA_FAILURE_MESSAGE("${FPHSA_FAIL_MESSAGE} (missing:${MISSING_VARS}) ${VERSION_MSG}")
endif()
endif()
endif ()
set(${_NAME}_FOUND ${${_NAME}_FOUND} PARENT_SCOPE)
set(${_NAME_UPPER}_FOUND ${${_NAME}_FOUND} PARENT_SCOPE)
endfunction()

48
CMakeModules/FindPackageMessage.cmake vendored Normal file
View File

@@ -0,0 +1,48 @@
# Distributed under the OSI-approved BSD 3-Clause License. See accompanying
# file Copyright.txt or https://cmake.org/licensing for details.
#[=======================================================================[.rst:
FindPackageMessage
------------------
.. code-block:: cmake
find_package_message(<name> "message for user" "find result details")
This function is intended to be used in FindXXX.cmake modules files.
It will print a message once for each unique find result. This is
useful for telling the user where a package was found. The first
argument specifies the name (XXX) of the package. The second argument
specifies the message to display. The third argument lists details
about the find result so that if they change the message will be
displayed again. The macro also obeys the QUIET argument to the
find_package command.
Example:
.. code-block:: cmake
if(X11_FOUND)
find_package_message(X11 "Found X11: ${X11_X11_LIB}"
"[${X11_X11_LIB}][${X11_INCLUDE_DIR}]")
else()
...
endif()
#]=======================================================================]
function(find_package_message pkg msg details)
# Avoid printing a message repeatedly for the same find result.
if(NOT ${pkg}_FIND_QUIETLY)
string(REPLACE "\n" "" details "${details}")
set(DETAILS_VAR FIND_PACKAGE_MESSAGE_DETAILS_${pkg})
if(NOT "${details}" STREQUAL "${${DETAILS_VAR}}")
# The message has not yet been printed.
message(STATUS "${msg}")
# Save the find details in the cache to avoid printing the same
# message again.
set("${DETAILS_VAR}" "${details}"
CACHE INTERNAL "Details about finding ${pkg}")
endif()
endif()
endfunction()

View File

@@ -1,22 +0,0 @@
FROM ubuntu:19.10
MAINTAINER simon987 <me@simon987.net>
RUN apt update
RUN apt install -y libglib2.0-0 libcurl4 libmagic1 libharfbuzz-bin libopenjp2-7 libarchive13 liblzma5 libzstd1 liblz4-1 \
curl libtiff5 libpng16-16 libpcre3
RUN mkdir -p /usr/share/tessdata && \
cd /usr/share/tessdata/ && \
curl -o /usr/share/tessdata/hin.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/hin.traineddata &&\
curl -o /usr/share/tessdata/jpn.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/jpn.traineddata &&\
curl -o /usr/share/tessdata/eng.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/eng.traineddata &&\
curl -o /usr/share/tessdata/fra.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/fra.traineddata &&\
curl -o /usr/share/tessdata/rus.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/rus.traineddata &&\
curl -o /usr/share/tessdata/spa.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/spa.traineddata && ls -lh
ADD sist2 /root/sist2
ENV LANG C.UTF-8
ENV LC_ALL C.UTF-8
ENTRYPOINT ["/root/sist2"]

View File

@@ -1,14 +0,0 @@
rm ./sist2 sist2_debug
cp ../sist2.gz .
gzip -d sist2.gz
strip sist2
version=$(./sist2 --version)
echo "Version ${version}"
docker build . -t simon987/sist2:${version} -t simon987/sist2:latest
docker push simon987/sist2:${version}
docker push simon987/sist2:latest
docker run --rm simon987/sist2 -v

132
README.md
View File

@@ -1,6 +1,5 @@
![GitHub](https://img.shields.io/github/license/simon987/sist2.svg)
[![CodeFactor](https://www.codefactor.io/repository/github/simon987/sist2/badge?s=05daa325188aac4eae32c786f3d9cf4e0593f822)](https://www.codefactor.io/repository/github/simon987/sist2)
[![Development snapshots](https://ci.simon987.net/app/rest/builds/buildType(Sist2_Build)/statusIcon)](https://files.simon987.net/artifacts/Sist2/Build/)
# sist2
@@ -8,124 +7,89 @@ sist2 (Simple incremental search tool)
*Warning: sist2 is in early development*
![sist2.png](docs/sist2.png)
## Features
* Fast, low memory usage, multi-threaded
* Mobile-friendly Web interface
* Fast, low memory usage
* Portable (all its features are packaged in a single executable)
* Extracts text from common file types \*
* Generates thumbnails \*
* Extracts text from common file types\*
* Generates thumbnails\*
* Incremental scanning
* Automatic tagging from file attributes via [user scripts](scripting/README.md)
* Recursive scan inside archive files \*\*
* OCR support with tesseract \*\*\*
\* See [format support](#format-support)
\*\* See [Archive files](#archive-files)
\*\*\* See [OCR](#ocr)
\* See [format support](#format-support)
## Getting Started
1. Have an Elasticsearch (>= 6.X.X) instance running
1. Download [from official website](https://www.elastic.co/downloads/elasticsearch)
1. *(or)* Run using docker:
```bash
docker run -d --name es1 --net sist2_net -p 9200:9200 \
-e "discovery.type=single-node" elasticsearch:7.5.2
```
1. *(or)* Run using docker-compose:
```yaml
elasticsearch:
image: docker.elastic.co/elasticsearch/elasticsearch:7.5.2
environment:
- discovery.type=single-node
- "ES_JAVA_OPTS=-Xms1G -Xmx2G"
```
1. Download sist2 executable
1. Download the [latest sist2 release](https://github.com/simon987/sist2/releases) *
1. *(or)* Download a [development snapshot](https://files.simon987.net/artifacts/Sist2/Build/) *(Not recommended!)*
1. *(or)* `docker pull simon987/sist2:latest`
1. Have an [Elasticsearch](https://www.elastic.co/downloads/elasticsearch) instance running
1. Download the [latest sist2 release](https://github.com/simon987/sist2/releases)
1. See [Usage guide](DOCS/USAGE.md)
*Windows users*: `sist2` runs under [WSL](https://en.wikipedia.org/wiki/Windows_Subsystem_for_Linux)
\* *Windows users*: **sist2** runs under [WSL](https://en.wikipedia.org/wiki/Windows_Subsystem_for_Linux)
*Mac users*: See [#1](https://github.com/simon987/sist2/issues/1)
## Example usage
See [Usage guide](DOCS/USAGE.md) for more details
![demo](demo.gif)
1. Scan a directory: `sist2 scan ~/Documents -o ./docs_idx`
1. Push index to Elasticsearch: `sist2 index ./docs_idx`
1. Start web interface: `sist2 web ./docs_idx`
See help page `sist2 --help` for more details.
**Scan a directory**
```bash
sist2 scan ~/Documents -o ./orig_idx/
sist2 scan --threads 4 --content-size 16384 /mnt/Pictures
sist2 scan --incremental ./orig_idx/ -o ./updated_idx/ ~/Documents
```
**Push index to Elasticsearch or file**
```bash
sist2 index --force-reset ./my_idx
sist2 index --print ./my_idx > raw_documents.ndjson
```
**Start web interface**
```bash
sist2 web --bind 0.0.0.0 --port 4321 ./my_idx1 ./my_idx2 ./my_idx3
```
## Format support
File type | Library | Content | Thumbnail | Metadata
:---|:---|:---|:---|:---
pdf,xps,cbz,cbr,fb2,epub | MuPDF | text+ocr | yes, `png` | title |
`audio/*` | ffmpeg | - | yes, `jpeg` | ID3 tags |
`video/*` | ffmpeg | - | yes, `jpeg` | title, comment, artist |
`image/*` | ffmpeg | - | yes, `jpeg` | [Common EXIF tags](https://github.com/simon987/sist2/blob/efdde2734eca9b14a54f84568863b7ffd59bdba3/src/parsing/media.c#L190) |
pdf,xps,cbz,cbr,fb2,epub | MuPDF | yes | yes, `png` | *planned* |
`audio/*` | libav | - | yes, `jpeg` | ID3 tags |
`video/*` | libav | - | yes, `jpeg` | *planned* |
`image/*` | libav | - | yes, `jpeg` | *planned* |
ttf,ttc,cff,woff,fnt,otf | Freetype2 | - | yes, `bmp` | Name & style |
`text/plain` | *(none)* | yes | no | - |
html, xml | *(none)* | yes | no | - |
tar, zip, rar, 7z, ar ... | Libarchive | yes\* | - | no |
docx, xlsx, pptx | *(none)* | yes | no | creator, modified_by, title |
mobi, azw, azw3 | libmobi | yes | no | author, title |
docx, xlsx, pptx | | *planned* | no | *planned* |
\* *See [Archive files](#archive-files)*
### Archive files
**sist2** will scan files stored into archive files (zip, tar, 7z...) as if
they were directly in the file system. Recursive (archives inside archives)
scan is also supported.
**Limitations**:
* Parsing media files with formats that require
*seek* (e.g. `.gif`, `.mp4` w/ fragmented metadata etc.) is not supported.
* Archive files are scanned sequentially, by a single thread. On systems where
**sist2** is not I/O bound, scans might be faster when larger archives are split
into smaller parts.
To check if a media file can be parsed without *seek*, execute `cat file.mp4 | ffprobe -`
### OCR
You can enable OCR support for pdf,xps,cbz,cbr,fb2,epub file types with the
`--ocr <lang>` option. Download the language data files with your
package manager (`apt install tesseract-ocr-eng`) or directly [from Github](https://github.com/tesseract-ocr/tesseract/wiki/Data-Files).
The `simon987/sist2` image comes with common languages
(hin, jpn, eng, fra, rus, spa) pre-installed.
Examples
```bash
sist2 scan --ocr jpn ~/Books/Manga/
sist2 scan --ocr eng ~/Books/Textbooks/
```
## Build from source
You can compile **sist2** by yourself if you don't want to use the pre-compiled
binaries (GCC 7+ required).
binaries.
1. Install compile-time dependencies
```bash
vcpkg install lmdb cjson glib libarchive[core,bzip2,libxml2,lz4,lzma,lzo] pthread tesseract libxml2 ffmpeg zstd gtest mongoose libuuid libmagic
*(Debian)*
```bash
apt install git cmake pkg-config libglib2.0-dev\
libssl-dev uuid-dev libavformat-dev libswscale-dev \
python3 libmagic-dev libfreetype6-dev libcurl-dev \
libbz2-dev yasm
```
*(FreeBSD)*
```bash
pkg install cmake gcc yasm gmake bash ffmpeg e2fsprogs-uuid
```
__
2. Build
```bash
git clone --recursive https://github.com/simon987/sist2/
cmake -D <VCPKG_ROOT>/scripts/buildsystems/vcpkg.cmake .
git clone --recurse-submodules https://github.com/simon987/sist2
./scripts/get_static_libs.sh
cmake .
make
```
```

1
argparse Submodule

Submodule argparse added at fafc503d23

1
cJSON Submodule

Submodule cJSON added at 2de7d04aaf

View File

@@ -1,16 +0,0 @@
#!/usr/bin/env bash
rm *.gz
rm -rf CMakeFiles CMakeCache.txt
cmake -DSIST_DEBUG=off -DCMAKE_TOOLCHAIN_FILE=/vcpkg/scripts/buildsystems/vcpkg.cmake .
make
strip sist2
gzip -9 sist2
rm -rf CMakeFiles CMakeCache.txt
cmake -DSIST_DEBUG=on -DCMAKE_TOOLCHAIN_FILE=/vcpkg/scripts/buildsystems/vcpkg.cmake .
make
cp /usr/lib/x86_64-linux-gnu/libasan.so.2.0.0 libasan.so.2
tar -czf sist2_debug.tar.gz sist2_debug libasan.so.2

BIN
demo.gif Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 18 MiB

View File

@@ -1,274 +0,0 @@
# Usage
*More examples (specifically with docker/compose) are in progress*
* [scan](#scan)
* [options](#scan-options)
* [examples](#scan-examples)
* [index format](#index-format)
* [index](#index)
* [options](#index-options)
* [examples](#index-examples)
* [web](#web)
* [options](#web-options)
* [examples](#web-examples)
* [rewrite_url](#rewrite_url)
* [link to specific indices](#link-to-specific-indices)
```
Usage: sist2 scan [OPTION]... PATH
or: sist2 index [OPTION]... INDEX
or: sist2 web [OPTION]... INDEX...
Lightning-fast file system indexer and search tool.
-h, --help show this help message and exit
-v, --version Show version and exit
--verbose Turn on logging
--very-verbose Turn on debug messages
Scan options
-t, --threads=<int> Number of threads. DEFAULT=1
-q, --quality=<flt> Thumbnail quality, on a scale of 1.0 to 31.0, 1.0 being the best. DEFAULT=5
--size=<int> Thumbnail size, in pixels. Use negative value to disable. DEFAULT=500
--content-size=<int> Number of bytes to be extracted from text documents. Use negative value to disable. DEFAULT=32768
--incremental=<str> Reuse an existing index and only scan modified files.
-o, --output=<str> Output directory. DEFAULT=index.sist2/
--rewrite-url=<str> Serve files from this url instead of from disk.
--name=<str> Index display name. DEFAULT: (name of the directory)
--depth=<int> Scan up to DEPTH subdirectories deep. Use 0 to only scan files in PATH. DEFAULT: -1
--archive=<str> Archive file mode (skip|list|shallow|recurse). skip: Don't parse, list: only get file names as text, shallow: Don't parse archives inside archives. DEFAULT: recurse
--ocr=<str> Tesseract language (use tesseract --list-langs to see which are installed on your machine)
-e, --exclude=<str> Files that match this regex will not be scanned
--fast Only index file names & mime type
Index options
--es-url=<str> Elasticsearch url with port. DEFAULT=http://localhost:9200
-p, --print Just print JSON documents to stdout.
--script-file=<str> Path to user script.
--batch-size=<int> Index batch size. DEFAULT: 100
-f, --force-reset Reset Elasticsearch mappings and settings. (You must use this option the first time you use the index command)
Web options
--es-url=<str> Elasticsearch url. DEFAULT=http://localhost:9200
--bind=<str> Listen on this address. DEFAULT=localhost:4090
--auth=<str> Basic auth in user:password format
Made by simon987 <me@simon987.net>. Released under GPL-3.0
```
## Scan
### Scan options
* `-t, --threads`
Number of threads for file parsing. **Do not set a number higher than `$(nproc)`!**.
* `-q, --quality`
Thumbnail quality, on a scale of 1.0 to 31.0, 1.0 being the best. *Does not affect PDF thumbnails quality*
* `--size`
Thumbnail size in pixels.
* `--content-size`
Number of bytes of text to be extracted from the content of files (plain text and PDFs).
Repeated whitespace and special characters do not count toward this limit.
* `--incremental`
Specify an existing index. Information about files in this index that were not modified (based on *mtime* attribute)
will be copied to the new index and will not be parsed again.
* `-o, --output` Output directory.
* `--rewrite-url` Set the `rewrite_url` option for the web module (See [rewrite_url](#rewrite_url))
* `--name` Set the `name` option for the web module
* `--depth` Maximum scan dept. Set to 0 only scan files directly in the root directory, set to -1 for infinite depth
* `--archive` Archive file mode.
* skip: Don't parse
* list: Only get file names as text
* shallow: Don't parse archives inside archives.
* recurse: Scan archives recursively (default)
* `--ocr` See [OCR](../README.md#OCR)
* `-e, --exclude` Regex pattern to exclude files. A file is excluded if the pattern matches any
part of the full absolute path.
Examples:
* `-e ".*\.ttf"`: Ignore ttf files
* `-e ".*\.(ttf|rar)"`: Ignore ttf and rar files
* `-e "^/mnt/backups/"`: Ignore all files in the `/mnt/backups/` directory
* `-e "^/mnt/Data[12]/"`: Ignore all files in the `/mnt/Data1/` and `/mnt/Data2/` directory
* `-e "(^/usr/)|(^/var/)|(^/media/DRIVE-A/tmp/)|(^/media/DRIVE-B/Trash/)"` Exclude the
`/usr`, `/var`, `/media/DRIVE-A/tmp`, `/media/DRIVE-B/Trash` directories
* `--fast` Only index file names and mime type
### Scan examples
Simple scan
```bash
sist2 scan ~/Documents
sist2 scan \
--threads 4 --content-size 16000000 --quality 1.0 --archive shallow \
--name "My Documents" --rewrite-url "http://nas.domain.local/My Documents/" \
~/Documents -o ./documents.idx/
```
Incremental scan
```
sist2 scan --incremental ./orig_idx/ -o ./updated_idx/ ~/Documents
```
### Index format
A typical `binary` type index structure looks like this:
```
documents.idx/
├── descriptor.json
├── _index_139965416830720
├── _index_139965425223424
├── _index_139965433616128
├── _index_139965442008832
└── thumbs
├── data.mdb
└── lock.mdb
```
The `_index_*` files contain the raw binary index data and are not meant to be
read by other applications. The format is generally compatible across different
sist2 versions.
The `thumbs/` folder is a [LMDB](https://en.wikipedia.org/wiki/Lightning_Memory-Mapped_Database)
database containing the thumbnails.
The `descriptor.json` file contains general information about the index. The
following fields are safe to modify manually: `root`, `name`, [rewrite_url](#rewrite_url) and `timestamp`.
*Advanced usage*
Instead of using the `scan` module, you can also import an index generated
by a third party application. The 'external' index must have the following format:
```
my_index/
├── descriptor.json
├── _index_0
└── thumbs
├── data.mdb
└── lock.mdb
```
*descriptor.json*:
```json
{
"uuid": "<valid UUID4>",
"version": "_external_v1",
"root": "(optional)",
"name": "<name>",
"rewrite_url": "(optional)",
"type": "json",
"timestamp": 1578971024
}
```
*_index_0*: NDJSON format (One json object per line)
```json
{
"_id": "unique uuid for the file",
"index": "index uuid4 (same one as descriptor.json!)",
"mime": "application/x-cbz",
"size": 14341204,
"mtime": 1578882996,
"extension": "cbz",
"name": "my_book",
"path": "path/to/books",
"content": "text contents of the book",
"title": "Title of the book",
"tag": ["genre.fiction", "author.someguy", "etc..."],
"_keyword": [
{"k": "ISBN", "v": "ABCD34789231"}
],
"_text": [
{"k": "other", "v": "This will be indexed as text"}
]
}
```
You can find the full list of supported fields [here](../src/io/serialize.c#L90)
The `_keyword.*` items will be indexed and searchable as **keyword** fields (only full matches allowed).
The `_text.*` items will be indexed and searchable as **text** fields (fuzzy searching allowed)
*thumbs/*:
LMDB key-value store. Keys are **binary** 128-bit UUID4s (`_id` field)
and values are raw image bytes.
Importing an external `binary` type index is technically possible but
it is currently unsupported and has no guaranties of back/forward compatibility.
## Index
### Index options
* `--es-url`
Elasticsearch url and port. If you are using docker, make sure that both containers are on the
same network.
* `-p, --print`
Print index in JSON format to stdout.
* `--script-file`
Path to user script. See [Scripting](scripting/README.md).
* `--batch-size=<int>`
Index batch size. Indexing is generally faster with larger batches, but payloads that
are too large will fail and additional overhead for retrying with smaller sizes may slow
down the process.
* `-f, --force-reset`
Reset Elasticsearch mappings and settings.
**(You must use this option the first time you use the index command)**.
### Index examples
**Push to elasticsearch**
```bash
sist2 index --force-reset --batch-size 1000 --es-url http://localhost:9200 ./my_index/
sist2 index ./my_index/
```
**Save index in JSON format**
```bash
sist2 index --print ./my_index/ > my_index.ndjson
```
**Inspect contents of an index**
```bash
sist2 index --print ./my_index/ | jq | less
```
## Web
### Web options
* `--es-url=<str>` Elasticsearch url.
* `--bind=<str>` Listen on this address.
* `--auth=<str>` Basic auth in user:password format
### Web examples
**Single index**
```bash
sist2 web --auth admin:hunter2 --bind 0.0.0.0:8888 my_index
```
**Multiple indices**
```bash
# Indices will be displayed in this order in the web interface
sist2 web index1 index2 index3 index4
```
### rewrite_url
When the `rewrite_url` field is not empty, the web module ignores the `root`
field and will return a HTTP redirect to `<rewrite_url><path>/<name><extension>`
instead of serving the file from disk.
Both the `root` and `rewrite_url` fields are safe to manually modify from the
`descriptor.json` file.
### Link to specific indices
To link to specific indices, you can add a list of comma-separated index name to
the URL: `?i=<name>,<name>`. By default, indices with `"(nsfw)"` in their name are
not displayed.

Binary file not shown.

Before

Width:  |  Height:  |  Size: 26 KiB

View File

@@ -1,152 +0,0 @@
## User scripts
*This document is under construction, more in-depth guide coming soon*
During the `index` step, you can use the `--script-file <script>` option to
modify documents or add user tags. This option is mainly used to
implement automatic tagging based on file attributes.
The scripting language used
([Painless Scripting Language](https://www.elastic.co/guide/en/elasticsearch/painless/7.4/index.html))
is very similar to Java, but you should be able to create user scripts
without programming experience at all if you're somewhat familiar with
regex.
This is the base structure of the documents we're working with:
```json
{
"_id": "e171405c-fdb5-4feb-bb32-82637bc32084",
"_index": "sist2",
"_type": "_doc",
"_source": {
"index": "206b3050-e821-421a-891d-12fcf6c2db0d",
"mime": "application/json",
"size": 1799,
"mtime": 1545443685,
"extension": "md",
"name": "README",
"path": "sist2/scripting",
"content": "..."
}
}
```
**Example script**
This script checks if the `genre` attribute exists, if it does
it adds the `genre.<genre>` tag.
```Java
ArrayList tags = ctx._source.tag = new ArrayList();
if (ctx._source?.genre != null) {
tags.add("genre." + ctx._source.genre.toLowerCase())
}
```
You can use `.` to create a hierarchical tag tree:
![scripting/genre_example](genre_example.png)
To use regular expressions, you need to add this line in `/etc/elasticsearch/elasticsearch.yml`
```yaml
script.painless.regex.enabled: true
```
Or, if you're using docker add `-e "script.painless.regex.enabled=true"`
**Tag color**
You can specify the color for an individual tag by appending an
hexadecimal color code (`#RRGGBBAA`) to the tag name.
### Examples
If `(20XX)` is in the file name, add the `year.<year>` tag:
```Java
ArrayList tags = ctx._source.tag = new ArrayList();
Matcher m = /[\(\.+](20[0-9]{2})[\)\.+]/.matcher(ctx._source.name);
if (m.find()) {
tags.add("year." + m.group(1))
}
```
Use default *Calibre* folder structure to infer author.
```Java
ArrayList tags = ctx._source.tag = new ArrayList();
// We expect the book path to look like this:
// /path/to/Calibre Library/Author/Title/Title - Author.pdf
if (ctx._source.name.contains("-") && ctx._source.extension == "pdf") {
String[] names = ctx._source.name.splitOnToken('-');
tags.add("author." + names[1].strip());
}
```
If the file matches a specific pattern `AAAA-000 fName1 lName1, <fName2 lName2>...`, add the `actress.<actress>` and
`studio.<studio>` tag:
```Java
ArrayList tags = ctx._source.tag = new ArrayList();
Matcher m = /([A-Z]{4})-[0-9]{3} (.*)/.matcher(ctx._source.name);
if (m.find()) {
tags.add("studio." + m.group(1));
// Take the matched group (.*), and add a tag for
// each name, separated by comma
for (String name : m.group(2).splitOnToken(',')) {
tags.add("actress." + name);
}
}
```
Set the name of the last folder (`/path/to/<studio>/file.mp4`) to `studio.<studio>` tag
```Java
ArrayList tags = ctx._source.tag = new ArrayList();
if (ctx._source.path != "") {
String[] names = ctx._source.path.splitOnToken('/');
tags.add("studio." + names[names.length-1]);
}
```
Set the name of the last folder (`/path/to/<studio>/file.mp4`) to `studio.<studio>` tag
```Java
ArrayList tags = ctx._source.tag = new ArrayList();
if (ctx._source.path != "") {
String[] names = ctx._source.path.splitOnToken('/');
tags.add("studio." + names[names.length-1]);
}
```
Parse `EXIF:F Number` tag
```Java
if (ctx._source?.exif_fnumber != null) {
String[] values = ctx._source.exif_fnumber.splitOnToken(' ');
String aperture = String.valueOf(Float.parseFloat(values[0]) / Float.parseFloat(values[1]));
if (aperture == "NaN") {
aperture = "0,0";
}
tags.add("Aperture.f/" + aperture.replace(".", ","));
}
```
Display year and months from `EXIF:DateTime` tag
```Java
if (ctx._source?.exif_datetime != null) {
SimpleDateFormat parser = new SimpleDateFormat("yyyy:MM:dd HH:mm:ss");
Date date = parser.parse(ctx._source.exif_datetime);
SimpleDateFormat yp = new SimpleDateFormat("yyyy");
SimpleDateFormat mp = new SimpleDateFormat("MMMMMMMMM");
String year = yp.format(date);
String month = mp.format(date);
tags.add("Month." + month);
tags.add("Year." + year);
}
```

Binary file not shown.

Before

Width:  |  Height:  |  Size: 889 KiB

1
lib/ffmpeg Submodule

Submodule lib/ffmpeg added at 0481a1f6e5

1
lib/mupdf Submodule

Submodule lib/mupdf added at 91782a4348

1
lib/onion Submodule

Submodule lib/onion added at d8d4cc9290

1
lmdb Submodule

Submodule lmdb added at 5c012bbe03

View File

@@ -2,14 +2,10 @@ application/arj, arj
application/base64, mme
application/binhex, hqx
application/book, boo|book
application/CDFV2-corrupt,
application/CDFV2, sdv
application/clariscad, ccad
application/commonground, dp
application/csv,
application/dicom, dcm
application/drafting, drw
application/epub+zip, epub
application/freeloader, frl
application/futuresplash, spl
application/groupwise, vew
@@ -21,6 +17,7 @@ application/inf, inf
application/java-archive, jar
application/java, class
application/javascript,
application/x-archive, a
application/json, json
application/marc, mrc
application/mbedlet, mbd
@@ -30,9 +27,7 @@ application/msword, doc|dot|w6w|wiz|word
application/netmc, mcp
application/octet-stream, bin|dump|gpg
application/oda, oda
application/ogg, ogv
application/pdf, pdf
application/pgp-keys,
application/pgp-signature, pgp
application/pkcs7-signature, p7s
application/pkix-cert, cer|crt
@@ -48,10 +43,6 @@ application/vda, vda
application/vnd.fdf, fdf
application/vnd.font-fontforge-sfd, sfd
application/vnd.hp-hpgl, hgl|hpg|hpgl
application/vnd.iccprofile, icm
application/vnd.iccprofile, icm
application/vnd.lotus-1-2-3,
application/vnd.ms-cab-compressed, cab
application/vnd.ms-excel, xlb|xlc|xll|xlm|xls|xlw
application/vnd.ms-fontobject, eot
application/vnd.ms-opentype, otf
@@ -63,75 +54,45 @@ application/vnd.ms-project, mpp
application/vnd.oasis.opendocument.base, odb
application/vnd.oasis.opendocument.formula, odf
application/vnd.oasis.opendocument.graphics, odg
application/vnd.oasis.opendocument.presentation, odp
application/vnd.oasis.opendocument.spreadsheet, ods
application/vnd.oasis.opendocument.text, odt
application/vnd.openxmlformats-officedocument.presentationml.presentation, pptx
application/vnd.openxmlformats-officedocument.spreadsheetml.sheet, xlsx
application/vnd.openxmlformats-officedocument.wordprocessingml.document, docx
application/vnd.symbian.install,
application/vnd.tcpdump.pcap, pcap
application/vnd.wap.wmlc, wmlc
application/vnd.wap.wmlscriptc, wmlsc
application/vnd.xara, web
application/vocaltec-media-desc, vmd
application/vocaltec-media-file, vmf
application/warc, warc
application/winhelp, hlp
application/wordperfect6.0, w60
application/wordperfect6.1, w61
application/wordperfect, wp|wp5|wp6|wpd
application/x-123, wk1
application/x-7z-compressed, 7z
application/x-aim, aim
application/x-apple-diskimage,
application/x-arc,
application/x-archive, a
application/x-atari-7800-rom, a78
application/x-authorware-bin, aab
application/x-authorware-map, aam
application/x-authorware-seg, aas
application/x-avira-qua,
application/x-bcpio, bcpio
application/x-bittorrent, torrent
application/x-bsh, bsh
application/x-bytecode.python, pyc
application/x-bzip2, boz|bz2
application/x-bzip, bz
application/x-cbr, cbr
application/x-cbz, cbz
application/x-cdlink, vcd
application/x-chat, cha|chat
application/x-chrome-extension,
application/x-cocoa, cco
application/x-conference, nsc
application/x-coredump,
application/x-cpio, cpio
application/x-dbf, dbf
application/x-dbt,
application/x-debian-package, deb
application/x-deepv, deepv
application/x-director, dcr|dir|dxr
application/x-dmp, dmp
application/x-dosdriver,
application/x-dosexec, dll
application/x-dvi, dvi
application/x-elc, elc
application/x-empty,
application/x-envoy, env|evy
application/x-esrehber, es
application/x-excel, xla|xld|xlk|xlt|xlv
application/x-executable, exe
application/x-font-gdos,
application/x-font-pf2, pf2
application/x-font-pfm, pfm
application/x-font-sfn,
application/x-font-ttf, ttf|ttc
application/x-fptapplication/x-dbt,
application/x-freelance, pre
application/x-gamecube-rom,
application/x-gdbm,
application/x-gettext-translation,
application/x-git,
application/x-gsp, gsp
application/x-gss, gss
@@ -141,68 +102,46 @@ application/x-hdf, hdf
application/x-helpfile, help
application/x-httpd-imap, imap
application/x-ima, ima
application/x-innosetup,
application/x-internett-signup, ins
application/x-inventor, iv
application/x-ip2, ip
application/x-java-applet,
application/x-java-commerce, jcm
application/x-java-image,
application/x-java-jmod, jmod
application/x-java-keystore,
application/x-kdelnk,
application/x-koan, skd|skm|skp|skt
application/x-latex, latex|ltx
application/x-livescreen, ivy
application/x-lotus, wq1
application/x-lz4+json, jsonlz4
application/x-lz4, lz4
application/x-lz4, lz4
application/x-lzh-compressed,
application/x-lzh, lzh
application/x-lzip, lz
application/x-lzma, lzma
application/x-lzop, lzo
application/x-lzx, lzx
application/x-mach-binary, jnilib|dylib
application/x-mach-executable,
application/x-magic-cap-package-1.0, mc$
application/x-mathcad, mcd
application/x-maxis-dbpf,
application/x-meme, mm
application/x-midi, midi
application/x-mif, mif
application/x-mix-transfer, nix
application/xml, opf
application/x-mobipocket-ebook, mobi
application/vnd.amazon.mobi8-ebook, azw|azw3
application/x-msaccess, accdb
application/x-ms-compress-szdd, fon
application/x-ms-pdb, pdb
application/x-ms-reader, lit
application/x-n64-rom, z64
application/x-navi-animation, ani
application/x-navidoc, nvd
application/x-navimap, map
application/x-navistyle, stl
application/x-nes-rom, nes
application/x-netcdf, cdf|nc
application/x-newton-compatible-pkg, pkg
application/x-nintendo-ds-rom,
application/x-object, o
application/x-omcdatamaker, omcd
application/x-omc, omc
application/x-omcregerator, omcr
application/x-pagemaker, pm4|pm5
application/x-pcl, pcl
application/x-pgp-keyring,
application/x-pixclscript, plx
application/x-pkcs7-certreqresp, p7r
application/x-pkcs7-signature, p7a
application/x-project, mpc|mpt|mpv|mpx
application/x-qpro, wb1
application/x-rar, rar
application/x-rpm, rpm
application/x-sdp, sdp
application/x-sea, sea
application/x-seelogo, sl
@@ -210,17 +149,12 @@ application/x-setupscript,
application/x-sharedlib, so
application/x-shar, shar
application/x-shockwave-flash, swf
application/x-snappy-framed,
application/x-sprite, spr|sprite
application/x-sqlite3,
application/x-stargallery-thm,
application/x-stuffit, sit
application/x-sv4cpio, sv4cpio
application/x-sv4crc, sv4crc
application/x-tar, tar
application/x-tbook, sbk|tbk
application/x-terminfo,
application/x-terminfo2,
application/x-texinfo, texi|texinfo
application/x-tex-tfm, tfm
application/x-ustar, ustar
@@ -229,22 +163,16 @@ application/x-vnd.audioexplosion.mzz, mzz
application/x-vnd.ls-xpix, xpix
application/x-vrml, vrml
application/x-wais-source, src|wsrc
application/x-wine-extension-ini,
application/x-wintalk, wtk
application/x-world, svr
application/x-wri, wri
application/x-x509-ca-cert, der
application/x-xz, xz
application/x-zip,
application/x-zstd, zst
application/zip, zip
application/zlib, z
!audio/basic, au
audio/it, it
audio/make, funk|my|pfunk
audio/midi, kar
audio/mid, rmi
audio/mp4, m4b
audio/mpeg, m2a|mpa
audio/ogg, ogg
audio/s3m, s3m
@@ -252,10 +180,7 @@ audio/tsp-audio, tsi
audio/tsplayer, tsp
audio/vnd.qcelp, qcp
audio/voxware, vox
audio/x-aiff, aiff|aif
audio/x-flac, flac
audio/x-gsm, gsd|gsm
audio/x-hx-aac-adts,
audio/x-jam, jam
audio/x-liveaudio, lam
audio/x-m4a, m4a
@@ -269,24 +194,17 @@ audio/x-nspaudio, lma
audio/x-pn-realaudio, ram|rm|rmm|rmp
audio/x-psid, sid
audio/x-realaudio, ra
audio/x-s3m,
audio/x-twinvq-plugin, vqe|vql
audio/x-twinvq, vqf
audio/x-voc, voc
audio/x-wav, wav
!audio/x-xbox360-executable, xex
!audio/x-xbox-executable, xbe
font/otf,
font/sfnt,
font/woff2, woff2
font/woff, woff
image/bmp,
image/cmu-raster, rast
image/fif, fif
image/florian, flo|turbot
image/g3fax, g3
image/gif, gif
image/heic, heic
image/ief, ief|iefs
image/jpeg, jfif|jfif-tbnl|jpe|jpeg|jpg
image/jutvision, jut
@@ -295,9 +213,6 @@ image/pict, pic|pict
image/png, png|x-png
!image/svg, svg
!image/svg+xml,
image/tiff,
!image/vnd.adobe.photoshop, psd
!image/vnd.djvu, djvu
image/vnd.fpx, fpx
image/vnd.microsoft.icon,
image/vnd.rn-realflash, rf
@@ -305,15 +220,9 @@ image/vnd.rn-realpix, rp
image/vnd.wap.wbmp, wbmp
image/vnd.xiff, xif
image/webp, webp
image/wmf,
image/x-3ds, 3ds
image/x-award-bioslogo,
image/x-cmu-raster, ras
image/x-cur, tga
image/x-dwg, dwg|dxf|svf
image/x-eps,
image/x-exr, exr
image/x-gem,
image/x-icns,
!image/x-icon, ico
image/x-jg, art
@@ -327,33 +236,34 @@ image/x-portable-graymap, pgm
image/x-portable-pixmap, ppm
image/x-quicktime, qif|qti|qtif
image/x-rgb, rgb
image/x-tga,
image/x-tiff, tif|tiff
image/x-win-bitmap,
image/tiff,
!image/x-xcf, xcf
!image/x-xpixmap, xpm
image/x-xwindowdump, xwd
message/news,
message/rfc822, mht|mhtml|mime
model/vnd.dwf, dwf
model/vnd.gdl, gdl
model/vnd.gs.gdl, gdsl
model/vrml, wrz
model/x-pov, pov
text/asp, asp
text/css, css
text/x-sass, sass
text/x-scss, scss
text/html, acgi|htm|html|htmls|htx|shtml
text/javascript, js
text/mcf, mcf
text/pascal, pas
text/PGP,
text/plain, com|cmd|conf|def|g|idc|list|lst|mar|sdml|text|txt|md|groovy|license|properties|desktop|ini|rst|cmake|ipynb|readme|less|lo|go|yml|d|cs|hpp|srt|nfo|sfv|m3u|csv|eml
text/plain, com|cmd|conf|def|g|idc|list|lst|mar|sdml|text|txt|md|groovy|license|properties|desktop|ini|rst|cmake|ipynb|readme|less|lo|go|yml|d|cs|hpp|srt
text/richtext, rt|rtf|rtx
text/rtf,
text/scriplet, wsc
text/x-awk, awk
!video/x-jng, jng
video/x-mng, mng
image/x-cur, tga
image/x-xwindowdump, xwd
!image/vnd.adobe.photoshop, psd
text/tab-separated-values, tsv
text/troff, man|me|ms|roff|t|tr
text/uri-list, uji|unis|uri|uris
text/uri-list, uni|unis|uri|uris
text/vnd.abc, abc
text/vnd.fmi.flexstor, flx
text/vnd.wap.wmlscript, wmls
@@ -362,7 +272,6 @@ text/webviewhtml, htt
text/x-Algol68,
text/x-asm, asm|s
text/x-audiosoft-intra, aip
text/x-awk, awk
text/x-bcpl,
text/x-c, c|cc|h
text/x-c++, cpp|cxx|c++
@@ -377,31 +286,23 @@ text/x-makefile, am|mak
text/xml, xml|pom|iml|plist
text/x-m, m
text/x-msdos-batch, bat
text/x-ms-regedit, reg
text/x-objective-c,
text/x-pascal, p
text/x-perl, pl
text/x-php, php
text/x-po, po
text/x-python, py
text/x-ruby, rb
text/x-sass, sass
text/x-scss, scss
text/x-server-parsed-html, ssi
text/x-setext, etx
text/x-sgml, sgm|sgml
text/x-shellscript, sh
text/x-speech, talk
text/x-tcl,
text/x-tex, tex
text/x-uil, uil
text/x-uuencode, uue
text/x-vcalendar, vcs
text/x-vcard, vcf
video/animaflex, afl
video/avi, avi
video/avs-video, avs
video/MP2T,
video/mp4, mp4
video/mpeg, m1v|m2v|mpe|mpeg|mpg
video/quicktime, moov|mov|qt
@@ -416,16 +317,46 @@ video/x-atomic3d-feature, fmf
video/x-dl, dl
video/x-dv, dif|dv
video/x-fli, fli
video/x-flv, flv
video/x-isvideo, isu
!video/x-jng, jng
video/x-m4v, m4v
video/x-matroska, mkv
video/x-mng, mng
video/x-motion-jpeg, mjpg
video/x-ms-asf, asf|asx|wmv
video/x-msvideo, divx
video/x-ms-asf, asf|asx
video/x-qtc, qtc
video/x-sgi-movie, movie|mv
x-epoc/x-sisx-app,
application/x-zstd-dictionary,
application/x-7z-compressed, 7z
application/vnd.openxmlformats-officedocument.wordprocessingml.document, docx
text/x-po, po
application/x-rpm, rpm
application/x-debian-package, deb
application/vnd.iccprofile, icm
application/dicom, dcm
image/x-exr, exr
application/vnd.iccprofile, icm
video/x-matroska, mkv
application/x-empty,
model/vnd.gdl, gdl
model/vnd.gs.gdl, gdsl
font/woff, woff
font/woff2, woff2
application/epub+zip, epub
application/x-mobipocket-ebook, mobi
audio/x-flac, flac
application/x-rar, rar
video/x-msvideo, divx
video/x-flv, flv
application/x-kdelnk,
text/x-tcl,
application/ogg, ogv
application/vnd.openxmlformats-officedocument.spreadsheetml.sheet, xlsx
application/vnd.ms-cab-compressed, cab
audio/mp4, m4b
!image/vnd.djvu, djvu
application/x-ms-reader, lit
application/CDFV2-corrupt,
text/x-vcard, vcf
application/x-innosetup,
application/winhelp, hlp
image/x-tga,
application/x-wine-extension-ini,
application/x-cbz, cbz
application/x-cbr, cbr
application/x-ms-compress-szdd, fon
1 application/arj arj
2 application/base64 mme
3 application/binhex hqx
4 application/book boo|book
application/CDFV2-corrupt
5 application/CDFV2 sdv
6 application/clariscad ccad
7 application/commonground dp
application/csv
application/dicom dcm
8 application/drafting drw
application/epub+zip epub
9 application/freeloader frl
10 application/futuresplash spl
11 application/groupwise vew
17 application/java-archive jar
18 application/java class
19 application/javascript
20 application/x-archive a
21 application/json json
22 application/marc mrc
23 application/mbedlet mbd
27 application/netmc mcp
28 application/octet-stream bin|dump|gpg
29 application/oda oda
application/ogg ogv
30 application/pdf pdf
application/pgp-keys
31 application/pgp-signature pgp
32 application/pkcs7-signature p7s
33 application/pkix-cert cer|crt
43 application/vnd.fdf fdf
44 application/vnd.font-fontforge-sfd sfd
45 application/vnd.hp-hpgl hgl|hpg|hpgl
application/vnd.iccprofile icm
application/vnd.iccprofile icm
application/vnd.lotus-1-2-3
application/vnd.ms-cab-compressed cab
46 application/vnd.ms-excel xlb|xlc|xll|xlm|xls|xlw
47 application/vnd.ms-fontobject eot
48 application/vnd.ms-opentype otf
54 application/vnd.oasis.opendocument.base odb
55 application/vnd.oasis.opendocument.formula odf
56 application/vnd.oasis.opendocument.graphics odg
application/vnd.oasis.opendocument.presentation odp
application/vnd.oasis.opendocument.spreadsheet ods
57 application/vnd.oasis.opendocument.text odt
application/vnd.openxmlformats-officedocument.presentationml.presentation pptx
application/vnd.openxmlformats-officedocument.spreadsheetml.sheet xlsx
application/vnd.openxmlformats-officedocument.wordprocessingml.document docx
application/vnd.symbian.install
application/vnd.tcpdump.pcap pcap
58 application/vnd.wap.wmlc wmlc
59 application/vnd.wap.wmlscriptc wmlsc
60 application/vnd.xara web
61 application/vocaltec-media-desc vmd
62 application/vocaltec-media-file vmf
application/warc warc
application/winhelp hlp
63 application/wordperfect6.0 w60
64 application/wordperfect6.1 w61
65 application/wordperfect wp|wp5|wp6|wpd
66 application/x-123 wk1
application/x-7z-compressed 7z
67 application/x-aim aim
application/x-apple-diskimage
application/x-arc
application/x-archive a
application/x-atari-7800-rom a78
68 application/x-authorware-bin aab
69 application/x-authorware-map aam
70 application/x-authorware-seg aas
application/x-avira-qua
71 application/x-bcpio bcpio
72 application/x-bittorrent torrent
73 application/x-bsh bsh
74 application/x-bytecode.python pyc
75 application/x-bzip2 boz|bz2
76 application/x-bzip bz
application/x-cbr cbr
application/x-cbz cbz
77 application/x-cdlink vcd
78 application/x-chat cha|chat
application/x-chrome-extension
79 application/x-cocoa cco
80 application/x-conference nsc
application/x-coredump
81 application/x-cpio cpio
82 application/x-dbf dbf
83 application/x-dbt
application/x-debian-package deb
84 application/x-deepv deepv
85 application/x-director dcr|dir|dxr
application/x-dmp dmp
application/x-dosdriver
86 application/x-dosexec dll
87 application/x-dvi dvi
88 application/x-elc elc
application/x-empty
89 application/x-envoy env|evy
90 application/x-esrehber es
91 application/x-excel xla|xld|xlk|xlt|xlv
92 application/x-executable exe
application/x-font-gdos
application/x-font-pf2 pf2
application/x-font-pfm pfm
93 application/x-font-sfn
94 application/x-font-ttf ttf|ttc
application/x-fptapplication/x-dbt
95 application/x-freelance pre
application/x-gamecube-rom
application/x-gdbm
application/x-gettext-translation
96 application/x-git
97 application/x-gsp gsp
98 application/x-gss gss
102 application/x-helpfile help
103 application/x-httpd-imap imap
104 application/x-ima ima
application/x-innosetup
105 application/x-internett-signup ins
106 application/x-inventor iv
107 application/x-ip2 ip
108 application/x-java-applet
109 application/x-java-commerce jcm
110 application/x-java-image
application/x-java-jmod jmod
111 application/x-java-keystore
application/x-kdelnk
112 application/x-koan skd|skm|skp|skt
113 application/x-latex latex|ltx
114 application/x-livescreen ivy
115 application/x-lotus wq1
application/x-lz4+json jsonlz4
application/x-lz4 lz4
application/x-lz4 lz4
application/x-lzh-compressed
116 application/x-lzh lzh
application/x-lzip lz
application/x-lzma lzma
application/x-lzop lzo
117 application/x-lzx lzx
118 application/x-mach-binary jnilib|dylib
119 application/x-mach-executable
120 application/x-magic-cap-package-1.0 mc$
121 application/x-mathcad mcd
application/x-maxis-dbpf
122 application/x-meme mm
123 application/x-midi midi
124 application/x-mif mif
125 application/x-mix-transfer nix
126 application/xml opf
application/x-mobipocket-ebook mobi
application/vnd.amazon.mobi8-ebook azw|azw3
application/x-msaccess accdb
application/x-ms-compress-szdd fon
127 application/x-ms-pdb pdb
application/x-ms-reader lit
application/x-n64-rom z64
128 application/x-navi-animation ani
129 application/x-navidoc nvd
130 application/x-navimap map
131 application/x-navistyle stl
application/x-nes-rom nes
132 application/x-netcdf cdf|nc
133 application/x-newton-compatible-pkg pkg
application/x-nintendo-ds-rom
134 application/x-object o
135 application/x-omcdatamaker omcd
136 application/x-omc omc
137 application/x-omcregerator omcr
138 application/x-pagemaker pm4|pm5
139 application/x-pcl pcl
application/x-pgp-keyring
140 application/x-pixclscript plx
141 application/x-pkcs7-certreqresp p7r
142 application/x-pkcs7-signature p7a
143 application/x-project mpc|mpt|mpv|mpx
144 application/x-qpro wb1
application/x-rar rar
application/x-rpm rpm
145 application/x-sdp sdp
146 application/x-sea sea
147 application/x-seelogo sl
149 application/x-sharedlib so
150 application/x-shar shar
151 application/x-shockwave-flash swf
application/x-snappy-framed
152 application/x-sprite spr|sprite
153 application/x-sqlite3
application/x-stargallery-thm
application/x-stuffit sit
154 application/x-sv4cpio sv4cpio
155 application/x-sv4crc sv4crc
156 application/x-tar tar
157 application/x-tbook sbk|tbk
application/x-terminfo
application/x-terminfo2
158 application/x-texinfo texi|texinfo
159 application/x-tex-tfm tfm
160 application/x-ustar ustar
163 application/x-vnd.ls-xpix xpix
164 application/x-vrml vrml
165 application/x-wais-source src|wsrc
application/x-wine-extension-ini
166 application/x-wintalk wtk
167 application/x-world svr
168 application/x-wri wri
169 application/x-x509-ca-cert der
170 application/x-xz xz
application/x-zip
application/x-zstd zst
171 application/zip zip
application/zlib z
!audio/basic au
172 audio/it it
173 audio/make funk|my|pfunk
174 audio/midi kar
175 audio/mid rmi
audio/mp4 m4b
176 audio/mpeg m2a|mpa
177 audio/ogg ogg
178 audio/s3m s3m
180 audio/tsplayer tsp
181 audio/vnd.qcelp qcp
182 audio/voxware vox
audio/x-aiff aiff|aif
audio/x-flac flac
183 audio/x-gsm gsd|gsm
audio/x-hx-aac-adts
184 audio/x-jam jam
185 audio/x-liveaudio lam
186 audio/x-m4a m4a
194 audio/x-pn-realaudio ram|rm|rmm|rmp
195 audio/x-psid sid
196 audio/x-realaudio ra
audio/x-s3m
197 audio/x-twinvq-plugin vqe|vql
198 audio/x-twinvq vqf
199 audio/x-voc voc
200 audio/x-wav wav
!audio/x-xbox360-executable xex
!audio/x-xbox-executable xbe
201 font/otf
202 font/sfnt
font/woff2 woff2
font/woff woff
image/bmp
203 image/cmu-raster rast
204 image/fif fif
205 image/florian flo|turbot
206 image/g3fax g3
207 image/gif gif
image/heic heic
208 image/ief ief|iefs
209 image/jpeg jfif|jfif-tbnl|jpe|jpeg|jpg
210 image/jutvision jut
213 image/png png|x-png
214 !image/svg svg
215 !image/svg+xml
image/tiff
!image/vnd.adobe.photoshop psd
!image/vnd.djvu djvu
216 image/vnd.fpx fpx
217 image/vnd.microsoft.icon
218 image/vnd.rn-realflash rf
220 image/vnd.wap.wbmp wbmp
221 image/vnd.xiff xif
222 image/webp webp
image/wmf
image/x-3ds 3ds
image/x-award-bioslogo
223 image/x-cmu-raster ras
image/x-cur tga
224 image/x-dwg dwg|dxf|svf
225 image/x-eps
image/x-exr exr
image/x-gem
226 image/x-icns
227 !image/x-icon ico
228 image/x-jg art
236 image/x-portable-pixmap ppm
237 image/x-quicktime qif|qti|qtif
238 image/x-rgb rgb
image/x-tga
239 image/x-tiff tif|tiff
240 image/x-win-bitmap image/tiff
241 !image/x-xcf xcf
242 !image/x-xpixmap xpm
image/x-xwindowdump xwd
message/news
243 message/rfc822 mht|mhtml|mime
244 model/vnd.dwf dwf
model/vnd.gdl gdl
model/vnd.gs.gdl gdsl
245 model/vrml wrz
246 model/x-pov pov
247 text/asp asp
248 text/css css
249 text/x-sass sass
250 text/x-scss scss
251 text/html acgi|htm|html|htmls|htx|shtml
252 text/javascript js
253 text/mcf mcf
254 text/pascal pas
255 text/PGP text/plain com|cmd|conf|def|g|idc|list|lst|mar|sdml|text|txt|md|groovy|license|properties|desktop|ini|rst|cmake|ipynb|readme|less|lo|go|yml|d|cs|hpp|srt
text/plain com|cmd|conf|def|g|idc|list|lst|mar|sdml|text|txt|md|groovy|license|properties|desktop|ini|rst|cmake|ipynb|readme|less|lo|go|yml|d|cs|hpp|srt|nfo|sfv|m3u|csv|eml
256 text/richtext rt|rtf|rtx
text/rtf
257 text/scriplet wsc
258 text/x-awk awk
259 !video/x-jng jng
260 video/x-mng mng
261 image/x-cur tga
262 image/x-xwindowdump xwd
263 !image/vnd.adobe.photoshop psd
264 text/tab-separated-values tsv
265 text/troff man|me|ms|roff|t|tr
266 text/uri-list uji|unis|uri|uris uni|unis|uri|uris
267 text/vnd.abc abc
268 text/vnd.fmi.flexstor flx
269 text/vnd.wap.wmlscript wmls
272 text/x-Algol68
273 text/x-asm asm|s
274 text/x-audiosoft-intra aip
text/x-awk awk
275 text/x-bcpl
276 text/x-c c|cc|h
277 text/x-c++ cpp|cxx|c++
286 text/xml xml|pom|iml|plist
287 text/x-m m
288 text/x-msdos-batch bat
text/x-ms-regedit reg
text/x-objective-c
289 text/x-pascal p
290 text/x-perl pl
291 text/x-php php
text/x-po po
292 text/x-python py
293 text/x-ruby rb
text/x-sass sass
text/x-scss scss
294 text/x-server-parsed-html ssi
295 text/x-setext etx
296 text/x-sgml sgm|sgml
297 text/x-shellscript sh
298 text/x-speech talk
text/x-tcl
299 text/x-tex tex
300 text/x-uil uil
301 text/x-uuencode uue
302 text/x-vcalendar vcs
text/x-vcard vcf
303 video/animaflex afl
304 video/avi avi
305 video/avs-video avs
video/MP2T
306 video/mp4 mp4
307 video/mpeg m1v|m2v|mpe|mpeg|mpg
308 video/quicktime moov|mov|qt
317 video/x-dl dl
318 video/x-dv dif|dv
319 video/x-fli fli
video/x-flv flv
320 video/x-isvideo isu
!video/x-jng jng
video/x-m4v m4v
video/x-matroska mkv
video/x-mng mng
321 video/x-motion-jpeg mjpg
322 video/x-ms-asf asf|asx|wmv asf|asx
video/x-msvideo divx
323 video/x-qtc qtc
324 video/x-sgi-movie movie|mv
325 x-epoc/x-sisx-app application/x-7z-compressed 7z
326 application/x-zstd-dictionary application/vnd.openxmlformats-officedocument.wordprocessingml.document docx
327 text/x-po po
328 application/x-rpm rpm
329 application/x-debian-package deb
330 application/vnd.iccprofile icm
331 application/dicom dcm
332 image/x-exr exr
333 application/vnd.iccprofile icm
334 video/x-matroska mkv
335 application/x-empty
336 model/vnd.gdl gdl
337 model/vnd.gs.gdl gdsl
338 font/woff woff
339 font/woff2 woff2
340 application/epub+zip epub
341 application/x-mobipocket-ebook mobi
342 audio/x-flac flac
343 application/x-rar rar
344 video/x-msvideo divx
345 video/x-flv flv
346 application/x-kdelnk
347 text/x-tcl
348 application/ogg ogv
349 application/vnd.openxmlformats-officedocument.spreadsheetml.sheet xlsx
350 application/vnd.ms-cab-compressed cab
351 audio/mp4 m4b
352 !image/vnd.djvu djvu
353 application/x-ms-reader lit
354 application/CDFV2-corrupt
355 text/x-vcard vcf
356 application/x-innosetup
357 application/winhelp hlp
358 image/x-tga
359 application/x-wine-extension-ini
360 application/x-cbz cbz
361 application/x-cbr cbr
362 application/x-ms-compress-szdd fon

View File

@@ -1,53 +1,31 @@
{
"properties": {
"_tie": {
"type": "keyword",
"doc_values": true
},
"_depth": {
"type": "integer"
},
"path": {
"type": "text",
"analyzer": "path_analyzer",
"fielddata": true,
"fields": {
"nGram": {
"type": "text",
"analyzer": "my_nGram"
},
"text": {
"type": "text",
"analyzer": "content_analyzer"
}
}
"copy_to": "suggest-path"
},
"suggest-path": {
"type": "completion",
"analyzer": "keyword"
},
"mime": {
"type": "keyword"
},
"thumbnail": {
"type": "keyword",
"index": false
},
"videoc": {
"type": "keyword",
"index": false
"type": "keyword"
},
"audioc": {
"type": "keyword",
"index": false
"type": "keyword"
},
"duration": {
"type": "float",
"index": false
"type": "float"
},
"width": {
"type": "integer",
"index": false
"type": "integer"
},
"height": {
"type": "integer",
"index": false
"type": "integer"
},
"mtime": {
"type": "integer"
@@ -92,23 +70,6 @@
"analyzer": "my_nGram",
"type": "text"
},
"_keyword.*": {
"type": "keyword"
},
"_text.*": {
"analyzer": "content_analyzer",
"type": "text",
"fields": {
"nGram": {
"type": "text",
"analyzer": "my_nGram"
}
}
},
"_url": {
"type": "keyword",
"index": false
},
"content": {
"analyzer": "content_analyzer",
"type": "text",
@@ -119,39 +80,6 @@
"analyzer": "my_nGram"
}
}
},
"tag": {
"type": "keyword"
},
"exif_make": {
"type": "text"
},
"exif_model": {
"type": "text"
},
"exif:software": {
"type": "text"
},
"exif_exposure_time": {
"type": "keyword"
},
"exif_fnumber": {
"type": "keyword"
},
"exif_iso_speed_ratings": {
"type": "keyword"
},
"exif_focal_length": {
"type": "keyword"
},
"exif_user_comment": {
"type": "text"
},
"author": {
"type": "text"
},
"modified_by": {
"type": "text"
}
}
}

View File

@@ -1,10 +0,0 @@
{
"description": "Copy _id to _tie, save path depth",
"processors": [
{
"script": {
"source": "ctx._tie = ctx._id; ctx._depth = ctx.path.length() == 0 ? 0 : 1 + ctx.path.length() - ctx.path.replace(\"/\", \"\").length();"
}
}
]
}

View File

@@ -21,12 +21,6 @@
"lowercase"
]
},
"case_insensitive_kw_analyzer": {
"tokenizer": "keyword",
"filter": [
"lowercase"
]
},
"my_nGram": {
"tokenizer": "my_nGram_tokenizer",
"filter": [

View File

@@ -2,15 +2,15 @@
rm -rf index.sist2/
rm src/static/js/bundle.js 2> /dev/null
cat `ls src/static/js/*.min.js` > src/static/js/bundle.js
cat src/static/js/{util,dom,search}.js >> src/static/js/bundle.js
rm web/js/bundle.js 2> /dev/null
cat `ls web/js/*.min.js` > web/js/bundle.js
cat web/js/{util,dom,search}.js >> web/js/bundle.js
rm src/static/css/bundle*.css 2> /dev/null
cat src/static/css/*.min.css > src/static/css/bundle.css
cat src/static/css/light.css >> src/static/css/bundle.css
cat src/static/css/*.min.css > src/static/css/bundle_dark.css
cat src/static/css/dark.css >> src/static/css/bundle_dark.css
rm web/css/bundle*.css 2> /dev/null
cat web/css/*.min.css > web/css/bundle.css
cat web/css/light.css >> web/css/bundle.css
cat web/css/*.min.css > web/css/bundle_dark.css
cat web/css/dark.css >> web/css/bundle_dark.css
python3 scripts/mime.py > src/parsing/mime_generated.c
python3 scripts/serve_static.py > src/web/static_generated.c

57
scripts/get_static_libs.sh Executable file
View File

@@ -0,0 +1,57 @@
#!/usr/bin/env bash
cd lib
cd mupdf
HAVE_X11=no HAVE_GLUT=no make -j 4
cd ..
mv mupdf/build/release/libmupdf.a .
mv mupdf/build/release/libmupdf-third.a .
# ffmpeg
cd ffmpeg
./configure --disable-shared --enable-static --disable-ffmpeg --disable-ffplay \
--disable-ffprobe --disable-doc\
--disable-manpages --disable-postproc --disable-avfilter \
--disable-alsa --disable-lzma --disable-xlib --disable-debug\
--disable-vdpau --disable-vaapi --disable-sdl2 --disable-network
make -j 4
cd ..
mv ffmpeg/libavcodec/libavcodec.a .
mv ffmpeg/libavformat/libavformat.a .
mv ffmpeg/libavutil/libavutil.a .
mv ffmpeg/libswresample/libswresample.a .
mv ffmpeg/libswscale/libswscale.a .
# onion
cd onion
mkdir build 2> /dev/null
cd build
cmake -DONION_USE_SSL=false -DONION_USE_PAM=false -DONION_USE_PNG=false -DONION_USE_JPEG=false \
-DONION_USE_JPEG=false -DONION_USE_XML2=false -DONION_USE_SYSTEMD=false -DONION_USE_SQLITE3=false \
-DONION_USE_REDIS=false -DONION_USE_GC=false -DONION_USE_TESTS=false -DONION_EXAMPLES=false \
-DONION_USE_BINDINGS_CPP=false ..
make -j 4
cd ../..
mv onion/build/src/onion/libonion_static.a .
#bzip2
git clone https://github.com/enthought/bzip2-1.0.6
cd bzip2-1.0.6
make -j 4
cd ..
mv bzip2-1.0.6/libbz2.a .
# magic
git clone https://github.com/threatstack/libmagic
cd libmagic
./autogen.sh
./configure --enable-static --disable-shared
make -j 4
cd ..
mv libmagic/src/.libs/libmagic.a .
cd ..

View File

@@ -0,0 +1,44 @@
#!/usr/bin/env bash
cd lib
# mupdf
cd mupdf
HAVE_X11=no HAVE_GLUT=no gmake -j 4
cd ..
mv mupdf/build/release/libmupdf.a .
mv mupdf/build/release/libmupdf-third.a .
# ffmpeg
cd ffmpeg
./configure --disable-shared --enable-static --disable-ffmpeg --disable-ffplay \
--disable-ffprobe --disable-doc\
--disable-manpages --disable-postproc --disable-avfilter \
--disable-alsa --disable-lzma --disable-xlib --disable-debug\
--disable-vdpau --disable-vaapi --disable-sdl2 --disable-network
gmake -j 4
cd ..
mv ffmpeg/libavcodec/libavcodec.a .
mv ffmpeg/libavformat/libavformat.a .
mv ffmpeg/libavutil/libavutil.a .
mv ffmpeg/libswresample/libswresample.a .
mv ffmpeg/libswscale/libswscale.a .
#bzip2
git clone https://github.com/enthought/bzip2-1.0.6
cd bzip2-1.0.6
make -j 4
cd ..
mv bzip2-1.0.6/libbz2.a .
# magic
git clone https://github.com/threatstack/libmagic
cd libmagic
./autogen.sh
./configure --enable-static --disable-shared
make -j 4
cd ..
mv libmagic/src/.libs/libmagic.a .
cd ..

View File

@@ -1,9 +1,6 @@
import json
files = [
"schema/mappings.json",
"schema/settings.json",
"schema/pipeline.json",
]
@@ -12,7 +9,6 @@ def clean(filepath):
for file in files:
with open(file, "r") as f:
data = json.dumps(json.load(f), separators=(",", ":")).encode()
data += b'\0'
with open(file, "rb") as f:
data = f.read()
print("char %s[%d] = {%s};" % (clean(file), len(data), ",".join(str(int(b)) for b in data)))

View File

@@ -12,8 +12,7 @@ major_mime = {
"audio": 7,
"image": 8,
"text": 9,
"application": 10,
"x-epoc": 11,
"application": 10
}
pdf = (
@@ -34,45 +33,6 @@ font = (
"font/woff2"
)
# Archive "formats"
archive = (
"application/x-tar",
"application/zip",
"application/x-rar",
"application/x-arc",
"application/x-warc",
"application/x-7z-compressed",
)
# Archive "filters"
arc_filter = (
"application/gzip",
"application/x-bzip2",
"application/x-xz",
"application/x-zstd",
"application/x-lzma",
"application/x-lz4",
"application/x-lzip",
"application/x-lzop",
)
doc = (
"application/vnd.openxmlformats-officedocument.wordprocessingml.document",
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
"application/vnd.openxmlformats-officedocument.presentationml.presentation"
)
mobi = (
"application/x-mobipocket-ebook",
"application/vnd.amazon.mobi8-ebook"
)
markup = (
"text/xml",
"text/html",
"text/x-sgml"
)
cnt = 1
@@ -87,16 +47,6 @@ def mime_id(mime):
mime_id += " | 0x40000000"
elif mime in font:
mime_id += " | 0x20000000"
elif mime in archive:
mime_id += " | 0x10000000"
elif mime in arc_filter:
mime_id += " | 0x08000000"
elif mime in doc:
mime_id += " | 0x04000000"
elif mime in mobi:
mime_id += " | 0x02000000"
elif mime in markup:
mime_id += " | 0x01000000"
elif mime == "application/x-empty":
return "1"
return mime_id
@@ -106,7 +56,7 @@ def clean(t):
return t.replace("/", "_").replace(".", "_").replace("+", "_").replace("-", "_")
with open("scripts/mime.csv") as f:
with open("mime.csv") as f:
for l in f:
mime, ext_list = l.split(",")
if l.startswith("!"):
@@ -118,7 +68,7 @@ with open("scripts/mime.csv") as f:
print("// **Generated by mime.py**")
print("#ifndef MIME_GENERATED_C")
print("#define MIME_GENERATED_C")
print("#include <glib.h>\n")
print("#include <glib-2.0/glib.h>\n")
print("#include <stdlib.h>\n")
# Enum
print("enum mime {")

View File

@@ -1,10 +1,10 @@
files = [
"src/static/css/bundle.css",
"src/static/css/bundle_dark.css",
"src/static/js/bundle.js",
"src/static/img/sprite-skin-flat.png",
"src/static/img/sprite-skin-flat-dark.png",
"src/static/search.html",
"web/css/bundle.css",
"web/css/bundle_dark.css",
"web/js/bundle.js",
"web/img/sprite-skin-flat.png",
"web/img/sprite-skin-flat-dark.png",
"web/search.html",
]

220
src/cli.c
View File

@@ -1,57 +1,22 @@
#include "cli.h"
#include "ctx.h"
#include <tesseract/capi.h>
#define DEFAULT_OUTPUT "index.sist2/"
#define DEFAULT_CONTENT_SIZE 32768
#define DEFAULT_QUALITY 5
#define DEFAULT_SIZE 500
#define DEFAULT_CONTENT_SIZE 4096
#define DEFAULT_QUALITY 15
#define DEFAULT_SIZE 200
#define DEFAULT_REWRITE_URL ""
#define DEFAULT_ES_URL "http://localhost:9200"
#define DEFAULT_BATCH_SIZE 100
#define DEFAULT_LISTEN_ADDRESS "localhost:4090"
const char* TESS_DATAPATHS[] = {
"/usr/share/tessdata/",
"/usr/share/tesseract-ocr/tessdata/",
"./",
NULL
};
#define DEFAULT_BIND_ADDR "localhost"
#define DEFAULT_PORT "4090"
scan_args_t *scan_args_create() {
scan_args_t *args = calloc(sizeof(scan_args_t), 1);
args->depth = -1;
return args;
}
void scan_args_destroy(scan_args_t *args) {
if (args->name != NULL) {
free(args->name);
}
if (args->path != NULL) {
free(args->path);
}
if (args->output != NULL) {
free(args->output);
}
free(args);
}
void index_args_destroy(index_args_t *args) {
//todo
free(args);
}
void web_args_destroy(web_args_t *args) {
//todo
free(args);
}
int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
if (argc < 2) {
fprintf(stderr, "Required positional argument: PATH.\n");
@@ -60,7 +25,7 @@ int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
char *abs_path = abspath(argv[1]);
if (abs_path == NULL) {
fprintf(stderr, "File not found: %s\n", argv[1]);
fprintf(stderr, "File not found: %s", argv[1]);
return 1;
} else {
args->path = abs_path;
@@ -69,8 +34,8 @@ int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
if (args->incremental != NULL) {
abs_path = abspath(args->incremental);
if (abs_path == NULL) {
sist_log("main.c", SIST_WARNING, "Could not open original index! Disabled incremental scan feature.");
args->incremental = NULL;
fprintf(stderr, "File not found: %s", args->incremental);
return 1;
}
}
@@ -83,13 +48,16 @@ int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
if (args->size == 0) {
args->size = DEFAULT_SIZE;
} else if (args->size > 0 && args->size < 32) {
printf("Invalid size: %d\n", args->content_size);
} else if (args->size <= 0) {
fprintf(stderr, "Invalid size: %d\n", args->size);
return 1;
}
if (args->content_size == 0) {
args->content_size = DEFAULT_CONTENT_SIZE;
} else if (args->content_size <= 0) {
fprintf(stderr, "Invalid content-size: %d\n", args->content_size);
return 1;
}
if (args->threads == 0) {
@@ -112,12 +80,6 @@ int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
return 1;
}
if (args->depth < 0) {
args->depth = G_MAXINT32;
} else {
args->depth += 1;
}
if (args->name == NULL) {
args->name = g_path_get_basename(args->output);
}
@@ -125,84 +87,12 @@ int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
if (args->rewrite_url == NULL) {
args->rewrite_url = DEFAULT_REWRITE_URL;
}
if (args->archive == NULL || strcmp(args->archive, "recurse") == 0) {
args->archive_mode = ARC_MODE_RECURSE;
} else if (strcmp(args->archive, "list") == 0) {
args->archive_mode = ARC_MODE_LIST;
} else if (strcmp(args->archive, "shallow") == 0) {
args->archive_mode = ARC_MODE_SHALLOW;
} else if (strcmp(args->archive, "skip") == 0) {
args->archive_mode = ARC_MODE_SKIP;
} else {
fprintf(stderr, "Archive mode must be one of (skip, list, shallow, recurse), got '%s'", args->archive);
return 1;
}
if (args->tesseract_lang != NULL) {
TessBaseAPI *api = TessBaseAPICreate();
char filename[128];
sprintf(filename, "%s.traineddata", args->tesseract_lang);
const char * path = find_file_in_paths(TESS_DATAPATHS, filename);
if (path == NULL) {
LOG_FATAL("cli.c", "Could not find tesseract language file!");
}
ret = TessBaseAPIInit3(api, path, args->tesseract_lang);
if (ret != 0) {
fprintf(stderr, "Could not initialize tesseract with lang '%s'\n", args->tesseract_lang);
return 1;
}
TessBaseAPIEnd(api);
TessBaseAPIDelete(api);
args->tesseract_path = path;
}
if (args->exclude_regex != NULL) {
const char *error;
int error_offset;
pcre *re = pcre_compile(args->exclude_regex, 0, &error, &error_offset, 0);
if (error != NULL) {
LOG_FATALF("cli.c", "pcre_compile returned error: %s (offset:%d)", error, error_offset)
}
pcre_extra *re_extra = pcre_study(re, 0, &error);
if (error != NULL) {
LOG_FATALF("cli.c", "pcre_study returned error: %s", error)
}
ScanCtx.exclude = re;
ScanCtx.exclude_extra = re_extra;
} else {
ScanCtx.exclude = NULL;
}
LOG_DEBUGF("cli.c", "arg quality=%f", args->quality)
LOG_DEBUGF("cli.c", "arg size=%d", args->size)
LOG_DEBUGF("cli.c", "arg content_size=%d", args->content_size)
LOG_DEBUGF("cli.c", "arg threads=%d", args->threads)
LOG_DEBUGF("cli.c", "arg incremental=%s", args->incremental)
LOG_DEBUGF("cli.c", "arg output=%s", args->output)
LOG_DEBUGF("cli.c", "arg rewrite_url=%s", args->rewrite_url)
LOG_DEBUGF("cli.c", "arg name=%s", args->name)
LOG_DEBUGF("cli.c", "arg depth=%d", args->depth)
LOG_DEBUGF("cli.c", "arg path=%s", args->path)
LOG_DEBUGF("cli.c", "arg archive=%s", args->archive)
LOG_DEBUGF("cli.c", "arg tesseract_lang=%s", args->tesseract_lang)
LOG_DEBUGF("cli.c", "arg tesseract_path=%s", args->tesseract_path)
LOG_DEBUGF("cli.c", "arg exclude=%s", args->exclude_regex)
LOG_DEBUGF("cli.c", "arg fast=%d", args->fast)
return 0;
}
#ifndef SIST_SCAN_ONLY
int index_args_validate(index_args_t *args, int argc, const char **argv) {
LogCtx.verbose = 1;
if (argc < 2) {
fprintf(stderr, "Required positional argument: PATH.\n");
return 1;
@@ -210,62 +100,20 @@ int index_args_validate(index_args_t *args, int argc, const char **argv) {
char *index_path = abspath(argv[1]);
if (index_path == NULL) {
fprintf(stderr, "File not found: %s\n", argv[1]);
fprintf(stderr, "File not found: %s", argv[1]);
return 1;
} else {
args->index_path = argv[1];
free(index_path);
}
if (args->es_url == NULL) {
args->es_url = DEFAULT_ES_URL;
}
if (args->script_path != NULL) {
struct stat info;
int res = stat(args->script_path, &info);
if (res == -1) {
fprintf(stderr, "Error opening script file '%s': %s\n", args->script_path, strerror(errno));
return 1;
}
int fd = open(args->script_path, O_RDONLY);
if (fd == -1) {
fprintf(stderr, "Error opening script file '%s': %s\n", args->script_path, strerror(errno));
return 1;
}
args->script = malloc(info.st_size + 1);
res = read(fd, args->script, info.st_size);
if (res < 0) {
fprintf(stderr, "Error reading script file '%s': %s\n", args->script_path, strerror(errno));
return 1;
}
*(args->script + info.st_size) = '\0';
close(fd);
}
if (args->batch_size == 0) {
args->batch_size = DEFAULT_BATCH_SIZE;
}
LOG_DEBUGF("cli.c", "arg es_url=%s", args->es_url)
LOG_DEBUGF("cli.c", "arg index_path=%s", args->index_path)
LOG_DEBUGF("cli.c", "arg script_path=%s", args->script_path)
LOG_DEBUGF("cli.c", "arg script=%s", args->script)
LOG_DEBUGF("cli.c", "arg print=%d", args->print)
LOG_DEBUGF("cli.c", "arg batch_size=%d", args->batch_size)
LOG_DEBUGF("cli.c", "arg force_reset=%d", args->force_reset)
return 0;
}
int web_args_validate(web_args_t *args, int argc, const char **argv) {
LogCtx.verbose = 1;
if (argc < 2) {
fprintf(stderr, "Required positional argument: PATH.\n");
return 1;
@@ -275,28 +123,12 @@ int web_args_validate(web_args_t *args, int argc, const char **argv) {
args->es_url = DEFAULT_ES_URL;
}
if (args->listen_address == NULL) {
args->listen_address = DEFAULT_LISTEN_ADDRESS;
if (args->bind == NULL) {
args->bind = DEFAULT_BIND_ADDR;
}
if (args->credentials != NULL) {
char * ptr = strstr(args->credentials, ":");
if (ptr == NULL) {
fprintf(stderr, "Invalid --auth format, see usage\n");
return 1;
}
strncpy(args->auth_user, args->credentials, (ptr - args->credentials));
strncpy(args->auth_pass, ptr + 1, strlen(ptr + 1));
if (strlen(args->auth_user) == 0) {
fprintf(stderr, "--auth username must be at least one character long");
return 1;
}
args->auth_enabled = TRUE;
} else {
args->auth_enabled = FALSE;
if (args->port == NULL) {
args->port = DEFAULT_PORT;
}
args->index_count = argc - 1;
@@ -305,21 +137,10 @@ int web_args_validate(web_args_t *args, int argc, const char **argv) {
for (int i = 0; i < args->index_count; i++) {
char *abs_path = abspath(args->indices[i]);
if (abs_path == NULL) {
fprintf(stderr, "File not found: %s\n", args->indices[i]);
fprintf(stderr, "File not found: %s", abs_path);
return 1;
}
}
LOG_DEBUGF("cli.c", "arg es_url=%s", args->es_url)
LOG_DEBUGF("cli.c", "arg listen=%s", args->listen_address)
LOG_DEBUGF("cli.c", "arg credentials=%s", args->credentials)
LOG_DEBUGF("cli.c", "arg auth_user=%s", args->auth_user)
LOG_DEBUGF("cli.c", "arg auth_pass=%s", args->auth_pass)
LOG_DEBUGF("cli.c", "arg index_count=%d", args->index_count)
for (int i = 0; i < args->index_count; i++) {
LOG_DEBUGF("cli.c", "arg indices[%d]=%s", i, args->indices[i])
}
return 0;
}
@@ -332,4 +153,5 @@ web_args_t *web_args_create() {
web_args_t *args = calloc(sizeof(web_args_t), 1);
return args;
}
#endif

View File

@@ -3,8 +3,6 @@
#include "sist.h"
#include "libscan/arc/arc.h"
typedef struct scan_args {
float quality;
int size;
@@ -14,53 +12,33 @@ typedef struct scan_args {
char *output;
char *rewrite_url;
char *name;
int depth;
char *path;
char *archive;
archive_mode_t archive_mode;
char *tesseract_lang;
const char *tesseract_path;
char *exclude_regex;
int fast;
} scan_args_t;
scan_args_t *scan_args_create();
void scan_args_destroy(scan_args_t *args);
int scan_args_validate(scan_args_t *args, int argc, const char **argv);
#ifndef SIST_SCAN_ONLY
typedef struct index_args {
char *es_url;
const char *index_path;
const char *script_path;
char *script;
int print;
int batch_size;
int force_reset;
} index_args_t;
typedef struct web_args {
char *es_url;
char *listen_address;
char *credentials;
char auth_user[256];
char auth_pass[256];
int auth_enabled;
char *bind;
char *port;
int index_count;
const char **indices;
} web_args_t;
index_args_t *index_args_create();
void index_args_destroy(index_args_t *args);
web_args_t *web_args_create();
void web_args_destroy(web_args_t *args);
int index_args_validate(index_args_t *args, int argc, const char **argv);
int web_args_validate(web_args_t *args, int argc, const char **argv);
#endif
#endif

View File

@@ -2,21 +2,7 @@
#define SIST2_CTX_H
#include "sist.h"
#include "tpool.h"
#include "libscan/scan.h"
#include "libscan/arc/arc.h"
#include "libscan/cbr/cbr.h"
#include "libscan/ebook/ebook.h"
#include "libscan/font/font.h"
#include "libscan/media/media.h"
#include "libscan/ooxml/ooxml.h"
#include "libscan/text/text.h"
#include "libscan/mobi/scan_mobi.h"
#include <glib.h>
#include <pcre.h>
//TODO Move to individual scan ctx
struct {
struct index_t index;
@@ -25,8 +11,10 @@ struct {
tpool_t *pool;
int tn_size;
int threads;
int depth;
int content_size;
float tn_qscale;
size_t stat_tn_size;
size_t stat_index_size;
@@ -34,39 +22,21 @@ struct {
GHashTable *original_table;
GHashTable *copy_table;
pcre *exclude;
pcre_extra *exclude_extra;
int fast;
scan_arc_ctx_t arc_ctx;
scan_cbr_ctx_t cbr_ctx;
scan_ebook_ctx_t ebook_ctx;
scan_font_ctx_t font_ctx;
scan_media_ctx_t media_ctx;
scan_ooxml_ctx_t ooxml_ctx;
scan_text_ctx_t text_ctx;
scan_mobi_ctx_t mobi_ctx;
pthread_mutex_t mupdf_mu;
} ScanCtx;
struct {
int verbose;
int very_verbose;
int no_color;
} LogCtx;
#ifndef SIST_SCAN_ONLY
struct {
char *es_url;
int batch_size;
} IndexCtx;
struct {
char *es_url;
int index_count;
char *auth_user;
char *auth_pass;
int auth_enabled;
struct index_t indices[16];
} WebCtx;
#endif
#endif

View File

@@ -1,10 +1,16 @@
#include "elastic.h"
#include "src/ctx.h"
#include <stdlib.h>
#include "web.h"
#include <stdio.h>
#include <string.h>
#include <cJSON/cJSON.h>
#include <src/ctx.h>
#include "static_generated.c"
#define BULK_INDEX_SIZE 100
typedef struct es_indexer {
int queued;
@@ -16,8 +22,6 @@ typedef struct es_indexer {
static es_indexer_t *Indexer;
void delete_queue(int max);
void print_json(cJSON *document, const char uuid_str[UUID_STR_LEN]) {
cJSON *line = cJSON_CreateObject();
@@ -25,14 +29,13 @@ void print_json(cJSON *document, const char uuid_str[UUID_STR_LEN]) {
cJSON_AddStringToObject(line, "_id", uuid_str);
cJSON_AddStringToObject(line, "_index", "sist2");
cJSON_AddStringToObject(line, "_type", "_doc");
cJSON_AddItemReferenceToObject(line, "_source", document);
cJSON_AddItemToObject(line, "_source", document);
char *json = cJSON_PrintUnformatted(line);
printf("%s\n", json);
cJSON_free(json);
cJSON_Delete(line);
cJSON_free(line);
}
void index_json(cJSON *document, const char uuid_str[UUID_STR_LEN]) {
@@ -51,52 +54,24 @@ void index_json(cJSON *document, const char uuid_str[UUID_STR_LEN]) {
elastic_index_line(bulk_line);
}
void execute_update_script(const char *script, const char index_id[UUID_STR_LEN]) {
void elastic_flush() {
cJSON *body = cJSON_CreateObject();
cJSON *script_obj = cJSON_AddObjectToObject(body, "script");
cJSON_AddStringToObject(script_obj, "lang", "painless");
cJSON_AddStringToObject(script_obj, "source", script);
cJSON *query = cJSON_AddObjectToObject(body, "query");
cJSON *term_obj = cJSON_AddObjectToObject(query, "term");
cJSON_AddStringToObject(term_obj, "index", index_id);
char *str = cJSON_Print(body);
char bulk_url[4096];
snprintf(bulk_url, 4096, "%s/sist2/_update_by_query?pretty", Indexer->es_url);
response_t *r = web_post(bulk_url, str);
LOG_INFOF("elastic.c", "Executed user script <%d>", r->status_code);
cJSON *resp = cJSON_Parse(r->body);
cJSON_free(str);
cJSON_Delete(body);
free_response(r);
cJSON *error = cJSON_GetObjectItem(resp, "error");
if (error != NULL) {
char *error_str = cJSON_Print(error);
LOG_ERRORF("elastic.c", "User script error: \n%s", error_str);
cJSON_free(error_str);
if (Indexer == NULL) {
Indexer = create_indexer(IndexCtx.es_url);
}
cJSON_Delete(resp);
}
void *create_bulk_buffer(int max, int *count, size_t *buf_len) {
es_bulk_line_t *line = Indexer->line_head;
*count = 0;
int count = 0;
size_t buf_size = 0;
size_t buf_cur = 0;
char *buf = malloc(1);
while (line != NULL && *count < max) {
while (line != NULL) {
char action_str[512];
snprintf(action_str, 512,
"{\"index\":{\"_id\":\"%s\", \"_type\":\"_doc\", \"_index\":\"sist2\"}}\n", line->uuid_str);
"{\"index\":{\"_id\":\"%s\", \"_type\":\"_doc\", \"_index\":\"sist2\"}}\n", line->uuid_str);
size_t action_str_len = strlen(action_str);
size_t line_len = strlen(line->line);
@@ -108,114 +83,31 @@ void *create_bulk_buffer(int max, int *count, size_t *buf_len) {
memcpy(buf + buf_cur, line->line, line_len);
buf_cur += line_len;
es_bulk_line_t *tmp = line;
line = line->next;
(*count)++;
free(tmp);
count++;
}
buf = realloc(buf, buf_size + 1);
*(buf + buf_cur) = '\0';
*(buf+buf_cur) = '\0';
*buf_len = buf_cur;
return buf;
}
void print_errors(response_t *r) {
char * tmp = malloc(r->size + 1);
memcpy(tmp, r->body, r->size);
*(tmp + r->size) = '\0';
cJSON *ret_json = cJSON_Parse(tmp);
if (cJSON_GetObjectItem(ret_json, "errors")->valueint != 0) {
cJSON *err;
cJSON_ArrayForEach(err, cJSON_GetObjectItem(ret_json, "items")) {
if (cJSON_GetObjectItem(cJSON_GetObjectItem(err, "index"), "status")->valueint != 201) {
char *str = cJSON_Print(err);
LOG_ERRORF("elastic.c", "%s\n", str);
cJSON_free(str);
}
}
}
cJSON_Delete(ret_json);
free(tmp);
}
void _elastic_flush(int max) {
if (max == 0) {
LOG_WARNING("elastic.c", "calling _elastic_flush with 0 in queue")
return;
}
size_t buf_len;
int count;
void *buf = create_bulk_buffer(max, &count, &buf_len);
Indexer->line_head = NULL;
Indexer->line_tail = NULL;
Indexer->queued = 0;
char bulk_url[4096];
snprintf(bulk_url, 4096, "%s/sist2/_bulk?pipeline=tie", Indexer->es_url);
response_t *r = web_post(bulk_url, buf);
snprintf(bulk_url, 4096, "%s/sist2/_bulk", Indexer->es_url);
response_t *r = web_post(bulk_url, buf, "Content-Type: application/x-ndjson");
printf("Indexed %3d documents (%zukB) <%d>\n", count, buf_cur / 1024, r->status_code);
if (r->status_code == 0) {
LOG_FATALF("elastic.c", "Could not connect to %s, make sure that elasticsearch is running!\n", IndexCtx.es_url)
cJSON *ret_json = cJSON_Parse(r->body);
if (cJSON_GetObjectItem(ret_json, "errors")->valueint != 0) {
fprintf(stderr, "%s\n", r->body);
}
if (r->status_code == 413) {
if (max <= 1) {
LOG_ERRORF("elastic.c", "Single document too large, giving up: {%s}", Indexer->line_head->uuid_str)
free_response(r);
free(buf);
delete_queue(1);
if (Indexer->queued != 0) {
elastic_flush();
}
return;
}
LOG_WARNINGF("elastic.c", "Payload too large, retrying (%d documents)", count);
free_response(r);
free(buf);
_elastic_flush(max / 2);
return;
} else if (r->status_code != 200) {
print_errors(r);
delete_queue(Indexer->queued);
} else {
print_errors(r);
LOG_INFOF("elastic.c", "Indexed %d documents (%zukB) <%d>", count, buf_len / 1024, r->status_code);
delete_queue(max);
if (Indexer->queued != 0) {
elastic_flush();
}
}
cJSON_Delete(ret_json);
free_response(r);
free(buf);
}
void delete_queue(int max) {
for (int i = 0; i < max; i++) {
es_bulk_line_t *tmp = Indexer->line_head;
Indexer->line_head = tmp->next;
if (Indexer->line_head == NULL) {
Indexer->line_tail = NULL;
} else {
free(tmp);
}
Indexer->queued -= 1;
}
}
void elastic_flush() {
if (Indexer == NULL) {
Indexer = create_indexer(IndexCtx.es_url);
}
_elastic_flush(Indexer->queued);
}
void elastic_index_line(es_bulk_line_t *line) {
@@ -234,14 +126,15 @@ void elastic_index_line(es_bulk_line_t *line) {
Indexer->queued += 1;
if (Indexer->queued >= IndexCtx.batch_size) {
if (Indexer->queued >= BULK_INDEX_SIZE) {
elastic_flush();
}
}
es_indexer_t *create_indexer(const char *url) {
char *es_url = malloc(strlen(url) + 1);
size_t url_len = strlen(url);
char *es_url = malloc(url_len);
strcpy(es_url, url);
es_indexer_t *indexer = malloc(sizeof(es_indexer_t));
@@ -254,27 +147,18 @@ es_indexer_t *create_indexer(const char *url) {
return indexer;
}
void destroy_indexer(char *script, char index_id[UUID_STR_LEN]) {
void destroy_indexer() {
char url[4096];
snprintf(url, sizeof(url), "%s/sist2/_refresh", IndexCtx.es_url);
response_t *r = web_post(url, "");
LOG_INFOF("elastic.c", "Refresh index <%d>", r->status_code);
free_response(r);
if (script != NULL) {
execute_update_script(script, index_id);
}
snprintf(url, sizeof(url), "%s/sist2/_refresh", IndexCtx.es_url);
r = web_post(url, "");
LOG_INFOF("elastic.c", "Refresh index <%d>", r->status_code);
response_t *r = web_post(url, "", NULL);
printf("Refresh index <%d>\n", r->status_code);
free_response(r);
snprintf(url, sizeof(url), "%s/sist2/_forcemerge", IndexCtx.es_url);
r = web_post(url, "");
LOG_INFOF("elastic.c", "Merge index <%d>", r->status_code);
r = web_post(url, "", NULL);
printf("Merge index <%d>\n", r->status_code);
free_response(r);
if (Indexer != NULL) {
@@ -294,37 +178,32 @@ void elastic_init(int force_reset) {
if (!index_exists || force_reset) {
r = web_delete(url);
LOG_INFOF("elastic.c", "Delete index <%d>", r->status_code);
printf("Delete index <%d>\n", r->status_code);
free_response(r);
snprintf(url, 4096, "%s/sist2", IndexCtx.es_url);
r = web_put(url, "");
LOG_INFOF("elastic.c", "Create index <%d>", r->status_code);
r = web_put(url, "", NULL);
printf("Create index <%d>\n", r->status_code);
free_response(r);
snprintf(url, 4096, "%s/sist2/_close", IndexCtx.es_url);
r = web_post(url, "");
LOG_INFOF("elastic.c", "Close index <%d>", r->status_code);
free_response(r);
snprintf(url, 4096, "%s/_ingest/pipeline/tie", IndexCtx.es_url);
r = web_put(url, pipeline_json);
LOG_INFOF("elastic.c", "Create pipeline <%d>", r->status_code);
r = web_post(url, "", NULL);
printf("Close index <%d>\n", r->status_code);
free_response(r);
snprintf(url, 4096, "%s/sist2/_settings", IndexCtx.es_url);
r = web_put(url, settings_json);
LOG_INFOF("elastic.c", "Update settings <%d>", r->status_code);
r = web_put(url, settings_json, "Content-Type: application/json");
printf("Update settings <%d>\n", r->status_code);
free_response(r);
snprintf(url, 4096, "%s/sist2/_mappings/_doc?include_type_name=true", IndexCtx.es_url);
r = web_put(url, mappings_json);
LOG_INFOF("elastic.c", "Update mappings <%d>", r->status_code);
r = web_put(url, mappings_json, "Content-Type: application/json");
printf("Update mappings <%d>\n", r->status_code);
free_response(r);
snprintf(url, 4096, "%s/sist2/_open", IndexCtx.es_url);
r = web_post(url, "");
LOG_INFOF("elastic.c", "Open index <%d>", r->status_code);
r = web_post(url, "", NULL);
printf("Open index <%d>\n", r->status_code);
free_response(r);
}
}
@@ -341,28 +220,3 @@ cJSON *elastic_get_document(const char *uuid_str) {
free_response(r);
return json;
}
char *elastic_get_status() {
char url[4096];
snprintf(url, 4096,
"%s/_cluster/state/metadata/sist2?filter_path=metadata.indices.*.state", WebCtx.es_url);
response_t *r = web_get(url);
cJSON *json = NULL;
char *status = malloc(128 * sizeof(char));
status[0] = '\0';
if (r->status_code == 200) {
json = cJSON_Parse(r->body);
const cJSON *metadata = cJSON_GetObjectItem(json, "metadata");
if (metadata != NULL) {
const cJSON *indices = cJSON_GetObjectItem(metadata, "indices");
const cJSON *sist2 = cJSON_GetObjectItem(indices, "sist2");
const cJSON *state = cJSON_GetObjectItem(sist2, "state");
strcpy(status, state->valuestring);
}
}
free_response(r);
cJSON_Delete(json);
return status;
}

View File

@@ -24,12 +24,10 @@ void index_json(cJSON *document, const char uuid_str[UUID_STR_LEN]);
es_indexer_t *create_indexer(const char* es_url);
void destroy_indexer(char *script, char index_id[UUID_STR_LEN]);
void destroy_indexer();
void elastic_init(int force_reset);
cJSON *elastic_get_document(const char *uuid_str);
char *elastic_get_status();
#endif

File diff suppressed because one or more lines are too long

View File

@@ -1,154 +1,131 @@
#include "web.h"
#include "src/sist.h"
#include "src/ctx.h"
#include <mongoose.h>
#include <pthread.h>
size_t write_cb(char *ptr, size_t size, size_t nmemb, void *user_data) {
size_t real_size = size * nmemb;
dyn_buffer_t *buf = user_data;
dyn_buffer_write(buf, ptr, real_size);
return real_size;
}
void free_response(response_t *resp) {
if (resp->body != NULL) {
free(resp->body);
}
free(resp->body);
free(resp);
}
#define SIST2_HEADERS "User-Agent: sist2\r\nContent-Type: application/json\r\n"
void http_req_ev(struct mg_connection *nc, int ev, void *ptr) {
http_ev_data_t *ev_data = (http_ev_data_t *) nc->user_data;
switch (ev) {
case MG_EV_CONNECT: {
int connect_status = *(int *) ptr;
if (connect_status != 0) {
ev_data->done = TRUE;
ev_data->resp->status_code = 0;
}
break;
}
case MG_EV_HTTP_REPLY: {
struct http_message *hm = (struct http_message *) ptr;
//TODO: Check errors?
ev_data->resp->size = hm->body.len;
ev_data->resp->status_code = hm->resp_code;
ev_data->resp->body = malloc(hm->body.len + 1);
memcpy(ev_data->resp->body, hm->body.p, hm->body.len);
*(ev_data->resp->body + hm->body.len) = '\0';
ev_data->done = TRUE;
break;
}
case MG_EV_CLOSE: {
ev_data->done = TRUE;
break;
}
default:
break;
}
}
subreq_ctx_t *http_req(const char *url, const char *extra_headers, const char *post_data, const char *method) {
struct mg_str scheme;
struct mg_str user_info;
struct mg_str host;
unsigned int port;
struct mg_str path;
struct mg_str query;
struct mg_str fragment;
if (post_data == NULL) post_data = "";
if (extra_headers == NULL) extra_headers = "";
if (path.len == 0) path = mg_mk_str("/");
if (host.len == 0) host = mg_mk_str("");
// [scheme://[user_info@]]host[:port][/path][?query][#fragment]
mg_parse_uri(mg_mk_str(url), &scheme, &user_info, &host, &port, &path, &query, &fragment);
if (query.len > 0) path.len += query.len + 1;
subreq_ctx_t *ctx = malloc(sizeof(subreq_ctx_t));
mg_mgr_init(&ctx->mgr, NULL);
char address[8196];
snprintf(address, sizeof(address), "tcp://%.*s:%u", (int) host.len, host.p, port);
struct mg_connection *nc = mg_connect(&ctx->mgr, address, http_req_ev);
nc->user_data = &ctx->ev_data;
mg_set_protocol_http_websocket(nc);
ctx->ev_data.resp = calloc(1, sizeof(response_t));
ctx->ev_data.done = FALSE;
mg_printf(
nc, "%s %.*s HTTP/1.1\r\n"
"Host: %.*s\r\n"
"Content-Length: %zu\r\n"
"%s\r\n"
"%s",
method, (int) path.len, path.p,
(int) (path.p - host.p), host.p,
strlen(post_data),
extra_headers,
post_data
);
return ctx;
}
response_t *web_get(const char *url) {
subreq_ctx_t *ctx = http_req(url, SIST2_HEADERS, NULL, "GET");
while (ctx->ev_data.done == FALSE) {
mg_mgr_poll(&ctx->mgr, 50);
}
mg_mgr_free(&ctx->mgr);
response_t *resp = malloc(sizeof(response_t));
response_t *ret = ctx->ev_data.resp;
free(ctx);
return ret;
CURL *curl;
dyn_buffer_t buffer = dyn_buffer_create();
curl = curl_easy_init();
curl_easy_setopt(curl, CURLOPT_URL, url);
curl_easy_setopt(curl, CURLOPT_WRITEDATA, (void *) (&buffer));
curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, write_cb);
curl_easy_setopt(curl, CURLOPT_USERAGENT, "sist2");
curl_easy_perform(curl);
curl_easy_getinfo(curl, CURLINFO_RESPONSE_CODE, &resp->status_code);
curl_easy_cleanup(curl);
resp->body = buffer.buf;
resp->size = buffer.cur;
return resp;
}
subreq_ctx_t *web_post_async(const char *url, const char *data) {
return http_req(url, SIST2_HEADERS, data, "POST");
response_t *web_post(const char *url, const char *data, const char *header) {
response_t *resp = malloc(sizeof(response_t));
CURL *curl;
dyn_buffer_t buffer = dyn_buffer_create();
curl = curl_easy_init();
curl_easy_setopt(curl, CURLOPT_URL, url);
curl_easy_setopt(curl, CURLOPT_WRITEDATA, (void *) (&buffer));
curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, write_cb);
curl_easy_setopt(curl, CURLOPT_POST, 1);
curl_easy_setopt(curl, CURLOPT_USERAGENT, "sist2");
struct curl_slist *headers = NULL;
if (header != NULL) {
headers = curl_slist_append(headers, header);
curl_easy_setopt(curl, CURLOPT_HTTPHEADER, headers);
}
curl_easy_setopt(curl, CURLOPT_POSTFIELDS, data);
curl_easy_perform(curl);
curl_easy_getinfo(curl, CURLINFO_RESPONSE_CODE, &resp->status_code);
curl_easy_cleanup(curl);
curl_slist_free_all(headers);
resp->body = buffer.buf;
resp->size = buffer.cur;
return resp;
}
response_t *web_post(const char *url, const char *data) {
subreq_ctx_t *ctx = http_req(url, SIST2_HEADERS, data, "POST");
while (ctx->ev_data.done == FALSE) {
mg_mgr_poll(&ctx->mgr, 50);
response_t *web_put(const char *url, const char *data, const char *header) {
response_t *resp = malloc(sizeof(response_t));
CURL *curl;
dyn_buffer_t buffer = dyn_buffer_create();
curl = curl_easy_init();
curl_easy_setopt(curl, CURLOPT_URL, url);
curl_easy_setopt(curl, CURLOPT_WRITEDATA, (void *) (&buffer));
curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, write_cb);
curl_easy_setopt(curl, CURLOPT_CUSTOMREQUEST, "PUT");
curl_easy_setopt(curl, CURLOPT_USERAGENT, "sist2");
curl_easy_setopt(curl, CURLOPT_DNS_USE_GLOBAL_CACHE, 0);
curl_easy_setopt(curl, CURLOPT_IPRESOLVE, CURLOPT_DNS_LOCAL_IP4 );
if (header != NULL) {
struct curl_slist *headers = NULL;
headers = curl_slist_append(headers, header);
curl_easy_setopt(curl, CURLOPT_HTTPHEADER, headers);
}
mg_mgr_free(&ctx->mgr);
response_t *ret = ctx->ev_data.resp;
free(ctx);
return ret;
}
curl_easy_setopt(curl, CURLOPT_POSTFIELDS, data);
response_t *web_put(const char *url, const char *data) {
subreq_ctx_t *ctx = http_req(url, SIST2_HEADERS, data, "PUT");
while (ctx->ev_data.done == FALSE) {
mg_mgr_poll(&ctx->mgr, 50);
}
mg_mgr_free(&ctx->mgr);
curl_easy_perform(curl);
curl_easy_getinfo(curl, CURLINFO_RESPONSE_CODE, &resp->status_code);
response_t *ret = ctx->ev_data.resp;
free(ctx);
return ret;
curl_easy_cleanup(curl);
resp->body = buffer.buf;
resp->size = buffer.cur;
return resp;
}
response_t *web_delete(const char *url) {
subreq_ctx_t *ctx = http_req(url, SIST2_HEADERS, NULL, "DELETE");
while (ctx->ev_data.done == FALSE) {
mg_mgr_poll(&ctx->mgr, 50);
}
mg_mgr_free(&ctx->mgr);
response_t *ret = ctx->ev_data.resp;
free(ctx);
return ret;
response_t *resp = malloc(sizeof(response_t));
CURL *curl;
dyn_buffer_t buffer = dyn_buffer_create();
curl = curl_easy_init();
curl_easy_setopt(curl, CURLOPT_URL, url);
curl_easy_setopt(curl, CURLOPT_WRITEDATA, (void *) (&buffer));
curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, write_cb);
curl_easy_setopt(curl, CURLOPT_CUSTOMREQUEST, "DELETE");
curl_easy_setopt(curl, CURLOPT_USERAGENT, "sist2");
curl_easy_setopt(curl, CURLOPT_POSTFIELDS, "");
curl_easy_perform(curl);
curl_easy_getinfo(curl, CURLINFO_RESPONSE_CODE, &resp->status_code);
curl_easy_cleanup(curl);
resp->body = buffer.buf;
resp->size = buffer.cur;
return resp;
}

View File

@@ -2,7 +2,6 @@
#define SIST2_WEB_H
#include "src/sist.h"
#include <mongoose.h>
typedef struct response {
char *body;
@@ -10,20 +9,9 @@ typedef struct response {
int status_code;
} response_t;
typedef struct {
response_t *resp;
int done;
} http_ev_data_t;
typedef struct {
http_ev_data_t ev_data;
struct mg_mgr mgr;
} subreq_ctx_t;
response_t *web_get(const char *url);
response_t *web_post(const char * url, const char * data);
subreq_ctx_t *web_post_async(const char *url, const char *data);
response_t *web_put(const char *url, const char *data);
response_t *web_post(const char * url, const char * data, const char* header);
response_t *web_put(const char *url, const char *data, const char *header);
response_t *web_delete(const char *url);
void free_response(response_t *resp);

View File

@@ -1,9 +1,7 @@
#include "src/ctx.h"
#include "serialize.h"
#include "src/parsing/parse.h"
#include "src/parsing/mime.h"
static __thread int index_fd = -1;
static __thread int IndexFd = -1;
typedef struct {
unsigned char uuid[16];
@@ -36,19 +34,15 @@ void write_index_descriptor(char *path, index_descriptor_t *desc) {
cJSON_AddStringToObject(json, "version", desc->version);
cJSON_AddStringToObject(json, "root", desc->root);
cJSON_AddStringToObject(json, "name", desc->name);
cJSON_AddStringToObject(json, "type", desc->type);
cJSON_AddStringToObject(json, "rewrite_url", desc->rewrite_url);
cJSON_AddNumberToObject(json, "timestamp", (double) desc->timestamp);
int fd = open(path, O_CREAT | O_WRONLY, S_IRUSR | S_IWUSR);
if (fd < 0) {
LOG_FATALF("serialize.c", "Could not open index descriptor: %s", strerror(errno));
if (fd == -1) {
perror(path);
}
char *str = cJSON_Print(json);
int ret = write(fd, str, strlen(str));
if (ret == -1) {
LOG_FATALF("serialize.c", "Could not write index descriptor: %s", strerror(errno));
}
write(fd, str, strlen(str));
free(str);
close(fd);
@@ -60,16 +54,8 @@ index_descriptor_t read_index_descriptor(char *path) {
struct stat info;
stat(path, &info);
int fd = open(path, O_RDONLY);
if (fd == -1) {
LOG_FATALF("serialize.c", "Invalid/corrupt index (Could not find descriptor): %s: %s\n", path ,strerror(errno))
}
char *buf = malloc(info.st_size + 1);
int ret = read(fd, buf, info.st_size);
if (ret == -1) {
LOG_FATALF("serialize.c", "Could not read index descriptor: %s", strerror(errno));
}
read(fd, buf, info.st_size);
*(buf + info.st_size) = '\0';
close(fd);
@@ -80,14 +66,9 @@ index_descriptor_t read_index_descriptor(char *path) {
strcpy(descriptor.root, cJSON_GetObjectItem(json, "root")->valuestring);
strcpy(descriptor.name, cJSON_GetObjectItem(json, "name")->valuestring);
strcpy(descriptor.rewrite_url, cJSON_GetObjectItem(json, "rewrite_url")->valuestring);
descriptor.root_len = (short) strlen(descriptor.root);
descriptor.root_len = (short)strlen(descriptor.root);
strcpy(descriptor.version, cJSON_GetObjectItem(json, "version")->valuestring);
strcpy(descriptor.uuid, cJSON_GetObjectItem(json, "uuid")->valuestring);
if (cJSON_GetObjectItem(json, "type") == NULL) {
strcpy(descriptor.type, INDEX_TYPE_BIN);
} else {
strcpy(descriptor.type, cJSON_GetObjectItem(json, "type")->valuestring);
}
cJSON_Delete(json);
free(buf);
@@ -124,32 +105,6 @@ char *get_meta_key_text(enum metakey meta_key) {
return "title";
case MetaFontName:
return "font_name";
case MetaParent:
return "parent";
case MetaExifMake:
return "exif_make";
case MetaExifSoftware:
return "exif_software";
case MetaExifExposureTime:
return "exif_exposure_time";
case MetaExifFNumber:
return "exif_fnumber";
case MetaExifFocalLength:
return "exif_focal_length";
case MetaExifUserComment:
return "exif_user_comment";
case MetaExifIsoSpeedRatings:
return "exif_iso_speed_ratings";
case MetaExifModel:
return "exif_model";
case MetaExifDateTime:
return "exif_datetime";
case MetaAuthor:
return "author";
case MetaModifiedBy:
return "modified_by";
case MetaThumbnail:
return "thumbnail";
default:
return NULL;
}
@@ -158,13 +113,13 @@ char *get_meta_key_text(enum metakey meta_key) {
void write_document(document_t *doc) {
if (index_fd == -1) {
if (IndexFd == -1) {
char dstfile[PATH_MAX];
pthread_t self = pthread_self();
snprintf(dstfile, PATH_MAX, "%s_index_%lu", ScanCtx.index.path, self);
index_fd = open(dstfile, O_CREAT | O_WRONLY | O_APPEND, S_IRUSR | S_IWUSR);
IndexFd = open(dstfile, O_CREAT | O_WRONLY | O_APPEND, S_IRUSR | S_IWUSR);
if (index_fd == -1) {
if (IndexFd == -1) {
perror("open");
}
}
@@ -184,11 +139,11 @@ void write_document(document_t *doc) {
dyn_buffer_write_char(&buf, meta->key);
if (IS_META_INT(meta->key)) {
dyn_buffer_write_int(&buf, meta->int_val);
dyn_buffer_write_int(&buf, meta->intval);
} else if (IS_META_LONG(meta->key)) {
dyn_buffer_write_long(&buf, meta->long_val);
dyn_buffer_write_long(&buf, meta->longval);
} else {
dyn_buffer_write_str(&buf, meta->str_val);
dyn_buffer_write_str(&buf, meta->strval);
}
meta_line_t *tmp = meta;
@@ -197,29 +152,24 @@ void write_document(document_t *doc) {
}
dyn_buffer_write_char(&buf, '\n');
int res = write(index_fd, buf.buf, buf.cur);
if (res == -1) {
LOG_FATALF("serialize.c", "Could not write document: %s", strerror(errno))
}
write(IndexFd, buf.buf, buf.cur);
ScanCtx.stat_index_size += buf.cur;
dyn_buffer_destroy(&buf);
}
void thread_cleanup() {
close(index_fd);
cleanup_parse();
cleanup_font();
void serializer_cleanup() {
close(IndexFd);
}
void read_index(const char *path, const char index_id[UUID_STR_LEN], index_func func) {
void read_index_bin(const char *path, const char *index_id, index_func func) {
line_t line;
dyn_buffer_t buf = dyn_buffer_create();
FILE *file = fopen(path, "rb");
while (1) {
buf.cur = 0;
size_t _ = fread((void *) &line, 1, sizeof(line_t), file);
fread((void *) &line, 1, sizeof(line_t), file);
if (feof(file)) {
break;
}
@@ -230,13 +180,8 @@ void read_index_bin(const char *path, const char *index_id, index_func func) {
char uuid_str[UUID_STR_LEN];
uuid_unparse(line.uuid, uuid_str);
const char* mime_text = mime_get_mime_text(line.mime);
if (mime_text == NULL) {
cJSON_AddNullToObject(document, "mime");
} else {
cJSON_AddStringToObject(document, "mime", mime_get_mime_text(line.mime));
}
cJSON_AddNumberToObject(document, "size", (double) line.size);
cJSON_AddStringToObject(document, "mime", mime_get_mime_text(line.mime));
cJSON_AddNumberToObject(document, "size", (double)line.size);
cJSON_AddNumberToObject(document, "mtime", line.mtime);
int c;
@@ -260,48 +205,38 @@ void read_index_bin(const char *path, const char *index_id, index_func func) {
}
enum metakey key = getc(file);
size_t ret = 0;
while (key != '\n') {
switch (key) {
case MetaWidth:
case MetaHeight: {
case MetaHeight:
case MetaMediaDuration:
case MetaMediaBitrate: {
int value;
ret = fread(&value, sizeof(int), 1, file);
fread(&value, sizeof(int), 1, file);
cJSON_AddNumberToObject(document, get_meta_key_text(key), value);
break;
}
case MetaMediaDuration:
case MetaMediaBitrate: {
long value;
ret = fread(&value, sizeof(long), 1, file);
cJSON_AddNumberToObject(document, get_meta_key_text(key), (double) value);
case MetaMediaAudioCodec:
case MetaMediaVideoCodec: {
int value;
fread(&value, sizeof(int), 1, file);
const AVCodecDescriptor *desc = avcodec_descriptor_get(value);
if (desc != NULL) {
cJSON_AddStringToObject(document, get_meta_key_text(key), desc->name);
}
break;
}
case MetaMediaAudioCodec:
case MetaMediaVideoCodec:
case MetaContent:
case MetaArtist:
case MetaAlbum:
case MetaAlbumArtist:
case MetaGenre:
case MetaFontName:
case MetaParent:
case MetaExifMake:
case MetaExifSoftware:
case MetaExifExposureTime:
case MetaExifFNumber:
case MetaExifFocalLength:
case MetaExifUserComment:
case MetaExifIsoSpeedRatings:
case MetaExifDateTime:
case MetaExifModel:
case MetaAuthor:
case MetaModifiedBy:
case MetaThumbnail:
case MetaTitle: {
buf.cur = 0;
while ((c = getc(file)) != 0) {
if (SHOULD_KEEP_CHAR(c) || c == ' ') {
if (!(SHOULD_IGNORE_CHAR(c)) || c == ' ') {
dyn_buffer_write_char(&buf, (char) c);
}
}
@@ -309,110 +244,24 @@ void read_index_bin(const char *path, const char *index_id, index_func func) {
cJSON_AddStringToObject(document, get_meta_key_text(key), buf.buf);
break;
}
default:
LOG_FATALF("serialize.c", "Invalid meta key (corrupt index): %x", key)
}
key = getc(file);
}
func(document, uuid_str);
cJSON_Delete(document);
}
dyn_buffer_destroy(&buf);
fclose(file);
}
const char *json_type_copy_fields[] = {
"mime", "name", "path", "extension", "index", "size", "mtime", "parent",
// Meta
"title", "content", "width", "height", "duration", "audioc", "videoc",
"bitrate", "artist", "album", "album_artist", "genre", "title", "font_name",
// Special
"tag", "_url"
};
const char *json_type_array_fields[] = {
"_keyword", "_text"
};
void read_index_json(const char *path, UNUSED(const char *index_id), index_func func) {
FILE *file = fopen(path, "r");
while (1) {
char *line = NULL;
size_t len;
size_t read = getline(&line, &len, file);
if (read < 0) {
if (line) {
free(line);
}
break;
}
cJSON *input = cJSON_Parse(line);
if (input == NULL) {
LOG_FATALF("serialize.c", "Could not parse JSON line: \n%s", line)
}
if (line) {
free(line);
}
cJSON *document = cJSON_CreateObject();
const char *uuid_str = cJSON_GetObjectItem(input, "_id")->valuestring;
for (int i = 0; i < (sizeof(json_type_copy_fields) / sizeof(json_type_copy_fields[0])); i++) {
cJSON *value = cJSON_GetObjectItem(input, json_type_copy_fields[i]);
if (value != NULL) {
cJSON_AddItemReferenceToObject(document, json_type_copy_fields[i], value);
}
}
for (int i = 0; i < (sizeof(json_type_array_fields) / sizeof(json_type_array_fields[0])); i++) {
cJSON *arr = cJSON_GetObjectItem(input, json_type_array_fields[i]);
if (arr != NULL) {
cJSON *obj;
cJSON_ArrayForEach(obj, arr) {
char key[1024];
cJSON *k = cJSON_GetObjectItem(obj, "k");
cJSON *v = cJSON_GetObjectItem(obj, "v");
if (k == NULL || v == NULL || !cJSON_IsString(k) || !cJSON_IsString(v)) {
char *str = cJSON_Print(obj);
LOG_FATALF("serialize.c", "Invalid %s member: must contain .k and .v string fields: \n%s",
json_type_array_fields[i], str)
}
snprintf(key, sizeof(key), "%s.%s", json_type_array_fields[i], k->valuestring);
cJSON_AddStringToObject(document, key, v->valuestring);
}
}
}
func(document, uuid_str);
cJSON_Delete(document);
cJSON_Delete(input);
cJSON_free(document);
}
fclose(file);
}
void read_index(const char *path, const char index_id[UUID_STR_LEN], const char *type, index_func func) {
if (strcmp(type, INDEX_TYPE_BIN) == 0) {
read_index_bin(path, index_id, func);
} else if (strcmp(type, INDEX_TYPE_JSON) == 0) {
read_index_json(path, index_id, func);
}
}
void incremental_read(GHashTable *table, const char *filepath) {
FILE *file = fopen(filepath, "rb");
line_t line;
while (1) {
size_t ret = fread((void *) &line, 1, sizeof(line_t), file);
if (ret != 1 || feof(file)) {
fread((void *) &line, 1, sizeof(line_t), file);
if (feof(file)) {
break;
}
@@ -435,8 +284,8 @@ void incremental_copy(store_t *store, store_t *dst_store, const char *filepath,
line_t line;
while (1) {
size_t ret = fread((void *) &line, 1, sizeof(line_t), file);
if (ret != 1 || feof(file)) {
fread((void *) &line, 1, sizeof(line_t), file);
if (feof(file)) {
break;
}
@@ -464,11 +313,11 @@ void incremental_copy(store_t *store, store_t *dst_store, const char *filepath,
if (IS_META_INT(key)) {
int val;
ret = fread(&val, sizeof(val), 1, file);
fread(&val, sizeof(val), 1, file);
fwrite(&val, sizeof(val), 1, dst_file);
} else if (IS_META_LONG(key)) {
long val;
ret = fread(&val, sizeof(val), 1, file);
fread(&val, sizeof(val), 1, file);
fwrite(&val, sizeof(val), 1, dst_file);
} else {
while ((c = (char) getc(file))) {
@@ -476,10 +325,6 @@ void incremental_copy(store_t *store, store_t *dst_store, const char *filepath,
}
fwrite("\0", sizeof(c), 1, dst_file);
}
if (ret != 1) {
break;
}
}
} else {
skip_meta(file);

View File

@@ -2,10 +2,7 @@
#define SIST2_SERIALIZE_H
#include "src/sist.h"
#include "store.h"
#include <sys/syscall.h>
#include <glib.h>
typedef void(*index_func)(cJSON *, const char[UUID_STR_LEN]);
@@ -14,14 +11,14 @@ void incremental_copy(store_t *store, store_t *dst_store, const char *filepath,
void write_document(document_t *doc);
void read_index(const char *path, const char[UUID_STR_LEN], const char *type, index_func);
void read_index(const char *path, const char[UUID_STR_LEN], index_func);
void incremental_read(GHashTable *table, const char *filepath);
/**
* Must be called after write_document
*/
void thread_cleanup();
void serializer_cleanup();
void write_index_descriptor(char *path, index_descriptor_t *desc);

View File

@@ -9,13 +9,14 @@ store_t *store_create(char *path) {
mdb_env_create(&store->env);
int open_ret = mdb_env_open(store->env,
path,
MDB_WRITEMAP | MDB_MAPASYNC,
S_IRUSR | S_IWUSR
path,
MDB_WRITEMAP | MDB_MAPASYNC,
S_IRUSR | S_IWUSR
);
if (open_ret != 0) {
LOG_FATALF("store.c", "Error while opening store: %s (%s)\n", mdb_strerror(open_ret), path)
fprintf(stderr, "Error while opening store: %s", mdb_strerror(open_ret));
exit(1);
}
store->size = (size_t) 1024 * 1024 * 5;
@@ -41,12 +42,6 @@ void store_destroy(store_t *store) {
void store_write(store_t *store, char *key, size_t key_len, char *buf, size_t buf_len) {
if (LogCtx.very_verbose) {
char uuid_str[UUID_STR_LEN];
uuid_unparse((unsigned char *) key, uuid_str);
LOG_DEBUGF("store.c", "Store write {%s} %lu bytes", uuid_str, buf_len)
}
MDB_val mdb_key;
mdb_key.mv_data = key;
mdb_key.mv_size = key_len;
@@ -73,15 +68,13 @@ void store_write(store_t *store, char *key, size_t key_len, char *buf, size_t bu
mdb_env_set_mapsize(store->env, store->size);
mdb_txn_begin(store->env, NULL, 0, &txn);
put_ret = mdb_put(txn, store->dbi, &mdb_key, &mdb_value, 0);
LOG_INFOF("store.c", "Updated mdb mapsize to %lu bytes", store->size)
}
mdb_txn_commit(txn);
pthread_rwlock_unlock(&store->lock);
if (put_ret != 0) {
LOG_ERROR("store.c", mdb_strerror(put_ret))
printf("%s\n", mdb_strerror(put_ret));
}
}

View File

@@ -11,6 +11,8 @@ typedef struct store_t {
pthread_rwlock_t lock;
} store_t;
#include "src/sist.h"
store_t *store_create(char *path);
void store_destroy(store_t *store);

View File

@@ -1,50 +1,28 @@
#include "walk.h"
#include "src/ctx.h"
#include "src/parsing/parse.h"
#include <ftw.h>
__always_inline
parse_job_t *create_fs_parse_job(const char *filepath, const struct stat *info, int base) {
parse_job_t *create_parse_job(const char *filepath, const struct stat *info, int base) {
int len = (int) strlen(filepath);
parse_job_t *job = malloc(sizeof(parse_job_t) + len);
strcpy(job->filepath, filepath);
memcpy(&(job->filepath), filepath, len + 1);
job->base = base;
char *p = strrchr(filepath + base, '.');
if (p != NULL) {
job->ext = (int) (p - filepath + 1);
job->ext = (int)(p - filepath + 1);
} else {
job->ext = len;
}
job->vfile.info = *info;
memset(job->parent, 0, 16);
job->vfile.filepath = job->filepath;
job->vfile.read = fs_read;
job->vfile.reset = fs_reset;
job->vfile.close = fs_close;
job->vfile.fd = -1;
job->vfile.is_fs_file = TRUE;
memcpy(&(job->info), info, sizeof(struct stat));
return job;
}
int sub_strings[30];
#define EXCLUDED(str) (pcre_exec(ScanCtx.exclude, ScanCtx.exclude_extra, filepath, strlen(filepath), 0, 0, sub_strings, sizeof(sub_strings)) >= 0)
int handle_entry(const char *filepath, const struct stat *info, int typeflag, struct FTW *ftw) {
if (typeflag == FTW_F && S_ISREG(info->st_mode) && ftw->level <= ScanCtx.depth) {
if (ScanCtx.exclude != NULL && EXCLUDED(filepath)) {
LOG_DEBUGF("walk.c", "Excluded: %s", filepath)
return 0;
}
parse_job_t *job = create_fs_parse_job(filepath, info, ftw->base);
if (typeflag == FTW_F && S_ISREG(info->st_mode)) {
parse_job_t *job = create_parse_job(filepath, info, ftw->base);
tpool_add_work(ScanCtx.pool, parse, job);
}

View File

@@ -3,6 +3,8 @@
#define _XOPEN_SOURCE 500
#include "src/sist.h"
int walk_directory_tree(const char *);
#endif

112
src/log.c
View File

@@ -1,112 +0,0 @@
#include "log.h"
#include <pthread.h>
#include <stdarg.h>
const char *log_colors[] = {
"\033[34m", "\033[01;34m", "\033[0m",
"\033[01;33m", "\033[31m", "\033[01;31m"
};
const char *log_levels[] = {
"DEBUG", "INFO", "WARNING", "ERROR", "FATAL"
};
void vsist_logf(const char *filepath, int level, char *format, va_list ap) {
static int is_tty = -1;
if (is_tty == -1) {
is_tty = isatty(STDERR_FILENO);
}
char log_str[LOG_MAX_LENGTH];
unsigned long long pid = (unsigned long long) pthread_self();
char datetime[32];
time_t t;
struct tm result;
t = time(NULL);
localtime_r(&t, &result);
strftime(datetime, sizeof(datetime), "%Y-%m-%d %H:%M:%S", &result);
int log_len;
if (is_tty) {
log_len = snprintf(
log_str, sizeof(log_str),
"\033[%dm[%04llX]%s [%s] [%s %s] ",
31 + ((unsigned int) (pid)) % 7, pid, log_colors[level],
datetime, log_levels[level], filepath
);
} else {
log_len = snprintf(
log_str, sizeof(log_str),
"[%04llX] [%s] [%s %s] ",
pid, datetime, log_levels[level], filepath
);
}
size_t maxsize = sizeof(log_str) - log_len;
log_len += vsnprintf(log_str + log_len, maxsize, format, ap);
if (is_tty) {
log_len += sprintf(log_str + log_len, "\033[0m\n");
} else {
*(log_str + log_len) = '\n';
log_len += 1;
}
int ret = write(STDERR_FILENO, log_str, log_len);
if (ret == -1) {
LOG_FATALF("serialize.c", "Could not write index descriptor: %s", strerror(errno))
}
}
void sist_logf(const char *filepath, int level, char *format, ...) {
va_list ap;
va_start(ap, format);
vsist_logf(filepath, level, format, ap);
va_end(ap);
}
void sist_log(const char *filepath, int level, char *str) {
static int is_tty = -1;
if (is_tty == -1) {
is_tty = isatty(STDERR_FILENO);
}
char log_str[LOG_MAX_LENGTH];
unsigned long long pid = (unsigned long long) pthread_self();
char datetime[32];
time_t t;
struct tm result;
t = time(NULL);
localtime_r(&t, &result);
strftime(datetime, sizeof(datetime), "%Y-%m-%d %H:%M:%S", &result);
int log_len;
if (is_tty) {
log_len = snprintf(
log_str, sizeof(log_str),
"\033[%dm[%04llX]%s [%s] [%s %s] %s \033[0m\n",
31 + ((unsigned int) (pid)) % 7, pid, log_colors[level],
datetime, log_levels[level], filepath,
str
);
} else {
log_len = snprintf(
log_str, sizeof(log_str),
"[%04llX] [%s] [%s %s] %s \n",
pid, datetime, log_levels[level], filepath,
str
);
}
int ret = write(STDERR_FILENO, log_str, log_len);
if (ret == -1) {
LOG_FATALF("serialize.c", "Could not write index descriptor: %s", strerror(errno));
}
}

View File

@@ -1,47 +0,0 @@
#ifndef SIST2_LOG_H
#define SIST2_LOG_H
#define LOG_MAX_LENGTH 8192
#define SIST_DEBUG 0
#define SIST_INFO 1
#define SIST_WARNING 2
#define SIST_ERROR 3
#define SIST_FATAL 4
#define LOG_DEBUGF(filepath, fmt, ...) \
if (LogCtx.very_verbose) {sist_logf(filepath, SIST_DEBUG, fmt, __VA_ARGS__);}
#define LOG_DEBUG(filepath, str) \
if (LogCtx.very_verbose) {sist_log(filepath, SIST_DEBUG, str);}
#define LOG_INFOF(filepath, fmt, ...) \
if (LogCtx.verbose) {sist_logf(filepath, SIST_INFO, fmt, __VA_ARGS__);}
#define LOG_INFO(filepath, str) \
if (LogCtx.verbose) {sist_log(filepath, SIST_INFO, str);}
#define LOG_WARNINGF(filepath, fmt, ...) \
if (LogCtx.verbose) {sist_logf(filepath, SIST_WARNING, fmt, __VA_ARGS__);}
#define LOG_WARNING(filepath, str) \
if (LogCtx.verbose) {sist_log(filepath, SIST_WARNING, str);}
#define LOG_ERRORF(filepath, fmt, ...) \
if (LogCtx.verbose) {sist_logf(filepath, SIST_ERROR, fmt, __VA_ARGS__);}
#define LOG_ERROR(filepath, str) \
if (LogCtx.verbose) {sist_log(filepath, SIST_ERROR, str);}
#define LOG_FATALF(filepath, fmt, ...) \
sist_logf(filepath, SIST_FATAL, fmt, __VA_ARGS__);\
exit(-1);
#define LOG_FATAL(filepath, str) \
sist_log(filepath, SIST_FATAL, str);\
exit(-1);
#include "sist.h"
void sist_logf(const char *filepath, int level, char *format, ...);
void vsist_logf(const char *filepath, int level, char *format, va_list ap);
void sist_log(const char *filepath, int level, char *str);
#endif

View File

@@ -1,25 +1,16 @@
#include "sist.h"
#include "ctx.h"
#include <third-party/argparse/argparse.h>
#include <glib.h>
#include "cli.h"
#include "io/serialize.h"
#include "io/store.h"
#include "tpool.h"
#include "io/walk.h"
#include "index/elastic.h"
#include "web/serve.h"
#include "parsing/mime.h"
#include "parsing/parse.h"
#ifndef SIST_SCAN_ONLY
#define DESCRIPTION "Lightning-fast file system indexer and search tool."
#else
#define DESCRIPTION "Lightning-fast file system indexer and search tool. (SCAN ONLY)"
#endif
#define EPILOG "Made by simon987 <me@simon987.net>. Released under GPL-3.0"
static const char *const Version = "2.2.0";
static const char *const Version = "1.0.11";
static const char *const usage[] = {
"sist2 scan [OPTION]... PATH",
"sist2 index [OPTION]... INDEX",
@@ -27,6 +18,13 @@ static const char *const usage[] = {
NULL,
};
void global_init() {
#ifndef SIST_SCAN_ONLY
curl_global_init(CURL_GLOBAL_NOTHING);
#endif
av_log_set_level(AV_LOG_QUIET);
}
void init_dir(const char *dirpath) {
char path[PATH_MAX];
snprintf(path, PATH_MAX, "%sdescriptor.json", dirpath);
@@ -36,132 +34,36 @@ void init_dir(const char *dirpath) {
uuid_unparse(uuid, ScanCtx.index.desc.uuid);
time(&ScanCtx.index.desc.timestamp);
strcpy(ScanCtx.index.desc.version, Version);
strcpy(ScanCtx.index.desc.type, INDEX_TYPE_BIN);
write_index_descriptor(path, &ScanCtx.index.desc);
}
void scan_print_header() {
LOG_INFOF("main.c", "sist2 v%s", Version)
printf("sist2 V%s\n", Version);
printf("---------------------\n");
printf("threads\t\t%d\n", ScanCtx.threads);
printf("tn_qscale\t%.1f/31.0\n", ScanCtx.tn_qscale);
printf("tn_size\t\t%dpx\n", ScanCtx.tn_size);
printf("output\t\t%s\n", ScanCtx.index.path);
}
void _store(char *key, size_t key_len, char *buf, size_t buf_len) {
store_write(ScanCtx.index.store, key, key_len, buf, buf_len);
}
void _log(const char *filepath, int level, char *str) {
if (level == LEVEL_FATAL) {
sist_log(filepath, level, str);
exit(-1);
}
if (LogCtx.verbose) {
if (level == LEVEL_DEBUG) {
if (LogCtx.very_verbose) {
sist_log(filepath, level, str);
}
} else {
sist_log(filepath, level, str);
}
}
}
void _logf(const char *filepath, int level, char *format, ...) {
va_list args;
va_start(args, format);
if (level == LEVEL_FATAL) {
sist_logf(filepath, level, format, args);
exit(-1);
}
if (LogCtx.verbose) {
if (level == LEVEL_DEBUG) {
if (LogCtx.very_verbose) {
vsist_logf(filepath, level, format, args);
}
} else {
sist_logf(filepath, level, format, args);
}
}
va_end(args);
}
void initialize_scan_context(scan_args_t *args) {
// Arc
ScanCtx.arc_ctx.mode = args->archive_mode;
ScanCtx.arc_ctx.log = _log;
ScanCtx.arc_ctx.logf = _logf;
ScanCtx.arc_ctx.parse = (parse_callback_t) parse;
// Cbr
ScanCtx.cbr_ctx.log = _log;
ScanCtx.cbr_ctx.logf = _logf;
ScanCtx.cbr_ctx.store = _store;
ScanCtx.cbr_ctx.cbr_mime = mime_get_mime_by_string(ScanCtx.mime_table, "application/x-cbr");
// Ebook
pthread_mutex_init(&ScanCtx.ebook_ctx.mupdf_mutex, NULL);
ScanCtx.ebook_ctx.content_size = args->content_size;
ScanCtx.ebook_ctx.tn_size = args->size;
ScanCtx.ebook_ctx.tesseract_lang = args->tesseract_lang;
ScanCtx.ebook_ctx.tesseract_path = args->tesseract_path;
ScanCtx.ebook_ctx.log = _log;
ScanCtx.ebook_ctx.logf = _logf;
ScanCtx.ebook_ctx.store = _store;
// Font
ScanCtx.font_ctx.enable_tn = args->size > 0;
ScanCtx.font_ctx.log = _log;
ScanCtx.font_ctx.logf = _logf;
ScanCtx.font_ctx.store = _store;
// Media
ScanCtx.media_ctx.tn_qscale = args->quality;
ScanCtx.media_ctx.tn_size = args->size;
ScanCtx.media_ctx.log = _log;
ScanCtx.media_ctx.logf = _logf;
ScanCtx.media_ctx.store = _store;
init_media();
// OOXML
ScanCtx.ooxml_ctx.content_size = args->content_size;
ScanCtx.ooxml_ctx.log = _log;
ScanCtx.ooxml_ctx.logf = _logf;
// MOBI
ScanCtx.mobi_ctx.content_size = args->content_size;
ScanCtx.mobi_ctx.log = _log;
ScanCtx.mobi_ctx.logf = _logf;
// TEXT
ScanCtx.text_ctx.content_size = args->content_size;
ScanCtx.text_ctx.log = _log;
ScanCtx.text_ctx.logf = _logf;
ScanCtx.threads = args->threads;
ScanCtx.depth = args->depth;
strncpy(ScanCtx.index.path, args->output, sizeof(ScanCtx.index.path));
strncpy(ScanCtx.index.desc.name, args->name, sizeof(ScanCtx.index.desc.name));
strncpy(ScanCtx.index.desc.root, args->path, sizeof(ScanCtx.index.desc.root));
strncpy(ScanCtx.index.desc.rewrite_url, args->rewrite_url, sizeof(ScanCtx.index.desc.rewrite_url));
ScanCtx.index.desc.root_len = (short) strlen(ScanCtx.index.desc.root);
ScanCtx.fast = args->fast;
}
void sist2_scan(scan_args_t *args) {
ScanCtx.mime_table = mime_get_mime_table();
ScanCtx.ext_table = mime_get_ext_table();
initialize_scan_context(args);
ScanCtx.tn_qscale = args->quality;
ScanCtx.tn_size = args->size;
ScanCtx.content_size = args->content_size;
ScanCtx.pool = tpool_create(args->threads, serializer_cleanup);
ScanCtx.threads = args->threads;
strncpy(ScanCtx.index.path, args->output, sizeof(ScanCtx.index.path));
strncpy(ScanCtx.index.desc.name, args->name, sizeof(ScanCtx.index.desc.name));
strcpy(ScanCtx.index.desc.root, args->path);
ScanCtx.index.desc.root_len = (short) strlen(ScanCtx.index.desc.root);
init_dir(ScanCtx.index.path);
ScanCtx.mime_table = mime_get_mime_table();
ScanCtx.ext_table = mime_get_ext_table();
char store_path[PATH_MAX];
snprintf(store_path, PATH_MAX, "%sthumbs", ScanCtx.index.path);
mkdir(store_path, S_IWUSR | S_IRUSR | S_IXUSR);
@@ -175,18 +77,9 @@ void sist2_scan(scan_args_t *args) {
DIR *dir = opendir(args->incremental);
if (dir == NULL) {
LOG_FATALF("main.c", "Could not open original index for incremental scan: %s", strerror(errno))
perror("opendir");
return;
}
char descriptor_path[PATH_MAX];
snprintf(descriptor_path, PATH_MAX, "%s/descriptor.json", args->incremental);
index_descriptor_t original_desc = read_index_descriptor(descriptor_path);
if (strcmp(original_desc.version, Version) != 0) {
LOG_FATALF("main.c", "Version mismatch! Index is %s but executable is %s/%s", original_desc.version,
Version, INDEX_VERSION_EXTERNAL)
}
struct dirent *de;
while ((de = readdir(dir)) != NULL) {
if (strncmp(de->d_name, "_index_", sizeof("_index_") - 1) == 0) {
@@ -197,11 +90,9 @@ void sist2_scan(scan_args_t *args) {
}
closedir(dir);
LOG_INFOF("main.c", "Loaded %d items in to mtime table.", g_hash_table_size(ScanCtx.original_table))
printf("Loaded %d items in to mtime table.", g_hash_table_size(ScanCtx.original_table));
}
ScanCtx.pool = tpool_create(args->threads, thread_cleanup);
tpool_start(ScanCtx.pool);
walk_directory_tree(ScanCtx.index.desc.root);
tpool_wait(ScanCtx.pool);
tpool_destroy(ScanCtx.pool);
@@ -232,10 +123,10 @@ void sist2_scan(scan_args_t *args) {
store_destroy(ScanCtx.index.store);
}
#ifndef SIST_SCAN_ONLY
void sist2_index(index_args_t *args) {
IndexCtx.es_url = args->es_url;
IndexCtx.batch_size = args->batch_size;
if (!args->print) {
elastic_init(args->force_reset);
@@ -245,17 +136,15 @@ void sist2_index(index_args_t *args) {
snprintf(descriptor_path, PATH_MAX, "%s/descriptor.json", args->index_path);
index_descriptor_t desc = read_index_descriptor(descriptor_path);
LOG_DEBUGF("main.c", "descriptor version %s (%s)", desc.version, desc.type)
if (strcmp(desc.version, Version) != 0 && strcmp(desc.version, INDEX_VERSION_EXTERNAL) != 0) {
LOG_FATALF("main.c", "Version mismatch! Index is %s but executable is %s/%s", desc.version, Version,
INDEX_VERSION_EXTERNAL)
if (strcmp(desc.version, Version) != 0) {
fprintf(stderr, "Version mismatch! Index is v%s but executable is v%s\n", desc.version, Version);
return;
}
DIR *dir = opendir(args->index_path);
if (dir == NULL) {
LOG_FATALF("main.c", "Could not open index %s: %s", args->index_path, strerror(errno))
perror("opendir");
return;
}
index_func f;
@@ -270,14 +159,13 @@ void sist2_index(index_args_t *args) {
if (strncmp(de->d_name, "_index_", sizeof("_index_") - 1) == 0) {
char file_path[PATH_MAX];
snprintf(file_path, PATH_MAX, "%s/%s", args->index_path, de->d_name);
read_index(file_path, desc.uuid, desc.type, f);
read_index(file_path, desc.uuid, f);
}
}
closedir(dir);
if (!args->print) {
elastic_flush();
destroy_indexer(args->script, desc.uuid);
destroy_indexer();
}
}
@@ -285,9 +173,6 @@ void sist2_web(web_args_t *args) {
WebCtx.es_url = args->es_url;
WebCtx.index_count = args->index_count;
WebCtx.auth_user = args->auth_user;
WebCtx.auth_pass = args->auth_pass;
WebCtx.auth_enabled = args->auth_enabled;
for (int i = 0; i < args->index_count; i++) {
char *abs_path = abspath(args->indices[i]);
@@ -307,62 +192,51 @@ void sist2_web(web_args_t *args) {
free(abs_path);
}
serve(args->listen_address);
serve(args->bind, args->port);
}
#endif
int main(int argc, const char *argv[]) {
global_init();
scan_args_t *scan_args = scan_args_create();
#ifndef SIST_SCAN_ONLY
index_args_t *index_args = index_args_create();
web_args_t *web_args = web_args_create();
#endif
int arg_version = 0;
char *common_es_url = NULL;
char * common_es_url = NULL;
struct argparse_option options[] = {
OPT_HELP(),
OPT_BOOLEAN('v', "version", &arg_version, "Show version and exit"),
OPT_BOOLEAN(0, "verbose", &LogCtx.verbose, "Turn on logging"),
OPT_BOOLEAN(0, "very-verbose", &LogCtx.very_verbose, "Turn on debug messages"),
OPT_GROUP("Scan options"),
OPT_INTEGER('t', "threads", &scan_args->threads, "Number of threads. DEFAULT=1"),
OPT_FLOAT('q', "quality", &scan_args->quality,
"Thumbnail quality, on a scale of 1.0 to 31.0, 1.0 being the best. DEFAULT=5"),
OPT_INTEGER(0, "size", &scan_args->size,
"Thumbnail size, in pixels. Use negative value to disable. DEFAULT=500"),
"Thumbnail quality, on a scale of 1.0 to 31.0, 1.0 being the best. DEFAULT=15"),
OPT_INTEGER(0, "size", &scan_args->size, "Thumbnail size, in pixels. DEFAULT=200"),
OPT_INTEGER(0, "content-size", &scan_args->content_size,
"Number of bytes to be extracted from text documents. Use negative value to disable. DEFAULT=32768"),
"Number of bytes to be extracted from text documents. DEFAULT=4096"),
OPT_STRING(0, "incremental", &scan_args->incremental,
"Reuse an existing index and only scan modified files."),
OPT_STRING('o', "output", &scan_args->output, "Output directory. DEFAULT=index.sist2/"),
OPT_STRING(0, "rewrite-url", &scan_args->rewrite_url, "Serve files from this url instead of from disk."),
OPT_STRING(0, "name", &scan_args->name, "Index display name. DEFAULT: (name of the directory)"),
OPT_INTEGER(0, "depth", &scan_args->depth, "Scan up to DEPTH subdirectories deep. "
"Use 0 to only scan files in PATH. DEFAULT: -1"),
OPT_STRING(0, "archive", &scan_args->archive, "Archive file mode (skip|list|shallow|recurse). "
"skip: Don't parse, list: only get file names as text, "
"shallow: Don't parse archives inside archives. DEFAULT: recurse"),
OPT_STRING(0, "ocr", &scan_args->tesseract_lang, "Tesseract language (use tesseract --list-langs to see "
"which are installed on your machine)"),
OPT_STRING('e', "exclude", &scan_args->exclude_regex, "Files that match this regex will not be scanned"),
OPT_BOOLEAN(0, "fast", &scan_args->fast, "Only index file names & mime type"),
#ifndef SIST_SCAN_ONLY
OPT_GROUP("Index options"),
OPT_STRING(0, "es-url", &common_es_url, "Elasticsearch url with port. DEFAULT=http://localhost:9200"),
OPT_STRING(0, "es-url", &common_es_url, "Elasticsearch url. DEFAULT=http://localhost:9200"),
OPT_BOOLEAN('p', "print", &index_args->print, "Just print JSON documents to stdout."),
OPT_STRING(0, "script-file", &index_args->script_path, "Path to user script."),
OPT_INTEGER(0, "batch-size", &index_args->batch_size, "Index batch size. DEFAULT: 100"),
OPT_BOOLEAN('f', "force-reset", &index_args->force_reset, "Reset Elasticsearch mappings and settings. "
"(You must use this option the first time you use the index command)"),
"(You must use this option the first time you use the index command)"),
OPT_GROUP("Web options"),
OPT_STRING(0, "es-url", &common_es_url, "Elasticsearch url. DEFAULT=http://localhost:9200"),
OPT_STRING(0, "bind", &web_args->listen_address, "Listen on this address. DEFAULT=localhost:4090"),
OPT_STRING(0, "auth", &web_args->credentials, "Basic auth in user:password format"),
OPT_STRING(0, "bind", &web_args->bind, "Listen on this address. DEFAULT=localhost"),
OPT_STRING(0, "port", &web_args->port, "Listen on this port. DEFAULT=4090"),
#endif
OPT_END(),
};
@@ -372,34 +246,30 @@ int main(int argc, const char *argv[]) {
argparse_describe(&argparse, DESCRIPTION, EPILOG);
argc = argparse_parse(&argparse, argc, argv);
if (arg_version) {
printf(Version);
goto end;
}
if (LogCtx.very_verbose != 0) {
LogCtx.verbose = 1;
}
#ifndef SIST_SCAN_ONLY
web_args->es_url = common_es_url;
index_args->es_url = common_es_url;
#endif
if (argc == 0) {
argparse_usage(&argparse);
goto end;
return 1;
} else if (strcmp(argv[0], "scan") == 0) {
int err = scan_args_validate(scan_args, argc, argv);
if (err != 0) {
goto end;
return err;
}
sist2_scan(scan_args);
} else if (strcmp(argv[0], "index") == 0) {
}
#ifndef SIST_SCAN_ONLY
else if (strcmp(argv[0], "index") == 0) {
int err = index_args_validate(index_args, argc, argv);
if (err != 0) {
goto end;
return err;
}
sist2_index(index_args);
@@ -407,21 +277,17 @@ int main(int argc, const char *argv[]) {
int err = web_args_validate(web_args, argc, argv);
if (err != 0) {
goto end;
return err;
}
sist2_web(web_args);
} else {
}
#endif
else {
fprintf(stderr, "Invalid command: '%s'\n", argv[0]);
argparse_usage(&argparse);
goto end;
return 1;
}
printf("\n");
end:
scan_args_destroy(scan_args);
index_args_destroy(index_args);
web_args_destroy(web_args);
return 0;
}

215
src/parsing/font.c Normal file
View File

@@ -0,0 +1,215 @@
#include "font.h"
#include "ft2build.h"
#include "freetype/freetype.h"
#include "src/ctx.h"
__thread FT_Library library = NULL;
typedef struct text_dimensions {
unsigned int width;
unsigned int height;
unsigned int baseline;
} text_dimensions_t;
typedef struct glyph {
unsigned int top;
unsigned int height;
unsigned int width;
unsigned int descent;
unsigned int ascent;
unsigned int advance_width;
unsigned char *pixmap;
} glyph_t;
__always_inline
int kerning_offset(char c, char pc, FT_Face face) {
FT_Vector kerning;
FT_Get_Kerning(face, c, pc, FT_KERNING_DEFAULT, &kerning);
return (int) (kerning.x / 64);
}
__always_inline
glyph_t ft_glyph_to_glyph(FT_GlyphSlot slot) {
glyph_t glyph;
glyph.pixmap = slot->bitmap.buffer;
glyph.width = slot->bitmap.width;
glyph.height = slot->bitmap.rows;
glyph.top = slot->bitmap_top;
glyph.advance_width = slot->advance.x / 64;
glyph.descent = MAX(0, glyph.height - glyph.top);
glyph.ascent = MAX(0, MAX(glyph.top, glyph.height) - glyph.descent);
return glyph;
}
__always_inline
glyph_t get_glyph(char character, FT_Face face) {
}
text_dimensions_t text_dimension(char *text, FT_Face face) {
text_dimensions_t dimensions;
dimensions.width = 0;
int num_chars = (int) strlen(text);
unsigned int max_ascent = 0;
unsigned int max_descent = 0;
char pc = 0;
for (int i = 0; i < num_chars; i++) {
char c = text[i];
FT_Load_Char(face, c, 0);
glyph_t glyph = ft_glyph_to_glyph(face->glyph);
max_descent = MAX(max_descent, glyph.descent);
max_ascent = MAX(max_ascent, glyph.ascent);
int kerning_x = kerning_offset(c, pc, face);
dimensions.width += MAX(glyph.advance_width, glyph.width) + kerning_x;
pc = c;
}
dimensions.height = max_ascent + max_descent;
dimensions.baseline = max_descent;
return dimensions;
}
void draw_glyph(glyph_t *glyph, int x, int y, struct text_dimensions text_info, unsigned char *bitmap) {
unsigned int src = 0;
unsigned int dst = y * text_info.width + x;
unsigned int row_offset = text_info.width - glyph->width;
unsigned int buf_len = text_info.width * text_info.height;
for (unsigned int sy = 0; sy < glyph->height; sy++) {
for (unsigned int sx = 0; sx < glyph->width; sx++) {
if (dst < buf_len) {
bitmap[dst] |= glyph->pixmap[src];
}
src++;
dst++;
}
dst += row_offset;
}
}
void bmp_format(dyn_buffer_t *buf, text_dimensions_t dimensions, const unsigned char *bitmap) {
dyn_buffer_write_short(buf, 0x4D42); // Magic
dyn_buffer_write_int(buf, 0); // Size placeholder
dyn_buffer_write_int(buf, 0x5157); //Reserved
dyn_buffer_write_int(buf, 14 + 40 + 256 * 4); // pixels offset
dyn_buffer_write_int(buf, 40); // DIB size
dyn_buffer_write_int(buf, (int) dimensions.width);
dyn_buffer_write_int(buf, (int) dimensions.height);
dyn_buffer_write_short(buf, 1); // Color planes
dyn_buffer_write_short(buf, 8); // bits per pixel
dyn_buffer_write_int(buf, 0); // compression
dyn_buffer_write_int(buf, 0); // Ignored
dyn_buffer_write_int(buf, 3800); // hres
dyn_buffer_write_int(buf, 3800); // vres
dyn_buffer_write_int(buf, 256); // Color count
dyn_buffer_write_int(buf, 0); // Ignored
// RGBA32 Color table (Grayscale)
for (int i = 255; i >= 0; i--) {
dyn_buffer_write_int(buf, i + (i << 8) + (i << 16));
}
// Pixel array: write from bottom to top, with rows padded to multiples of 4-bytes
for (int y = (int) dimensions.height - 1; y >= 0; y--) {
for (unsigned int x = 0; x < dimensions.width; x++) {
dyn_buffer_write_char(buf, (char) bitmap[y * dimensions.width + x]);
}
while (buf->cur % 4 != 0) {
dyn_buffer_write_char(buf, 0);
}
}
// Size
*(int *) ((char *) buf->buf + 2) = buf->cur;
}
void parse_font(const char *buf, size_t buf_len, document_t *doc) {
if (library == NULL) {
FT_Init_FreeType(&library);
}
FT_Face face;
FT_Error err = FT_New_Memory_Face(library, (unsigned char *) buf, buf_len, 0, &face);
if (err != 0) {
return;
}
char font_name[1024];
if (face->style_name == NULL || *(face->style_name) == '?') {
if (face->family_name == NULL) {
strcpy(font_name, "(null)");
} else {
strcpy(font_name, face->family_name);
}
} else {
snprintf(font_name, sizeof(font_name), "%s %s", face->family_name, face->style_name);
}
meta_line_t *meta_name = malloc(sizeof(meta_line_t) + strlen(font_name));
meta_name->key = MetaFontName;
strcpy(meta_name->strval, font_name);
APPEND_META(doc, meta_name)
int pixel = 64;
int num_chars = (int) strlen(font_name);
err = FT_Set_Pixel_Sizes(face, 0, pixel);
if (err != 0) {
return;
}
text_dimensions_t dimensions = text_dimension(font_name, face);
unsigned char *bitmap = calloc(dimensions.width * dimensions.height, 1);
FT_Vector pen;
pen.x = 0;
char pc = 0;
for (int i = 0; i < num_chars; i++) {
char c = font_name[i];
err = FT_Load_Char(face, c, FT_LOAD_NO_HINTING | FT_LOAD_RENDER);
if (err != 0) {
continue;
}
glyph_t glyph = ft_glyph_to_glyph(face->glyph);
pen.x += kerning_offset(c, pc, face);
pen.y = dimensions.height - glyph.ascent - dimensions.baseline;
draw_glyph(&glyph, pen.x, pen.y, dimensions, bitmap);
pen.x += glyph.advance_width;
pc = c;
}
dyn_buffer_t bmp_data = dyn_buffer_create();
bmp_format(&bmp_data, dimensions, bitmap);
store_write(ScanCtx.index.store, (char *) doc->uuid, sizeof(doc->uuid), (char *) bmp_data.buf, bmp_data.cur);
dyn_buffer_destroy(&bmp_data);
free(bitmap);
FT_Done_Face(face);
}

9
src/parsing/font.h Normal file
View File

@@ -0,0 +1,9 @@
#ifndef SIST2_FONT_H
#define SIST2_FONT_H
#include "src/sist.h"
void parse_font(const char * buf, size_t buf_len, document_t *doc);
#endif

278
src/parsing/media.c Normal file
View File

@@ -0,0 +1,278 @@
#include "src/sist.h"
#include "src/ctx.h"
AVCodecContext *alloc_jpeg_encoder(int dstW, int dstH, float qscale) {
AVCodec *jpeg_codec = avcodec_find_encoder(AV_CODEC_ID_MJPEG);
AVCodecContext *jpeg = avcodec_alloc_context3(jpeg_codec);
jpeg->width = dstW;
jpeg->height = dstH;
jpeg->time_base.den = 1000000;
jpeg->time_base.num = 1;
jpeg->i_quant_factor = qscale;
jpeg->pix_fmt = AV_PIX_FMT_YUVJ420P;
int ret = avcodec_open2(jpeg, jpeg_codec, NULL);
if (ret != 0) {
printf("Could not open jpeg encoder: %s!\n", av_err2str(ret));
return NULL;
}
return jpeg;
}
AVFrame *scale_frame(const AVCodecContext *decoder, const AVFrame *frame, int size) {
AVFrame *scaled_frame = av_frame_alloc();
int dstW;
int dstH;
if (frame->width <= size && frame->height <= size) {
dstW = frame->width;
dstH = frame->height;
} else {
double ratio = (double) frame->width / frame->height;
if (frame->width > frame->height) {
dstW = size;
dstH = (int) (size / ratio);
} else {
dstW = (int) (size * ratio);
dstH = size;
}
}
struct SwsContext *ctx = sws_getContext(
decoder->width, decoder->height, decoder->pix_fmt,
dstW, dstH, AV_PIX_FMT_YUVJ420P,
SWS_FAST_BILINEAR, 0, 0, 0
);
int dst_buf_len = avpicture_get_size(AV_PIX_FMT_YUVJ420P, dstW, dstH);
uint8_t *dst_buf = (uint8_t *) av_malloc(dst_buf_len);
avpicture_fill((AVPicture *) scaled_frame, dst_buf, AV_PIX_FMT_YUVJ420P, dstW, dstH);
sws_scale(ctx,
(const uint8_t *const *) frame->data, frame->linesize,
0, decoder->height,
scaled_frame->data, scaled_frame->linesize
);
scaled_frame->width = dstW;
scaled_frame->height = dstH;
scaled_frame->format = AV_PIX_FMT_YUV420P;
sws_freeContext(ctx);
return scaled_frame;
}
AVFrame *read_frame(AVFormatContext *pFormatCtx, AVCodecContext *decoder, int stream_idx) {
AVFrame *frame = av_frame_alloc();
AVPacket avPacket;
av_init_packet(&avPacket);
int receive_ret = -EAGAIN;
while (receive_ret == -EAGAIN) {
// Get video frame
while (1) {
int read_frame_ret = av_read_frame(pFormatCtx, &avPacket);
if (read_frame_ret != 0) {
if (read_frame_ret != AVERROR_EOF) {
fprintf(stderr, "Error reading frame: %s\n", av_err2str(read_frame_ret));
}
av_frame_free(&frame);
av_packet_unref(&avPacket);
return NULL;
}
//Ignore audio/other frames
if (avPacket.stream_index != stream_idx) {
av_packet_unref(&avPacket);
continue;
}
break;
}
// Feed it to decoder
int decode_ret = avcodec_send_packet(decoder, &avPacket);
if (decode_ret != 0) {
printf("Error decoding frame: %s\n", av_err2str(decode_ret));
}
av_packet_unref(&avPacket);
receive_ret = avcodec_receive_frame(decoder, frame);
}
return frame;
}
void append_audio_meta(AVFormatContext *pFormatCtx, document_t *doc) {
AVDictionaryEntry *tag = NULL;
while ((tag = av_dict_get(pFormatCtx->metadata, "", tag, AV_DICT_IGNORE_SUFFIX))) {
char *key = tag->key;
for (; *key; ++key) *key = (char) tolower(*key);
if (strcmp(tag->key, "artist") == 0) {
size_t len = strlen(tag->value);
meta_line_t *meta_tag = malloc(sizeof(meta_line_t) + len);
meta_tag->key = MetaArtist;
memcpy(meta_tag->strval, tag->value, len);
APPEND_META(doc, meta_tag)
} else if (strcmp(tag->key, "genre") == 0) {
size_t len = strlen(tag->value);
meta_line_t *meta_tag = malloc(sizeof(meta_line_t) + len);
meta_tag->key = MetaGenre;
memcpy(meta_tag->strval, tag->value, len);
APPEND_META(doc, meta_tag)
} else if (strcmp(tag->key, "title") == 0) {
size_t len = strlen(tag->value);
meta_line_t *meta_tag = malloc(sizeof(meta_line_t) + len);
meta_tag->key = MetaTitle;
memcpy(meta_tag->strval, tag->value, len);
APPEND_META(doc, meta_tag)
} else if (strcmp(tag->key, "album_artist") == 0) {
size_t len = strlen(tag->value);
meta_line_t *meta_tag = malloc(sizeof(meta_line_t) + len);
meta_tag->key = MetaAlbumArtist;
memcpy(meta_tag->strval, tag->value, len);
APPEND_META(doc, meta_tag)
} else if (strcmp(tag->key, "album") == 0) {
size_t len = strlen(tag->value);
meta_line_t *meta_tag = malloc(sizeof(meta_line_t) + len);
meta_tag->key = MetaAlbum;
memcpy(meta_tag->strval, tag->value, len);
APPEND_META(doc, meta_tag)
}
}
}
void parse_media(const char *filepath, document_t *doc) {
int video_stream = -1;
int audio_stream = -1;
AVFormatContext *pFormatCtx = avformat_alloc_context();
if (pFormatCtx == NULL) {
fprintf(stderr, "Could not allocate AVFormatContext! %s \n", filepath);
return;
}
int res = avformat_open_input(&pFormatCtx, filepath, NULL, NULL);
if (res < 0) {
printf("ERR%s %s\n", filepath, av_err2str(res));
return;
}
avformat_find_stream_info(pFormatCtx, NULL);
for (int i = (int) pFormatCtx->nb_streams - 1; i >= 0; i--) {
AVStream *stream = pFormatCtx->streams[i];
if (stream->codecpar->codec_type == AVMEDIA_TYPE_AUDIO) {
if (audio_stream == -1) {
meta_line_t *meta_audio = malloc(sizeof(meta_line_t));
meta_audio->key = MetaMediaAudioCodec;
meta_audio->intval = stream->codecpar->codec_id;
APPEND_META(doc, meta_audio)
append_audio_meta(pFormatCtx, doc);
audio_stream = i;
}
} else if (stream->codecpar->codec_type == AVMEDIA_TYPE_VIDEO) {
if (video_stream == -1) {
meta_line_t *meta_vid = malloc(sizeof(meta_line_t));
meta_vid->key = MetaMediaVideoCodec;
meta_vid->intval = stream->codecpar->codec_id;
APPEND_META(doc, meta_vid)
meta_line_t *meta_w = malloc(sizeof(meta_line_t));
meta_w->key = MetaWidth;
meta_w->intval = stream->codecpar->width;
APPEND_META(doc, meta_w)
meta_line_t *meta_h = malloc(sizeof(meta_line_t));
meta_h->key = MetaHeight;
meta_h->intval = stream->codecpar->height;
APPEND_META(doc, meta_h)
video_stream = i;
}
}
}
if (video_stream != -1) {
AVStream *stream = pFormatCtx->streams[video_stream];
if (stream->nb_frames > 1) {
//This is a video (not a still image)
meta_line_t *meta_duration = malloc(sizeof(meta_line_t));
meta_duration->key = MetaMediaDuration;
meta_duration->longval = pFormatCtx->duration / AV_TIME_BASE;
APPEND_META(doc, meta_duration)
meta_line_t *meta_bitrate = malloc(sizeof(meta_line_t));
meta_bitrate->key = MetaMediaBitrate;
meta_bitrate->intval = pFormatCtx->bit_rate;
APPEND_META(doc, meta_bitrate)
}
if (stream->codecpar->width <= 20 || stream->codecpar->height <= 20) {
avformat_close_input(&pFormatCtx);
avformat_free_context(pFormatCtx);
return;
}
// Decoder
AVCodec *video_codec = avcodec_find_decoder(stream->codecpar->codec_id);
AVCodecContext *decoder = avcodec_alloc_context3(video_codec);
avcodec_parameters_to_context(decoder, stream->codecpar);
avcodec_open2(decoder, video_codec, NULL);
//Seek
if (stream->nb_frames > 1 && stream->codecpar->codec_id != AV_CODEC_ID_GIF) {
int seek_ret = 0;
for (int i = 20; i >= 0; i--) {
seek_ret = av_seek_frame(pFormatCtx, video_stream,
stream->duration * 0.10, 0);
if (seek_ret == 0) {
break;
}
}
}
AVFrame *frame = read_frame(pFormatCtx, decoder, video_stream);
if (frame == NULL) {
avcodec_free_context(&decoder);
avformat_close_input(&pFormatCtx);
avformat_free_context(pFormatCtx);
return;
}
// Scale frame
AVFrame *scaled_frame = scale_frame(decoder, frame, ScanCtx.tn_size);
// Encode frame to jpeg
AVCodecContext *jpeg_encoder = alloc_jpeg_encoder(scaled_frame->width, scaled_frame->height, ScanCtx.tn_qscale);
avcodec_send_frame(jpeg_encoder, scaled_frame);
AVPacket jpeg_packet;
av_init_packet(&jpeg_packet);
avcodec_receive_packet(jpeg_encoder, &jpeg_packet);
// Save thumbnail
store_write(ScanCtx.index.store, (char *) doc->uuid, sizeof(doc->uuid), (char *) jpeg_packet.data, jpeg_packet.size);
av_packet_unref(&jpeg_packet);
av_frame_free(&frame);
av_free(*scaled_frame->data);
av_frame_free(&scaled_frame);
avcodec_free_context(&jpeg_encoder);
avcodec_free_context(&decoder);
}
avformat_close_input(&pFormatCtx);
avformat_free_context(pFormatCtx);
}

11
src/parsing/media.h Normal file
View File

@@ -0,0 +1,11 @@
#ifndef SIST2_MEDIA_H
#define SIST2_MEDIA_H
#include "src/sist.h"
#define MIN_VIDEO_SIZE 1024 * 64
void parse_media(const char * filepath, document_t *doc);
#endif

View File

@@ -1,12 +1,10 @@
#include "mime.h"
unsigned int mime_get_mime_by_ext(GHashTable *ext_table, const char * ext) {
char lower[8];
char lower[64];
char *p = lower;
int cnt = 0;
while ((*ext) != '\0' && cnt + 1 < sizeof(lower)) {
while ((*ext)) {
*p++ = (char)tolower(*ext++);
cnt++;
}
*p = '\0';
return (size_t) g_hash_table_lookup(ext_table, lower);

View File

@@ -1,14 +1,14 @@
#ifndef SIST2_MIME_H
#define SIST2_MIME_H
#include "../sist.h"
#include "src/sist.h"
#define MAJOR_MIME(mime_id) (mime_id & 0x00FF0000) >> 16
#define MAJOR_MIME(mime_id) (mime_id & 0x0FFF0000) >> 16
#define MIME_EMPTY 1
#define DONT_PARSE 0x80000000
#define SHOULD_PARSE(mime_id) (ScanCtx.fast == 0 && (mime_id & DONT_PARSE) != DONT_PARSE && mime_id != 0)
#define SHOULD_PARSE(mime_id) (mime_id & DONT_PARSE) != DONT_PARSE
#define PDF_MASK 0x40000000
#define IS_PDF(mime_id) (mime_id & PDF_MASK) == PDF_MASK
@@ -16,21 +16,6 @@
#define FONT_MASK 0x20000000
#define IS_FONT(mime_id) (mime_id & FONT_MASK) == FONT_MASK
#define ARC_MASK 0x10000000
#define IS_ARC(mime_id) (mime_id & ARC_MASK) == ARC_MASK
#define ARC_FILTER_MASK 0x08000000
#define IS_ARC_FILTER(mime_id) (mime_id & ARC_FILTER_MASK) == ARC_FILTER_MASK
#define DOC_MASK 0x04000000
#define IS_DOC(mime_id) (mime_id & DOC_MASK) == DOC_MASK
#define MOBI_MASK 0x02000000
#define IS_MOBI(mime_id) (mime_id & MOBI_MASK) == MOBI_MASK
#define MARKUP_MASK 0x01000000
#define IS_MARKUP(mime_id) (mime_id & MARKUP_MASK) == MARKUP_MASK
enum major_mime {
MimeInvalid = 0,
MimeModel = 1,

File diff suppressed because it is too large Load Diff

View File

@@ -1,41 +1,34 @@
#include "parse.h"
#include "src/sist.h"
#include "src/ctx.h"
#include "mime.h"
#include "src/io/serialize.h"
#include <magic.h>
__thread magic_t Magic;
void *read_all(parse_job_t *job, const char *buf, int bytes_read, int *fd) {
#define MIN_VIDEO_SIZE 1024 * 64
#define MIN_IMAGE_SIZE 1024 * 2
void *full_buf;
int fs_read(struct vfile *f, void *buf, size_t size) {
if (f->fd == -1) {
f->fd = open(f->filepath, O_RDONLY);
if (f->fd == -1) {
LOG_ERRORF(f->filepath, "open(): [%d] %s", errno, strerror(errno))
return -1;
if (job->info.st_size <= bytes_read) {
full_buf = malloc(job->info.st_size);
memcpy(full_buf, buf, job->info.st_size);
} else {
if (*fd == -1) {
*fd = open(job->filepath, O_RDONLY);
if (*fd == -1) {
perror("open");
printf("%s\n", job->filepath);
free(job);
return NULL;
}
}
full_buf = malloc(job->info.st_size);
memcpy(full_buf, buf, bytes_read);
int ret = read(*fd, full_buf + bytes_read, job->info.st_size - bytes_read);
if (ret == -1) {
perror("read");
}
}
return read(f->fd, buf, size);
}
#define CLOSE_FILE(f) if (f.close != NULL) {f.close(&f);};
void fs_close(struct vfile *f) {
if (f->fd != -1) {
close(f->fd);
}
}
void fs_reset(struct vfile *f) {
if (f->fd != -1) {
lseek(f->fd, 0, SEEK_SET);
}
return full_buf;
}
void parse(void *arg) {
@@ -43,12 +36,16 @@ void parse(void *arg) {
parse_job_t *job = arg;
document_t doc;
int inc_ts = incremental_get(ScanCtx.original_table, job->vfile.info.st_ino);
if (inc_ts != 0 && inc_ts == job->vfile.info.st_mtim.tv_sec) {
incremental_mark_file_for_copy(ScanCtx.copy_table, job->vfile.info.st_ino);
if (incremental_get(ScanCtx.original_table, job->info.st_ino) == job->info.st_mtim.tv_sec) {
incremental_mark_file_for_copy(ScanCtx.copy_table, job->info.st_ino);
free(job);
return;
}
if (Magic == NULL) {
Magic = magic_open(MAGIC_MIME_TYPE);
magic_load(Magic, NULL);
}
doc.filepath = job->filepath;
doc.ext = (short) job->ext;
@@ -56,114 +53,74 @@ void parse(void *arg) {
doc.meta_head = NULL;
doc.meta_tail = NULL;
doc.mime = 0;
doc.size = job->vfile.info.st_size;
doc.ino = job->vfile.info.st_ino;
doc.mtime = job->vfile.info.st_mtim.tv_sec;
doc.size = job->info.st_size;
doc.ino = job->info.st_ino;
doc.mtime = job->info.st_mtim.tv_sec;
uuid_generate(doc.uuid);
char *buf[PARSE_BUF_SIZE];
if (LogCtx.very_verbose) {
char uuid_str[UUID_STR_LEN];
uuid_unparse(doc.uuid, uuid_str);
LOG_DEBUGF(job->filepath, "Starting parse job {%s}", uuid_str)
}
if (job->vfile.info.st_size == 0) {
if (job->info.st_size == 0) {
doc.mime = MIME_EMPTY;
} else if (*(job->filepath + job->ext) != '\0' && (job->ext - job->base != 1)) {
} else if (*(job->filepath + job->ext) != '\0') {
doc.mime = mime_get_mime_by_ext(ScanCtx.ext_table, job->filepath + job->ext);
}
int fd = -1;
int bytes_read = 0;
if (doc.mime == 0 && !ScanCtx.fast) {
if (doc.mime == 0) {
// Get mime type with libmagic
bytes_read = job->vfile.read(&job->vfile, buf, PARSE_BUF_SIZE);
if (bytes_read < 0) {
if (job->vfile.is_fs_file) {
LOG_ERRORF(job->filepath, "read(): [%d] %s", errno, strerror(errno))
} else {
LOG_ERRORF(job->filepath, "(virtual) read(): [%d] %s", bytes_read, archive_error_string(job->vfile.arc))
}
CLOSE_FILE(job->vfile)
fd = open(job->filepath, O_RDONLY);
if (fd == -1) {
perror("open");
free(job);
return;
}
magic_t magic = magic_open(MAGIC_MIME_TYPE);
magic_load(magic, NULL);
bytes_read = read(fd, buf, PARSE_BUF_SIZE);
const char *magic_mime_str = magic_buffer(magic, buf, bytes_read);
const char *magic_mime_str = magic_buffer(Magic, buf, bytes_read);
if (magic_mime_str != NULL) {
doc.mime = mime_get_mime_by_string(ScanCtx.mime_table, magic_mime_str);
LOG_DEBUGF(job->filepath, "libmagic: %s", magic_mime_str);
if (doc.mime == 0) {
LOG_WARNINGF(job->filepath, "Couldn't find mime %s", magic_mime_str);
fprintf(stderr, "Couldn't find mime %s, %s!\n", magic_mime_str, job->filepath + job->base);
}
}
job->vfile.reset(&job->vfile);
magic_close(magic);
}
int mmime = MAJOR_MIME(doc.mime);
if (!(SHOULD_PARSE(doc.mime))) {
} else if ((mmime == MimeVideo && doc.size >= MIN_VIDEO_SIZE) ||
(mmime == MimeImage && doc.size >= MIN_IMAGE_SIZE) || mmime == MimeAudio) {
parse_media(&ScanCtx.media_ctx, &job->vfile, &doc);
} else if ((mmime == MimeVideo && doc.size >= MIN_VIDEO_SIZE) || mmime == MimeAudio || mmime == MimeImage) {
parse_media(job->filepath, &doc);
} else if (IS_PDF(doc.mime)) {
parse_ebook(&ScanCtx.ebook_ctx, &job->vfile, mime_get_mime_text(doc.mime), &doc);
void *pdf_buf = read_all(job, (char *) buf, bytes_read, &fd);
parse_pdf(pdf_buf, doc.size, &doc);
} else if (mmime == MimeText && ScanCtx.text_ctx.content_size > 0) {
if (IS_MARKUP(doc.mime)) {
parse_markup(&ScanCtx.text_ctx, &job->vfile, &doc);
} else {
parse_text(&ScanCtx.text_ctx, &job->vfile, &doc);
if (pdf_buf != buf) {
free(pdf_buf);
}
} else if (mmime == MimeText && ScanCtx.content_size > 0) {
parse_text(bytes_read, &fd, (char *) buf, &doc);
} else if (IS_FONT(doc.mime)) {
parse_font(&ScanCtx.font_ctx, &job->vfile, &doc);
void *font_buf = read_all(job, (char *) buf, bytes_read, &fd);
parse_font(font_buf, doc.size, &doc);
} else if (
ScanCtx.arc_ctx.mode != ARC_MODE_SKIP && (
IS_ARC(doc.mime) ||
(IS_ARC_FILTER(doc.mime) && should_parse_filtered_file(doc.filepath, doc.ext))
)) {
parse_archive(&ScanCtx.arc_ctx, &job->vfile, &doc);
} else if (ScanCtx.ooxml_ctx.content_size > 0 && IS_DOC(doc.mime)) {
parse_ooxml(&ScanCtx.ooxml_ctx, &job->vfile, &doc);
} else if (is_cbr(&ScanCtx.cbr_ctx, doc.mime)) {
parse_cbr(&ScanCtx.cbr_ctx, &job->vfile, &doc);
} else if (IS_MOBI(doc.mime)) {
parse_mobi(&ScanCtx.mobi_ctx, &job->vfile, &doc);
}
//Parent meta
if (!uuid_is_null(job->parent)) {
char tmp[UUID_STR_LEN];
uuid_unparse(job->parent, tmp);
meta_line_t *meta_parent = malloc(sizeof(meta_line_t) + UUID_STR_LEN + 1);
meta_parent->key = MetaParent;
strcpy(meta_parent->str_val, tmp);
APPEND_META((&doc), meta_parent)
if (font_buf != buf) {
free(font_buf);
}
}
write_document(&doc);
CLOSE_FILE(job->vfile)
}
if (fd != -1) {
close(fd);
}
void cleanup_parse() {
// noop
free(job);
}

View File

@@ -1,16 +1,10 @@
#ifndef SIST2_PARSE_H
#define SIST2_PARSE_H
#include "../sist.h"
#include "src/sist.h"
#define PARSE_BUF_SIZE 4096
int fs_read(struct vfile *f, void *buf, size_t size);
void fs_close(struct vfile *f);
void fs_reset(struct vfile *f);
void parse(void *arg);
void cleanup_parse();
#endif

161
src/parsing/pdf.c Normal file
View File

@@ -0,0 +1,161 @@
#include <src/ctx.h>
#include "pdf.h"
#include "src/ctx.h"
fz_page *render_cover(fz_context *ctx, document_t *doc, fz_document *fzdoc) {
fz_page *cover = fz_load_page(ctx, fzdoc, 0);
fz_rect bounds = fz_bound_page(ctx, cover);
float scale;
float w = (float) bounds.x1 - bounds.x0;
float h = (float) bounds.y1 - bounds.y0;
if (w > h) {
scale = (float) ScanCtx.tn_size / w;
} else {
scale = (float) ScanCtx.tn_size / h;
}
fz_matrix m = fz_scale(scale, scale);
bounds = fz_transform_rect(bounds, m);
fz_irect bbox = fz_round_rect(bounds);
fz_pixmap *pixmap = fz_new_pixmap_with_bbox(ctx, ctx->colorspace->rgb, bbox, NULL, 0);
fz_clear_pixmap_with_value(ctx, pixmap, 0xFF);
fz_device *dev = fz_new_draw_device(ctx, m, pixmap);
pthread_mutex_lock(&ScanCtx.mupdf_mu);
fz_try(ctx)
fz_run_page(ctx, cover, dev, fz_identity, NULL);
fz_always(ctx)
pthread_mutex_unlock(&ScanCtx.mupdf_mu);
fz_catch(ctx)
fz_rethrow(ctx);
fz_drop_device(ctx, dev);
fz_buffer *fzbuf = fz_new_buffer_from_pixmap_as_png(ctx, pixmap, fz_default_color_params);
unsigned char *tn_buf;
size_t tn_len = fz_buffer_storage(ctx, fzbuf, &tn_buf);
store_write(ScanCtx.index.store, (char *) doc->uuid, sizeof(doc->uuid), (char *) tn_buf, tn_len);
fz_drop_pixmap(ctx, pixmap);
fz_drop_buffer(ctx, fzbuf);
return cover;
}
void fz_noop_callback(__attribute__((unused)) void *user, __attribute__((unused)) const char *message) {}
void parse_pdf(void *buf, size_t buf_len, document_t *doc) {
static int mu_is_initialized = 0;
if (!mu_is_initialized) {
pthread_mutex_init(&ScanCtx.mupdf_mu, NULL);
mu_is_initialized = 1;
}
fz_context *ctx = fz_new_context(NULL, NULL, FZ_STORE_UNLIMITED);
fz_stream *stream = NULL;
fz_document *fzdoc = NULL;
fz_var(stream);
fz_var(fzdoc);
fz_try(ctx)
{
fz_disable_icc(ctx);
fz_register_document_handlers(ctx);
//disable warnings
ctx->warn.print = fz_noop_callback;
ctx->error.print = fz_noop_callback;
stream = fz_open_memory(ctx, buf, buf_len);
fzdoc = fz_open_document_with_stream(ctx, mime_get_mime_text(doc->mime), stream);
char title[4096] = {'\0',};
fz_lookup_metadata(ctx, fzdoc, FZ_META_INFO_TITLE, title, sizeof(title));
printf("Title: %s\n", title); //todo rmv
if (strlen(title) > 0) {
meta_line_t *meta_content = malloc(sizeof(meta_line_t) + strlen(title) + 1);
meta_content->key = MetaTitle;
strcpy(meta_content->strval, title);
APPEND_META(doc, meta_content)
}
int page_count = fz_count_pages(ctx, fzdoc);
fz_page *cover = render_cover(ctx, doc, fzdoc);
fz_stext_options opts;
text_buffer_t text_buf = text_buffer_create(ScanCtx.content_size);
for (int current_page = 0; current_page < page_count; current_page++) {
fz_page *page; if (current_page == 0) {
page = cover;
} else {
page = fz_load_page(ctx, fzdoc, current_page);
}
fz_stext_page *stext = fz_new_stext_page(ctx, fz_bound_page(ctx, page));
fz_device *dev = fz_new_stext_device(ctx, stext, &opts);
pthread_mutex_lock(&ScanCtx.mupdf_mu);
fz_try(ctx)
fz_run_page_contents(ctx, page, dev, fz_identity, NULL);
fz_always(ctx)
pthread_mutex_unlock(&ScanCtx.mupdf_mu);
fz_catch(ctx)
fz_rethrow(ctx);
fz_drop_device(ctx, dev);
fz_stext_block *block = stext->first_block;
while (block != NULL) {
if (block->type != FZ_STEXT_BLOCK_TEXT) {
block = block->next;
continue;
}
fz_stext_line *line = block->u.t.first_line;
while (line != NULL) {
fz_stext_char *c = line->first_char;
while (c != NULL) {
if (text_buffer_append_char(&text_buf, c->c) == TEXT_BUF_FULL) {
fz_drop_page(ctx, page);
fz_drop_stext_page(ctx, stext);
goto write_loop_end;
}
c = c->next;
}
line = line->next;
}
block = block->next;
}
fz_drop_page(ctx, page);
fz_drop_stext_page(ctx, stext);
}
write_loop_end:;
text_buffer_terminate_string(&text_buf);
meta_line_t *meta_content = malloc(sizeof(meta_line_t) + text_buf.dyn_buffer.cur);
meta_content->key = MetaContent;
memcpy(meta_content->strval, text_buf.dyn_buffer.buf, text_buf.dyn_buffer.cur);
text_buffer_destroy(&text_buf);
APPEND_META(doc, meta_content)
}
fz_always(ctx)
{
fz_drop_stream(ctx, stream);
fz_drop_document(ctx, fzdoc);
fz_drop_context(ctx);
} fz_catch(ctx) {
fprintf(stderr, "Error %s %s\n", doc->filepath, ctx->error.message);
}
}

9
src/parsing/pdf.h Normal file
View File

@@ -0,0 +1,9 @@
#ifndef SIST2_PDF_H
#define SIST2_PDF_H
#include "src/sist.h"
void parse_pdf(void *buf, size_t buf_len, document_t *doc);
#endif

43
src/parsing/text.c Normal file
View File

@@ -0,0 +1,43 @@
#include "text.h"
#include "src/ctx.h"
void parse_text(int bytes_read, int *fd, char *buf, document_t *doc) {
char *intermediate_buf;
int intermediate_buf_len;
if (bytes_read == doc->size || bytes_read >= ScanCtx.content_size) {
int to_copy = MIN(bytes_read, ScanCtx.content_size);
intermediate_buf = malloc(to_copy);
intermediate_buf_len = to_copy;
memcpy(intermediate_buf, buf, to_copy);
} else {
if (*fd == -1) {
*fd = open(doc->filepath, O_RDONLY);
}
int to_read = MIN(ScanCtx.content_size, doc->size) - bytes_read;
intermediate_buf = malloc(to_read + bytes_read);
intermediate_buf_len = to_read + bytes_read;
if (bytes_read != 0) {
memcpy(intermediate_buf, buf, bytes_read);
}
read(*fd, intermediate_buf + bytes_read, to_read);
}
text_buffer_t text_buf = text_buffer_create(ScanCtx.content_size);
for (int i = 0; i < intermediate_buf_len; i++) {
text_buffer_append_char(&text_buf, *(intermediate_buf + i));
}
text_buffer_terminate_string(&text_buf);
meta_line_t *meta = malloc(sizeof(meta_line_t) + text_buf.dyn_buffer.cur);
meta->key = MetaContent;
strcpy(meta->strval, text_buf.dyn_buffer.buf);
text_buffer_destroy(&text_buf);
free(intermediate_buf);
APPEND_META(doc, meta)
}

8
src/parsing/text.h Normal file
View File

@@ -0,0 +1,8 @@
#ifndef SIST2_TEXT_H
#define SIST2_TEXT_H
#include "src/sist.h"
void parse_text(int bytes_read, int *fd, char *buf, document_t *doc);
#endif

View File

@@ -1,51 +1,61 @@
#ifndef SIST_H
#define SIST_H
#ifndef FALSE
#define FALSE (0)
#define BOOL int
#endif
#ifndef TRUE
#define TRUE (!FALSE)
#endif
#undef MAX
#define MAX(a, b) (((a) > (b)) ? (a) : (b))
#undef MIN
#define MIN(a, b) (((a) < (b)) ? (a) : (b))
#ifndef PATH_MAX
#define PATH_MAX 4096
#endif
#undef ABS
#define ABS(a) (((a) < 0) ? -(a) : (a))
#define UUID_STR_LEN 37
#define UNUSED(x) __attribute__((__unused__)) x
#include "util.h"
#include "log.h"
#include "types.h"
#include "libscan/scan.h"
#include <cjson/cJSON.h>
#include <string.h>
#include <glib-2.0/glib.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <stdarg.h>
#include <unistd.h>
#include <string.h>
#include <fcntl.h>
#include <dirent.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <errno.h>
#include <ftw.h>
#include <uuid.h>
#include <magic.h>
#include <libavformat/avformat.h>
#include <libswscale/swscale.h>
#include <libswresample/swresample.h>
#include <libavcodec/avcodec.h>
#include <ctype.h>
#include <mupdf/fitz.h>
#include <mupdf/pdf.h>
#include "argparse/argparse.h"
#include <time.h>
#include <limits.h>
#include <pthread.h>
#include <sys/stat.h>
#include <wordexp.h>
#ifndef SIST_SCAN_ONLY
#include <onion/onion.h>
#include <onion/handler.h>
#include <onion/block.h>
#include <onion/shortcuts.h>
#include <curl/curl.h>
#endif
#include "cJSON/cJSON.h"
#include "types.h"
#include "tpool.h"
#include "util.h"
#include "io/store.h"
#include "io/serialize.h"
#include "io/walk.h"
#include "parsing/parse.h"
#include "parsing/mime.h"
#include "parsing/text.h"
#include "parsing/pdf.h"
#include "parsing/media.h"
#include "parsing/font.h"
#include "cli.h"
#ifndef SIST_SCAN_ONLY
#include "src/index/elastic.h"
#include "index/web.h"
#include "web/serve.h"
#endif
;
#endif

View File

@@ -1 +0,0 @@
.bricklayer{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-box-align:start;-webkit-align-items:flex-start;-ms-flex-align:start;align-items:flex-start;-webkit-box-pack:center;-webkit-justify-content:center;-ms-flex-pack:center;justify-content:center;-webkit-flex-wrap:wrap;-ms-flex-wrap:wrap;flex-wrap:wrap}.bricklayer-column-sizer{width:100%;display:none}@media screen and (min-width:640px){.bricklayer-column-sizer{width:50%}}@media screen and (min-width:980px){.bricklayer-column-sizer{width:33.333%}}@media screen and (min-width:1200px){.bricklayer-column-sizer{width:25%}}.bricklayer-column{-webkit-box-flex:1;-webkit-flex:1;-ms-flex:1;flex:1;padding-left:5px;padding-right:5px}

View File

@@ -1,482 +0,0 @@
*:focus {
outline: 0;
}
.info-icon {
width: 1rem;
margin-right: 0.2rem;
cursor: pointer;
line-height: 1rem;
height: 1rem;
background-image: url(data:image/svg+xml;base64,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);
filter: brightness(65%);
}
.info-icon:hover {
color: inherit;
}
.modal-title {
max-width: calc(100% - 2rem);
overflow: hidden;
text-overflow: ellipsis;
}
.path-row {
display: -ms-flexbox;
display: flex;
-ms-flex-align: start;
align-items: flex-start;
}
.tag-container {
margin-left: 0.3rem;
}
.path-line {
color: #BBB;
text-overflow: ellipsis;
overflow: hidden;
white-space: nowrap;
}
a {
color: #00BCD4;
}
body {
overflow-y: scroll;
background: black;
}
.progress {
margin-top: 1em;
}
.card, .modal-content {
margin-top: 1em;
background: #212121;
color: #e0e0e0;
border-radius: 1px;
border: none;
}
.table {
color: #e0e0e0;
}
.table td, .table th {
border: none;
}
.table thead th {
border-bottom: 1px solid #646464;
}
.modal-header .close {
color: #e0e0e0;
text-shadow: none;
}
.modal-header {
border-bottom: 1px solid #646464;
}
.sub-document {
background: #37474F !important;
}
.list-group-item.sub-document {
border-top: 1px solid #646464 !important;
}
.sub-document .text-muted {
color: #8a949c !important;
}
.list-group-item {
background: #212121;
color: #e0e0e0;
border-top: 1px solid #424242;
border-bottom: none;
border-left: none;
border-right: none;
padding: .25rem 0.5rem;
}
.list-group-item:first-child {
border-top: none;
}
.navbar-brand {
font-size: 1.75rem;
padding: 0;
color: #f5f5f5;
}
.navbar {
background: #546b7a;
}
.navbar a:hover {
color: #fff;
}
.navbar span {
color: #eee;
}
.document {
padding: 0.5rem;
}
.document p {
margin-bottom: 0;
}
.document:hover p {
text-decoration: underline;
}
.badge-video {
color: #FFFFFF;
background-color: #F27761;
}
.badge-image {
color: #FFFFFF;
background-color: #AA99C9;
}
.badge-audio {
color: #FFFFFF;
background-color: #00ADEF;
}
.badge-resolution {
color: #212529;
background-color: #B0BEC5;
}
.badge-text {
color: #FFFFFF;
background-color: #FAAB3C;
}
.card-img-overlay {
pointer-events: none;
padding: 0.75rem;
bottom: unset;
top: 0;
left: unset;
right: unset;
}
.file-title {
width: 100%;
line-height: 1rem;
height: 1.1rem;
font-size: 10pt;
white-space: nowrap;
text-overflow: ellipsis;
overflow: hidden;
color: #00BCD4;
}
.badge {
margin-right: 3px;
}
.badge-user {
color: #212529;
background-color: #e0e0e0;
}
.fit {
display: block;
min-width: 64px;
max-width: 100%;
max-height: 175px;
margin: 0 auto 0;
padding: 3px 3px 0;
width: auto;
height: auto;
}
.fit-sm {
display: block;
max-width: 64px;
max-height: 64px;
margin: 0 auto;
width: auto;
height: auto;
}
.audio-fit {
height: 39px;
vertical-align: bottom;
display: inline;
width: 100%;
}
@media screen and (min-width: 1500px) {
.container {
max-width: 1440px;
}
.bricklayer-column-sizer {
width: 20% !important;
}
.bricklayer-column {
max-width: 20%;
}
}
@media screen and (min-width: 1800px) {
.container {
max-width: 1550px;
}
}
mark {
background: rgba(251, 191, 41, 0.25);
border-radius: 0;
padding: 1px 0;
color: inherit;
}
.content-div mark {
background: rgba(251, 191, 41, 0.40);
color: white;
}
.content-div {
font-family: SFMono-Regular, Menlo, Monaco, Consolas, "Liberation Mono", "Courier New", monospace;
font-size: 13px;
padding: 1em;
background-color: #37474F;
border: 1px solid #616161;
border-radius: 4px;
margin: 3px;
white-space: normal;
color: rgb(224, 224, 224);
}
.irs-single, .irs-from, .irs-to {
font-size: 13px;
background-color: #00BCD4;
}
.irs-slider {
cursor: col-resize;
}
.irs {
margin-top: 1em;
margin-bottom: 1em;
}
.custom-select {
overflow: auto;
background-color: #37474F;
border: 1px solid #616161;
color: #bdbdbd;
}
.custom-select:focus {
border-color: #757575;
outline: 0;
box-shadow: 0 0 0 .2rem rgba(0, 123, 255, .25);
}
option {
outline: none;
}
.form-control {
background-color: #37474F;
border: 1px solid #616161;
color: #fff;
}
.form-control:focus {
background-color: #546E7A;
color: #fff;
}
.input-group-text {
background: #263238;
border: 1px solid #616161;
color: #dbdbdb;
}
::placeholder {
color: #BDBDBD !important;
opacity: 1;
}
.inspire-tree .selected > .wholerow, .inspire-tree .selected > .title-wrap:hover + .wholerow {
background: none;
}
.inspire-tree .icon-expand::before, .inspire-tree .icon-collapse::before {
background-color: black;
}
.inspire-tree .title {
color: #eee;
}
.inspire-tree {
font-weight: 400;
font-size: 14px;
font-family: Helvetica, Nueue, Verdana, sans-serif;
max-height: 350px;
overflow: auto;
}
.page-indicator {
line-height: 1rem;
padding: 0.5rem;
background: #212121;
color: #eee;
margin-top: 1em;
}
.btn-xs {
padding: .1rem .3rem;
font-size: .875rem;
border-radius: .2rem;
}
.btn {
color: #eee;
}
.nav-tabs .nav-link {
color: #e0e0e0;
}
.nav-tabs .nav-item.show .nav-link, .nav-tabs .nav-link.active {
background-color: #212121;
border-color: #616161 #616161 #212121;
color: #e0e0e0;
}
.nav-tabs .nav-link:focus, .nav-tabs .nav-link:focus {
border-color: #616161 #616161 #212121;
color: #e0e0e0;
}
.nav-tabs .nav-link:focus, .nav-tabs .nav-link:hover {
border-color: #e0e0e0 #e0e0e0 #212121;
color: #e0e0e0;
}
.nav-tabs {
border-bottom: #616161;
}
.nav {
margin-top: 0.5rem;
}
@media (max-width: 800px) {
#treeTabs {
flex-basis: inherit;
flex-grow: inherit;
}
}
.list-group {
margin-top: 1em;
}
.wrapper-sm {
min-width: 64px;
}
.media-expanded {
display: inherit;
}
.media-expanded .fit {
max-height: 250px;
}
@media (max-width: 650px) {
.media-expanded .fit {
max-height: none;
}
.tagline {
display: none;
}
}
.version {
color: #00BCD4;
margin-left: -18px;
margin-top: -14px;
font-size: 11px;
}
@media (min-width: 800px) {
.small-btn {
display: none;
}
.large-btn {
display: inherit;
}
}
@media (max-width: 801px) {
.small-btn {
display: inherit;
}
.large-btn {
display: none;
}
}
#searchBar {
border-right: none;
}
#pathTree .title {
cursor: pointer;
}
svg {
fill: white;
}
.play {
position: absolute;
width: 50px;
height: 50px;
left: 50%;
top: 50%;
transform: translate(-50%, -50%);
pointer-events: none;
}
.play svg {
fill: rgba(255, 255, 255, 0.7);
}
.img-wrapper:hover svg {
fill: rgba(255, 255, 255, 1);
}
.pointer {
cursor: pointer;
}

View File

@@ -1 +0,0 @@
.jq-toast-wrap,.jq-toast-wrap *{margin:0;padding:0}.jq-toast-wrap{display:block;position:fixed;width:250px;pointer-events:none!important;letter-spacing:normal;z-index:9000!important}.jq-toast-wrap.bottom-left{bottom:20px;left:20px}.jq-toast-wrap.bottom-right{bottom:20px;right:40px}.jq-toast-wrap.top-left{top:20px;left:20px}.jq-toast-wrap.top-right{top:20px;right:40px}.jq-toast-single{display:block;width:100%;padding:10px;margin:0 0 5px;border-radius:4px;font-size:12px;font-family:arial,sans-serif;line-height:17px;position:relative;pointer-events:all!important;background-color:#444;color:#fff}.jq-toast-single h2{font-family:arial,sans-serif;font-size:14px;margin:0 0 7px;background:0 0;color:inherit;line-height:inherit;letter-spacing:normal}.jq-toast-single a{color:#eee;text-decoration:none;font-weight:700;border-bottom:1px solid #fff;padding-bottom:3px;font-size:12px}.jq-toast-single ul{margin:0 0 0 15px;background:0 0;padding:0}.jq-toast-single ul li{list-style-type:disc!important;line-height:17px;background:0 0;margin:0;padding:0;letter-spacing:normal}.close-jq-toast-single{position:absolute;top:3px;right:7px;font-size:14px;cursor:pointer}.jq-toast-loader{display:block;position:absolute;top:-2px;height:5px;width:0;left:0;border-radius:5px;background:red}.jq-toast-loaded{width:100%}.jq-has-icon{padding:10px 10px 10px 50px;background-repeat:no-repeat;background-position:10px}.jq-icon-info{background-image:url(data:image/png;base64,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);background-color:#31708f;color:#d9edf7;border-color:#bce8f1}.jq-icon-warning{background-image:url(data:image/png;base64,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);background-color:#8a6d3b;color:#fcf8e3;border-color:#faebcc}.jq-icon-error{background-image:url(data:image/png;base64,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);background-color:#a94442;color:#f2dede;border-color:#ebccd1}.jq-icon-success{background-image:url(data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABgAAAAYCAYAAADgdz34AAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsMAAA7DAcdvqGQAAADsSURBVEhLY2AYBfQMgf///3P8+/evAIgvA/FsIF+BavYDDWMBGroaSMMBiE8VC7AZDrIFaMFnii3AZTjUgsUUWUDA8OdAH6iQbQEhw4HyGsPEcKBXBIC4ARhex4G4BsjmweU1soIFaGg/WtoFZRIZdEvIMhxkCCjXIVsATV6gFGACs4Rsw0EGgIIH3QJYJgHSARQZDrWAB+jawzgs+Q2UO49D7jnRSRGoEFRILcdmEMWGI0cm0JJ2QpYA1RDvcmzJEWhABhD/pqrL0S0CWuABKgnRki9lLseS7g2AlqwHWQSKH4oKLrILpRGhEQCw2LiRUIa4lwAAAABJRU5ErkJggg==);color:#dff0d8;background-color:#3c763d;border-color:#d6e9c6}

View File

@@ -1,349 +0,0 @@
*:focus {
outline: 0;
}
.info-icon {
width: 1rem;
margin-right: 0.2rem;
cursor: pointer;
line-height: 1rem;
height: 1rem;
background-image: url(data:image/svg+xml;base64,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);
filter: brightness(45%);
}
.info-icon:hover {
color: inherit;
}
.modal-title {
max-width: calc(100% - 2rem);
overflow: hidden;
text-overflow: ellipsis;
}
.path-row {
display: -ms-flexbox;
display: flex;
-ms-flex-align: start;
align-items: flex-start;
}
.tag-container {
margin-left: 0.3rem;
}
.path-line {
color: #444;
text-overflow: ellipsis;
overflow: hidden;
white-space: nowrap;
}
body {
overflow-y: scroll;
}
.progress {
margin-top: 1em;
}
.card {
margin-top: 1em;
box-shadow: 0 .125rem .25rem rgba(0, 0, 0, .08) !important;
border-radius: 0;
border: none;
}
.sub-document {
background: #AB47BC1F !important;
}
.navbar-brand {
font-size: 1.75rem;
padding: 0;
}
.navbar {
background: #F7F7F7;
border-bottom: solid 1px #dfdfdf;
}
.document {
padding: 0.5rem;
}
.document p {
margin-bottom: 0;
}
.document:hover p {
text-decoration: underline;
}
.badge-video {
color: #FFFFFF;
background-color: #F27761;
}
.badge-image {
color: #FFFFFF;
background-color: #AA99C9;
}
.badge-audio {
color: #FFFFFF;
background-color: #00ADEF;
}
.badge-resolution {
color: #212529;
background-color: #FFC107;
}
.badge-user {
color: #212529;
background-color: #e0e0e0;
}
.badge-text {
color: #FFFFFF;
background-color: #FAAB3C;
}
.card-img-overlay {
pointer-events: none;
padding: 0.75rem;
bottom: unset;
top: 0;
left: unset;
right: unset;
}
.file-title {
width: 100%;
line-height: 1rem;
height: 1.1rem;
font-size: 10pt;
white-space: nowrap;
text-overflow: ellipsis;
overflow: hidden;
}
.badge {
margin-right: 3px;
}
.fit {
display: block;
min-width: 64px;
max-width: 100%;
max-height: 175px;
margin: 0 auto 0;
padding: 3px 3px 0 3px;
width: auto;
height: auto;
}
.fit-sm {
display: block;
max-width: 64px;
max-height: 64px;
margin: 0 auto 0;
width: auto;
height: auto;
}
.audio-fit {
height: 39px;
vertical-align: bottom;
display: inline;
width: 100%;
}
@media screen and (max-width: 1200px) {
.bricklayer-column {
max-width: 100%;
}
}
@media screen and (min-width: 1500px) {
.container {
max-width: 1440px;
}
.bricklayer-column-sizer {
width: 20% !important;
}
.bricklayer-column {
max-width: 20%;
}
}
@media screen and (min-width: 1800px) {
.container {
max-width: 1550px;
}
}
mark {
background: #fff217;
border-radius: 0;
padding: 1px 0;
color: inherit;
}
.content-div {
font-family: SFMono-Regular, Menlo, Monaco, Consolas, "Liberation Mono", "Courier New", monospace;
font-size: 13px;
padding: 1em;
background-color: #f5f5f5;
border: 1px solid #ccc;
border-radius: 4px;
margin: 3px;
white-space: normal;
color: #000;
}
.irs-single, .irs-from, .irs-to {
font-size: 13px;
}
.irs-slider {
cursor: col-resize;
}
.custom-select {
overflow: auto;
}
.irs {
margin-top: 1em;
margin-bottom: 1em;
}
.inspire-tree .selected > .wholerow, .inspire-tree .selected > .title-wrap:hover + .wholerow {
background: none;
}
.inspire-tree {
font-weight: 400;
font-size: 14px;
font-family: Helvetica, Nueue, Verdana, sans-serif;
max-height: 350px;
overflow: auto;
}
.page-indicator {
line-height: 1rem;
padding: 0.5rem;
background: #f8f9fa;
margin-top: 1em;
}
.btn-xs {
padding: .1rem .3rem;
font-size: .875rem;
border-radius: .2rem;
}
.nav {
margin-top: 0.5rem;
}
@media (max-width: 800px) {
#treeTabs {
flex-basis: inherit;
flex-grow: inherit;
}
}
.list-group {
margin-top: 1em;
}
.list-group-item {
padding: .25rem 0.5rem;
}
.wrapper-sm {
min-width: 64px;
}
.media-expanded {
display: inherit;
}
.media-expanded .fit {
max-height: 250px;
}
@media (max-width: 650px) {
.media-expanded .fit {
max-height: none;
}
.tagline {
display: none;
}
}
.version {
color: #007bff;
margin-left: -18px;
margin-top: -14px;
font-size: 11px;
}
@media (min-width: 800px) {
.small-btn {
display: none;
}
.large-btn {
display: inherit;
}
}
@media (max-width: 801px) {
.small-btn {
display: inherit;
}
.large-btn {
display: none;
}
}
#searchBar {
border-right: none;
}
#pathTree .title {
cursor: pointer;
}
.play {
position: absolute;
width: 50px;
height: 50px;
left: 50%;
top: 50%;
transform: translate(-50%, -50%);
pointer-events: none;
}
.play svg {
fill: rgba(0, 0, 0, 0.7);
}
.img-wrapper:hover svg {
fill: rgba(0, 0, 0, 1);
}
.pointer {
cursor: pointer;
}

View File

@@ -1,3 +0,0 @@
/*! Lity - v2.4.0 - 2019-08-10
* http://sorgalla.com/lity/
* Copyright (c) 2015-2019 Jan Sorgalla; Licensed MIT */.lity{z-index:9990;position:fixed;top:0;right:0;bottom:0;left:0;white-space:nowrap;background:#0b0b0b;background:rgba(0,0,0,0.9);outline:none !important;opacity:0;-webkit-transition:opacity .3s ease;-o-transition:opacity .3s ease;transition:opacity .3s ease}.lity.lity-opened{opacity:1}.lity.lity-closed{opacity:0}.lity *{-webkit-box-sizing:border-box;-moz-box-sizing:border-box;box-sizing:border-box}.lity-wrap{z-index:9990;position:fixed;top:0;right:0;bottom:0;left:0;text-align:center;outline:none !important}.lity-wrap:before{content:'';display:inline-block;height:100%;vertical-align:middle;margin-right:-0.25em}.lity-loader{z-index:9991;color:#fff;position:absolute;top:50%;margin-top:-0.8em;width:100%;text-align:center;font-size:14px;font-family:Arial,Helvetica,sans-serif;opacity:0;-webkit-transition:opacity .3s ease;-o-transition:opacity .3s ease;transition:opacity .3s ease}.lity-loading .lity-loader{opacity:1}.lity-container{z-index:9992;position:relative;text-align:left;vertical-align:middle;display:inline-block;white-space:normal;max-width:100%;max-height:100%;outline:none !important}.lity-content{z-index:9993;width:100%;-webkit-transform:scale(1);-ms-transform:scale(1);-o-transform:scale(1);transform:scale(1);-webkit-transition:-webkit-transform .3s ease;transition:-webkit-transform .3s ease;-o-transition:-o-transform .3s ease;transition:transform .3s ease;transition:transform .3s ease, -webkit-transform .3s ease, -o-transform .3s ease}.lity-loading .lity-content,.lity-closed .lity-content{-webkit-transform:scale(.8);-ms-transform:scale(.8);-o-transform:scale(.8);transform:scale(.8)}.lity-content:after{content:'';position:absolute;left:0;top:0;bottom:0;display:block;right:0;width:auto;height:auto;z-index:-1;-webkit-box-shadow:0 0 8px rgba(0,0,0,0.6);box-shadow:0 0 8px rgba(0,0,0,0.6)}.lity-close{z-index:9994;width:35px;height:35px;position:fixed;right:0;top:0;-webkit-appearance:none;cursor:pointer;text-decoration:none;text-align:center;padding:0;color:#fff;font-style:normal;font-size:35px;font-family:Arial,Baskerville,monospace;line-height:35px;text-shadow:0 1px 2px rgba(0,0,0,0.6);border:0;background:none;outline:none;-webkit-box-shadow:none;box-shadow:none}.lity-close::-moz-focus-inner{border:0;padding:0}.lity-close:hover,.lity-close:focus,.lity-close:active,.lity-close:visited{text-decoration:none;text-align:center;padding:0;color:#fff;font-style:normal;font-size:35px;font-family:Arial,Baskerville,monospace;line-height:35px;text-shadow:0 1px 2px rgba(0,0,0,0.6);border:0;background:none;outline:none;-webkit-box-shadow:none;box-shadow:none}.lity-close:active{top:1px}.lity-image img{max-width:100%;display:block;line-height:0;border:0}.lity-iframe .lity-container,.lity-youtube .lity-container,.lity-vimeo .lity-container,.lity-facebookvideo .lity-container,.lity-googlemaps .lity-container{width:100%;max-width:964px}.lity-iframe-container{width:100%;height:0;padding-top:56.25%;overflow:hidden;pointer-events:all;-webkit-transform:translateZ(0);transform:translateZ(0);-webkit-overflow-scrolling:touch}.lity-iframe-container iframe{position:absolute;display:block;top:0;left:0;width:100%;height:100%;-webkit-box-shadow:0 0 8px rgba(0,0,0,0.6);box-shadow:0 0 8px rgba(0,0,0,0.6);background:#000}.lity-hide{display:none}

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

View File

@@ -1 +0,0 @@
!function t(e,n,r){function o(s,u){if(!n[s]){if(!e[s]){var l="function"==typeof require&&require;if(!u&&l)return l(s,!0);if(i)return i(s,!0);var a=new Error("Cannot find module '"+s+"'");throw a.code="MODULE_NOT_FOUND",a}var p=n[s]={exports:{}};e[s][0].call(p.exports,function(t){var n=e[s][1][t];return o(n?n:t)},p,p.exports,t,e,n,r)}return n[s].exports}for(var i="function"==typeof require&&require,s=0;s<r.length;s++)o(r[s]);return o}({1:[function(t,e,n){var r,o=this&&this.__extends||function(t,e){function n(){this.constructor=t}for(var r in e)e.hasOwnProperty(r)&&(t[r]=e[r]);t.prototype=null===e?Object.create(e):(n.prototype=e.prototype,new n)};!function(t){function e(t){return[].slice.call(t)}function n(t,e,n){if(window.CustomEvent)var r=new CustomEvent(e,{detail:n});else{var r=document.createEvent("CustomEvent");r.initCustomEvent(e,!0,!0,n)}return t.dispatchEvent(r)}var r={rulerClassName:"bricklayer-column-sizer",columnClassName:"bricklayer-column"},i=function(){function t(t){this.element=document.createElement("div"),this.element.className=t}return t.prototype.destroy=function(){this.element.parentNode.removeChild(this.element)},t}(),s=function(t){function e(){t.apply(this,arguments)}return o(e,t),e.prototype.getWidth=function(){this.element.setAttribute("style","\n display: block;\n visibility: hidden !important;\n top: -1000px !important;\n ");var t=this.element.offsetWidth;return this.element.removeAttribute("style"),t},e}(i),u=function(t){function e(){t.apply(this,arguments)}return o(e,t),e}(i),l=function(){function t(t,e){void 0===e&&(e=r),this.element=t,this.options=e,this.build(),this.buildResponsive()}return t.prototype.append=function(t){var n=this;if(Array.isArray(t))return void t.forEach(function(t){return n.append(t)});var r=this.findMinHeightColumn();this.elements=e(this.elements).concat([t]),this.applyPosition("append",r,t)},t.prototype.prepend=function(t){var n=this;if(Array.isArray(t))return void t.forEach(function(t){return n.prepend(t)});var r=this.findMinHeightColumn();this.elements=[t].concat(e(this.elements)),this.applyPosition("prepend",r,t)},t.prototype.on=function(t,e){return this.element.addEventListener("bricklayer."+t,e),this},t.prototype.redraw=function(){var t=this.columnCount;this.checkColumnCount(!1),this.reorderElements(t),n(this.element,"bricklayer.redraw",{columnCount:t})},t.prototype.destroy=function(){var t=this;this.ruler.destroy(),e(this.elements).forEach(function(e){return t.element.appendChild(e)}),e(this.getColumns()).forEach(function(t){return t.parentNode.removeChild(t)}),n(this.element,"bricklayer.destroy",{})},t.prototype.build=function(){this.ruler=new s(this.options.rulerClassName),this.elements=this.getElementsInOrder(),this.element.insertBefore(this.ruler.element,this.element.firstChild)},t.prototype.buildResponsive=function(){var t=this;window.addEventListener("resize",function(e){return t.checkColumnCount()}),this.checkColumnCount(),this.on("breakpoint",function(e){return t.reorderElements(e.detail.columnCount)}),this.columnCount>=1&&this.reorderElements(this.columnCount)},t.prototype.getColumns=function(){return this.element.querySelectorAll(":scope > ."+this.options.columnClassName)},t.prototype.findMinHeightColumn=function(){var t=e(this.getColumns()),n=t.map(function(t){return t.offsetHeight}),r=Math.min.apply(null,n);return t[n.indexOf(r)]},t.prototype.getElementsInOrder=function(){return this.element.querySelectorAll(":scope > *:not(."+this.options.columnClassName+"):not(."+this.options.rulerClassName+")")},t.prototype.checkColumnCount=function(t){void 0===t&&(t=!0);var e=this.getColumnCount();this.columnCount!==e&&(t&&n(this.element,"bricklayer.breakpoint",{columnCount:e}),this.columnCount=e)},t.prototype.reorderElements=function(t){var n=this;void 0===t&&(t=1),(t==1/0||1>t)&&(t=1);for(var r=e(this.elements).map(function(t){var e=t.parentNode?t.parentNode.removeChild(t):t;return e}),o=this.getColumns(),i=0;i<o.length;i++)o[i].parentNode.removeChild(o[i]);for(var i=0;t>i;i++){var s=new u(this.options.columnClassName).element;this.element.appendChild(s)}r.forEach(function(t){var e=n.findMinHeightColumn();e.appendChild(t)})},t.prototype.getColumnCount=function(){var t=this.element.offsetWidth,e=this.ruler.getWidth();return Math.round(t/e)},t.prototype.applyPosition=function(t,e,r){var o=this,i=function(i){var s=i+t.charAt(0).toUpperCase()+t.substr(1);n(o.element,"bricklayer."+s,{item:r,column:e})};switch(i("before"),t){case"append":e.appendChild(r);break;case"prepend":e.insertBefore(r,e.firstChild)}i("after")},t}();t.Container=l}(r||(r={})),function(t,n){"function"==typeof define&&define.amd?define(function(){return n()}):"undefined"!=typeof window&&t===window?t.Bricklayer=n():"object"==typeof e&&e.exports&&(e.exports=n())}("undefined"!=typeof window?window:this,function(){return r.Container})},{}]},{},[1]);

View File

@@ -1,626 +0,0 @@
/**
* Enable gif loading on hover
*/
function gifOver(thumbnail, hit) {
let callee = arguments.callee;
thumbnail.addEventListener("mouseover", function () {
thumbnail.mouseStayedOver = true;
window.setTimeout(function () {
if (thumbnail.mouseStayedOver) {
thumbnail.removeEventListener('mouseover', callee, false);
//Load gif
thumbnail.setAttribute("src", "f/" + hit["_id"]);
}
}, 600);
});
thumbnail.addEventListener("mouseout", function () {
//Reset timer
thumbnail.mouseStayedOver = false;
thumbnail.setAttribute("src", `t/${hit["_source"]["index"]}/${hit["_id"]}`);
})
}
function getContentHighlight(hit) {
const re = RegExp(/<mark>/g);
const sortByMathCount = (a, b) => {
return b.match(re).length - a.match(re).length;
};
if (hit.hasOwnProperty("highlight")) {
if (hit["highlight"].hasOwnProperty("content")) {
return hit["highlight"]["content"].sort(sortByMathCount)[0];
} else if (hit["highlight"].hasOwnProperty("content.nGram")) {
return hit["highlight"]["content.nGram"].sort(sortByMathCount)[0];
}
}
return undefined;
}
function getPathHighlight(hit) {
if (hit.hasOwnProperty("highlight")) {
if (hit["highlight"].hasOwnProperty("path.text")) {
return hit["highlight"]["path.text"][0];
} else if (hit["highlight"].hasOwnProperty("path.nGram")) {
return hit["highlight"]["path.nGram"][0];
}
}
return undefined;
}
function applyNameToTitle(hit, title, extension) {
if (hit.hasOwnProperty("highlight")) {
if (hit["highlight"].hasOwnProperty("name")) {
title.insertAdjacentHTML('afterbegin', hit["highlight"]["name"] + extension);
return;
} else if (hit["highlight"].hasOwnProperty("name.nGram")) {
title.insertAdjacentHTML('afterbegin', hit["highlight"]["name.nGram"] + extension);
return;
}
}
title.appendChild(document.createTextNode(hit["_source"]["name"] + extension));
}
function shouldPlayVideo(hit) {
const videoc = hit["_source"]["videoc"];
const mime = hit["_source"]["mime"];
return mime &&
mime.startsWith("video/") &&
hit["_source"]["extension"] !== "mkv" &&
hit["_source"]["extension"] !== "avi" &&
videoc !== "hevc" &&
videoc !== "mpeg2video" &&
videoc !== "wmv3";
}
function shouldDisplayRawImage(hit) {
const mime = hit["_source"]["mime"];
return mime &&
mime.startsWith("image/") &&
hit["_source"]["mime"] &&
!hit["_source"]["parent"] &&
hit["_source"]["videoc"] !== "tiff" &&
hit["_source"]["videoc"] !== "ppm";
}
function makePlaceholder(w, h, small) {
let calc;
if (small) {
calc = w > h
? (64 / w / h) >= 100
? (64 * w / h)
: 64
: 64;
} else {
calc = w > h
? (175 / w / h) >= 272
? (175 * w / h)
: 175
: 175;
}
const el = document.createElement("div");
el.setAttribute("style", `height: ${calc}px`);
return el;
}
function ext(hit) {
return hit["_source"].hasOwnProperty("extension") && hit["_source"]["extension"] !== "" ? "." + hit["_source"]["extension"] : "";
}
function makeTitle(hit) {
let title = document.createElement("div");
title.setAttribute("class", "file-title");
let extension = ext(hit);
applyNameToTitle(hit, title, extension);
title.setAttribute("title", hit["_source"]["path"] + "/" + hit["_source"]["name"] + extension);
return title;
}
function getTags(hit, mimeCategory) {
let tags = [];
switch (mimeCategory) {
case "video":
case "image":
if (hit["_source"].hasOwnProperty("videoc") && hit["_source"]["videoc"]) {
const formatTag = document.createElement("span");
formatTag.setAttribute("class", "badge badge-pill badge-video");
formatTag.appendChild(document.createTextNode(hit["_source"]["videoc"].replace(" ", "")));
tags.push(formatTag);
}
break;
case "audio": {
if (hit["_source"].hasOwnProperty("audioc") && hit["_source"]["audioc"]) {
let formatTag = document.createElement("span");
formatTag.setAttribute("class", "badge badge-pill badge-audio");
formatTag.appendChild(document.createTextNode(hit["_source"]["audioc"]));
tags.push(formatTag);
}
}
break;
}
// User tags
if (hit["_source"].hasOwnProperty("tag")) {
hit["_source"]["tag"].forEach(tag => {
const userTag = document.createElement("span");
userTag.setAttribute("class", "badge badge-pill badge-user");
const tokens = tag.split("#");
if (tokens.length > 1) {
const bg = "#" + tokens[1];
const fg = lum(tokens[1]) > 40 ? "#000" : "#fff";
userTag.setAttribute("style", `background-color: ${bg}; color: ${fg}`);
}
const name = tokens[0].split(".")[tokens[0].split(".").length - 1];
userTag.appendChild(document.createTextNode(name));
tags.push(userTag);
})
}
return tags
}
function infoButtonCb(hit) {
return () => {
getDocumentInfo(hit["_id"]).then(doc => {
$("#modal-title").text(doc["name"] + ext(hit));
const tbody = $("<tbody>");
$("#modal-body").empty()
.append($("<table class='table table-sm'>")
.append($("<thead>")
.append($("<tr>")
.append($("<th>").text("Field"))
.append($("<th>").text("Value"))
)
)
.append(tbody)
);
const displayFields = new Set([
"mime", "size", "mtime", "path", "title", "width", "height", "duration", "audioc", "videoc",
"bitrate", "artist", "album", "album_artist", "genre", "title", "font_name", "tag"
]);
Object.keys(doc)
.filter(key => key.startsWith("_keyword.") || key.startsWith("_text.") || displayFields.has(key) || key.startsWith("exif_"))
.forEach(key => {
tbody.append($("<tr>")
.append($("<td>").text(key))
.append($("<td>").text(doc[key]))
);
});
if (doc.hasOwnProperty("content") && doc["content"]) {
$("#modal-body").append($("<div class='content-div'>").text(doc["content"]))
}
$("#modal").modal();
});
}
}
function createDocCard(hit) {
let docCard = document.createElement("div");
docCard.setAttribute("class", "card");
let docCardBody = document.createElement("div");
docCardBody.setAttribute("class", "card-body document");
//Title
let title = makeTitle(hit);
let isSubDocument = false;
let link = document.createElement("a");
link.setAttribute("href", "f/" + hit["_id"]);
link.setAttribute("target", "_blank");
link.style.maxWidth = "calc(100% - 1.2rem)";
link.appendChild(title);
if (hit["_source"].hasOwnProperty("parent")) {
docCard.classList.add("sub-document");
isSubDocument = true;
}
let tagContainer = document.createElement("div");
tagContainer.setAttribute("class", "card-text");
if (hit["_source"].hasOwnProperty("mime") && hit["_source"]["mime"] !== null) {
let thumbnailOverlay = null;
let imgWrapper = document.createElement("div");
imgWrapper.setAttribute("style", "position: relative");
imgWrapper.setAttribute("class", "img-wrapper");
let mimeCategory = hit["_source"]["mime"].split("/")[0];
//Thumbnail
let thumbnail = makeThumbnail(mimeCategory, hit, imgWrapper, false);
//Thumbnail overlay
switch (mimeCategory) {
case "image":
thumbnailOverlay = document.createElement("div");
thumbnailOverlay.setAttribute("class", "card-img-overlay");
//Resolution
if (hit["_source"].hasOwnProperty("width") && hit["_source"]["width"] > 32 && hit["_source"]["height"] > 32) {
let resolutionBadge = document.createElement("span");
resolutionBadge.setAttribute("class", "badge badge-resolution");
if (hit["_source"].hasOwnProperty("width")) {
resolutionBadge.appendChild(document.createTextNode(hit["_source"]["width"] + "x" + hit["_source"]["height"]));
}
thumbnailOverlay.appendChild(resolutionBadge);
}
// Hover
if (thumbnail && hit["_source"]["videoc"] === "gif" && !isSubDocument) {
gifOver(thumbnail, hit);
}
break;
case "video":
//Duration
if (hit["_source"].hasOwnProperty("duration")) {
thumbnailOverlay = document.createElement("div");
thumbnailOverlay.setAttribute("class", "card-img-overlay");
const durationBadge = document.createElement("span");
durationBadge.setAttribute("class", "badge badge-resolution");
durationBadge.appendChild(document.createTextNode(humanTime(hit["_source"]["duration"])));
thumbnailOverlay.appendChild(durationBadge);
}
}
// Tags
let tags = getTags(hit, mimeCategory);
for (let i = 0; i < tags.length; i++) {
tagContainer.appendChild(tags[i]);
}
//Content
let contentHl = getContentHighlight(hit);
if (contentHl !== undefined) {
const contentDiv = document.createElement("div");
contentDiv.setAttribute("class", "content-div");
contentDiv.insertAdjacentHTML('afterbegin', contentHl);
docCard.appendChild(contentDiv);
}
if (thumbnail !== null) {
docCard.appendChild(imgWrapper);
}
//Audio
if (mimeCategory === "audio" && hit["_source"].hasOwnProperty("audioc") && !isSubDocument) {
let audio = document.createElement("audio");
audio.setAttribute("preload", "none");
audio.setAttribute("class", "audio-fit fit");
audio.setAttribute("controls", "");
audio.setAttribute("type", hit["_source"]["mime"]);
audio.setAttribute("src", "f/" + hit["_id"]);
docCard.appendChild(audio)
}
if (thumbnailOverlay !== null) {
imgWrapper.appendChild(thumbnailOverlay);
}
}
//Size tag
let sizeTag = document.createElement("small");
sizeTag.appendChild(document.createTextNode(humanFileSize(hit["_source"]["size"])));
sizeTag.setAttribute("class", "text-muted");
tagContainer.appendChild(sizeTag);
const titleWrapper = document.createElement("div");
titleWrapper.style.display = "flex";
const infoButton = makeInfoButton(hit);
titleWrapper.appendChild(infoButton);
titleWrapper.appendChild(link);
docCardBody.appendChild(titleWrapper);
docCard.appendChild(docCardBody);
docCardBody.appendChild(tagContainer);
return docCard;
}
function makeThumbnail(mimeCategory, hit, imgWrapper, small) {
if (!hit["_source"].hasOwnProperty("thumbnail")) {
return null;
}
let thumbnail = document.createElement("img");
if (small) {
thumbnail.setAttribute("class", "fit-sm");
} else {
thumbnail.setAttribute("class", "card-img-top fit");
}
thumbnail.setAttribute("src", `t/${hit["_source"]["index"]}/${hit["_id"]}`);
if (shouldDisplayRawImage(hit)) {
thumbnail.addEventListener("click", () => {
const l = lity(`f/${hit["_id"]}#.jpg`);
window.addEventListener("scroll", () => l.close());
});
thumbnail.classList.add("pointer");
} else if (shouldPlayVideo(hit)) {
thumbnail.addEventListener("click", () => lity(`f/${hit["_id"]}#.mp4`));
thumbnail.classList.add("pointer");
if (!small) {
const playOverlay = document.createElement("div");
playOverlay.innerHTML = '<svg viewBox="0 0 494.942 494.942" xmlns="http://www.w3.org/2000/svg"><path d="m35.353 0 424.236 247.471-424.236 247.471z"/></svg>';
playOverlay.classList.add("play");
imgWrapper.prepend(playOverlay);
}
}
const placeholder = makePlaceholder(hit["_source"]["width"], hit["_source"]["height"], small);
imgWrapper.appendChild(placeholder);
thumbnail.addEventListener("error", () => {
imgWrapper.remove();
});
thumbnail.addEventListener("load", () => {
placeholder.remove();
imgWrapper.appendChild(thumbnail);
});
return thumbnail;
}
function makeInfoButton(hit) {
const infoButton = document.createElement("span");
infoButton.setAttribute("class", "info-icon");
infoButton.addEventListener("click", infoButtonCb(hit));
return infoButton;
}
function createDocLine(hit) {
const mime = hit["_source"]["mime"];
let mimeCategory = mime ? mime.split("/")[0] : null;
let tags = getTags(hit, mimeCategory);
let imgWrapper = document.createElement("div");
imgWrapper.setAttribute("class", "align-self-start mr-1 wrapper-sm");
let media = document.createElement("div");
media.setAttribute("class", "media");
const line = document.createElement("div");
line.setAttribute("class", "list-group-item flex-column align-items-start");
if (hit["_source"].hasOwnProperty("parent")) {
line.classList.add("sub-document");
isSubDocument = true;
}
const infoButton = makeInfoButton(hit);
const title = makeTitle(hit);
let link = document.createElement("a");
link.setAttribute("href", "f/" + hit["_id"]);
link.setAttribute("target", "_blank");
link.style.maxWidth = "calc(100% - 1.2rem)";
link.appendChild(title);
const titleDiv = document.createElement("div");
const titleWrapper = document.createElement("div");
titleWrapper.style.display = "flex";
titleWrapper.appendChild(infoButton);
titleWrapper.appendChild(link);
titleDiv.appendChild(titleWrapper);
line.appendChild(media);
let thumbnail = makeThumbnail(mimeCategory, hit, imgWrapper, true);
if (thumbnail) {
media.appendChild(imgWrapper);
titleDiv.style.maxWidth = "calc(100% - 64px)";
} else {
titleDiv.style.maxWidth = "100%";
}
media.appendChild(titleDiv);
// Content
let contentHl = getContentHighlight(hit);
if (contentHl !== undefined) {
const contentDiv = document.createElement("div");
contentDiv.setAttribute("class", "content-div");
contentDiv.insertAdjacentHTML("afterbegin", contentHl);
titleDiv.appendChild(contentDiv);
}
let pathLine = document.createElement("div");
pathLine.setAttribute("class", "path-row");
let path = document.createElement("div");
path.setAttribute("class", "path-line");
path.setAttribute("title", hit["_source"]["path"] + "/");
const pathHighlight = getPathHighlight(hit);
if (pathHighlight) {
path.insertAdjacentHTML("afterbegin", pathHighlight + "/");
} else {
path.appendChild(document.createTextNode(hit["_source"]["path"] + "/"));
}
let tagContainer = document.createElement("div");
tagContainer.setAttribute("class", "tag-container");
for (let i = 0; i < tags.length; i++) {
tagContainer.appendChild(tags[i]);
}
//Size tag
let sizeTag = document.createElement("small");
sizeTag.appendChild(document.createTextNode(humanFileSize(hit["_source"]["size"])));
sizeTag.setAttribute("class", "text-muted");
tagContainer.appendChild(sizeTag);
titleDiv.appendChild(pathLine);
pathLine.appendChild(path);
pathLine.appendChild(tagContainer);
return line;
}
function makePreloader() {
const elem = document.createElement("div");
elem.setAttribute("class", "progress");
const bar = document.createElement("div");
bar.setAttribute("class", "progress-bar progress-bar-striped progress-bar-animated");
bar.setAttribute("style", "width: 100%");
elem.appendChild(bar);
return elem;
}
function makePageIndicator(searchResult) {
let pageIndicator = document.createElement("div");
pageIndicator.setAttribute("class", "page-indicator font-weight-light");
const totalHits = searchResult["aggregations"]["total_count"]["value"];
pageIndicator.appendChild(document.createTextNode(docCount + " / " + totalHits));
return pageIndicator;
}
function makeStatsCard(searchResult) {
let statsCard = document.createElement("div");
statsCard.setAttribute("class", "card stat");
let statsCardBody = document.createElement("div");
statsCardBody.setAttribute("class", "card-body");
// Stats
let stat = document.createElement("span");
const totalHits = searchResult["aggregations"]["total_count"]["value"];
stat.appendChild(document.createTextNode(totalHits + " results in " + searchResult["took"] + "ms"));
statsCardBody.appendChild(stat);
// Display mode
const resultMode = document.createElement("div");
resultMode.setAttribute("class", "btn-group btn-group-toggle");
resultMode.setAttribute("data-toggle", "buttons");
resultMode.style.cssFloat = "right";
const listMode = document.createElement("label");
listMode.setAttribute("class", "btn btn-primary");
listMode.setAttribute("title", "List mode");
listMode.innerHTML = '<svg width="20px" height="20px" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512"><path fill="currentColor" d="M80 368H16a16 16 0 0 0-16 16v64a16 16 0 0 0 16 16h64a16 16 0 0 0 16-16v-64a16 16 0 0 0-16-16zm0-320H16A16 16 0 0 0 0 64v64a16 16 0 0 0 16 16h64a16 16 0 0 0 16-16V64a16 16 0 0 0-16-16zm0 160H16a16 16 0 0 0-16 16v64a16 16 0 0 0 16 16h64a16 16 0 0 0 16-16v-64a16 16 0 0 0-16-16zm416 176H176a16 16 0 0 0-16 16v32a16 16 0 0 0 16 16h320a16 16 0 0 0 16-16v-32a16 16 0 0 0-16-16zm0-320H176a16 16 0 0 0-16 16v32a16 16 0 0 0 16 16h320a16 16 0 0 0 16-16V80a16 16 0 0 0-16-16zm0 160H176a16 16 0 0 0-16 16v32a16 16 0 0 0 16 16h320a16 16 0 0 0 16-16v-32a16 16 0 0 0-16-16z"></path></svg>';
const gridMode = document.createElement("label");
gridMode.setAttribute("class", "btn btn-primary");
gridMode.setAttribute("title", "Grid mode");
gridMode.innerHTML = '<svg width="20px" height="20px" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512"><path fill="currentColor" d="M149.333 56v80c0 13.255-10.745 24-24 24H24c-13.255 0-24-10.745-24-24V56c0-13.255 10.745-24 24-24h101.333c13.255 0 24 10.745 24 24zm181.334 240v-80c0-13.255-10.745-24-24-24H205.333c-13.255 0-24 10.745-24 24v80c0 13.255 10.745 24 24 24h101.333c13.256 0 24.001-10.745 24.001-24zm32-240v80c0 13.255 10.745 24 24 24H488c13.255 0 24-10.745 24-24V56c0-13.255-10.745-24-24-24H386.667c-13.255 0-24 10.745-24 24zm-32 80V56c0-13.255-10.745-24-24-24H205.333c-13.255 0-24 10.745-24 24v80c0 13.255 10.745 24 24 24h101.333c13.256 0 24.001-10.745 24.001-24zm-205.334 56H24c-13.255 0-24 10.745-24 24v80c0 13.255 10.745 24 24 24h101.333c13.255 0 24-10.745 24-24v-80c0-13.255-10.745-24-24-24zM0 376v80c0 13.255 10.745 24 24 24h101.333c13.255 0 24-10.745 24-24v-80c0-13.255-10.745-24-24-24H24c-13.255 0-24 10.745-24 24zm386.667-56H488c13.255 0 24-10.745 24-24v-80c0-13.255-10.745-24-24-24H386.667c-13.255 0-24 10.745-24 24v80c0 13.255 10.745 24 24 24zm0 160H488c13.255 0 24-10.745 24-24v-80c0-13.255-10.745-24-24-24H386.667c-13.255 0-24 10.745-24 24v80c0 13.255 10.745 24 24 24zM181.333 376v80c0 13.255 10.745 24 24 24h101.333c13.255 0 24-10.745 24-24v-80c0-13.255-10.745-24-24-24H205.333c-13.255 0-24 10.745-24 24z"></path></svg>';
resultMode.appendChild(gridMode);
resultMode.appendChild(listMode);
if (CONF.options.display === "grid") {
gridMode.classList.add("active")
} else {
listMode.classList.add("active")
}
gridMode.addEventListener("click", () => {
CONF.options.display = "grid";
CONF.save();
searchDebounced();
});
listMode.addEventListener("click", () => {
CONF.options.display = "list";
CONF.save();
searchDebounced();
});
statsCardBody.appendChild(resultMode);
// Sort mode
const sortMode = document.createElement("div");
sortMode.setAttribute("class", "dropdown");
sortMode.style.cssFloat = "right";
sortMode.style.marginRight = "10px";
const sortModeBtn = document.createElement("button");
sortModeBtn.setAttribute("class", "btn btn-md btn-primary dropdown-toggle");
sortModeBtn.setAttribute("id", "sortModeBtn");
sortModeBtn.setAttribute("type", "button");
sortModeBtn.setAttribute("data-toggle", "dropdown");
sortModeBtn.setAttribute("aria-haspopup", "true");
sortModeBtn.setAttribute("aria-expanded", "false");
sortModeBtn.setAttribute("title", "Sort options");
sortModeBtn.innerHTML = '<svg aria-hidden="true" width="20px" height="20px" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 320 512"><path fill="currentColor" d="M41 288h238c21.4 0 32.1 25.9 17 41L177 448c-9.4 9.4-24.6 9.4-33.9 0L24 329c-15.1-15.1-4.4-41 17-41zm255-105L177 64c-9.4-9.4-24.6-9.4-33.9 0L24 183c-15.1 15.1-4.4 41 17 41h238c21.4 0 32.1-25.9 17-41z"></path></svg>';
const sortModeMenu = document.createElement("div");
sortModeMenu.setAttribute("class", "dropdown-menu");
sortModeMenu.setAttribute("aria-labelledby", "sortModeBtn");
Object.keys(SORT_MODES).forEach(mode => {
const item = document.createElement("div");
item.setAttribute("class", "dropdown-item");
item.appendChild(document.createTextNode(SORT_MODES[mode].text));
sortModeMenu.appendChild(item);
item.onclick = function () {
CONF.options.sort = mode;
CONF.save();
searchDebounced();
};
});
sortMode.appendChild(sortModeBtn);
sortMode.appendChild(sortModeMenu);
statsCardBody.appendChild(sortMode);
if (totalHits !== 0) {
let sizeStat = document.createElement("div");
sizeStat.appendChild(document.createTextNode(humanFileSize(searchResult["aggregations"]["total_size"]["value"])));
statsCardBody.appendChild(sizeStat);
}
statsCard.appendChild(statsCardBody);
return statsCard;
}
function makeResultContainer() {
let resultContainer = document.createElement("div");
if (CONF.options.display === "grid") {
resultContainer.setAttribute("class", "bricklayer");
} else {
resultContainer.setAttribute("class", "list-group");
}
return resultContainer;
}

File diff suppressed because one or more lines are too long

View File

@@ -1,713 +0,0 @@
const SIZE = 40;
let mimeMap = [];
let tagMap = [];
let mimeTree;
let tagTree;
let searchBar = document.getElementById("searchBar");
let pathBar = document.getElementById("pathBar");
let lastDoc = null;
let reachedEnd = false;
let docCount = 0;
let coolingDown = false;
let searchBusy = true;
let selectedIndices = [];
let indexMap = {};
let size_min = 0;
let size_max = 10000000000000;
let date_min = null;
let date_max = null;
const CONF = new Settings();
const _defaults = {
display: "grid",
fuzzy: true,
highlight: true,
sort: "score",
searchInPath: false,
};
SORT_MODES = {
score: {
text: "Relevance",
mode: [
{_score: {order: "desc"}},
{_tie: {order: "asc"}}
],
key: hit => hit["_score"]
},
date_asc: {
text: "Date (Ascending)", mode: [
{mtime: {order: "asc"}},
{_tie: {order: "asc"}}
],
key: hit => hit["_source"]["mtime"]
},
date_desc: {
text: "Date (Descending)", mode: [
{mtime: {order: "desc"}},
{_tie: {order: "asc"}}
],
key: hit => hit["_source"]["mtime"]
},
size_asc: {
text: "Size (Ascending)", mode: [
{size: {order: "asc"}},
{_tie: {order: "asc"}}
],
key: hit => hit["_source"]["size"]
},
size_desc: {
text: "Size (Descending)", mode: [
{size: {order: "desc"}},
{_tie: {order: "asc"}}
],
key: hit => hit["_source"]["size"]
},
};
function Settings() {
this.options = {};
this._onUpdate = function () {
$("#fuzzyToggle").prop("checked", this.options.fuzzy);
};
this.load = function () {
const raw = window.localStorage.getItem("options");
if (raw === null) {
this.options = _defaults;
} else {
const j = JSON.parse(raw);
if (!j || Object.keys(_defaults).some(k => !j.hasOwnProperty(k))) {
this.options = _defaults;
} else {
this.options = j;
}
}
this._onUpdate();
};
this.save = function () {
window.localStorage.setItem("options", JSON.stringify(this.options));
this._onUpdate();
}
}
function showEsError() {
$.toast({
heading: "Elasticsearch connection error",
text: "sist2 web module encountered an error while connecting " +
"to Elasticsearch. See server logs for more information.",
stack: false,
bgColor: "#a94442",
textColor: "#f2dede",
position: 'bottom-right',
hideAfter: false
});
}
jQuery["jsonPost"] = function (url, data) {
return jQuery.ajax({
url: url,
type: "post",
data: JSON.stringify(data),
contentType: "application/json"
}).fail(err => {
showEsError();
console.log(err);
});
};
window.onload = () => {
$("#theme").on("click", () => {
if (!document.cookie.includes("sist")) {
document.cookie = "sist=dark";
} else {
document.cookie = "sist=; Max-Age=-99999999;";
}
window.location.reload();
})
CONF.load();
};
function toggleFuzzy() {
searchDebounced();
}
$.jsonPost("i").then(resp => {
const urlIndices = (new URLSearchParams(location.search)).get("i");
resp["indices"].forEach(idx => {
indexMap[idx.id] = idx.name;
const opt = $("<option>")
.attr("value", idx.id)
.append(idx.name);
if (urlIndices) {
if (urlIndices.split(",").indexOf(idx.name) !== -1) {
opt.attr("selected", true);
selectedIndices.push(idx.id);
}
} else if (!idx.name.includes("(nsfw)")) {
opt.attr("selected", true);
selectedIndices.push(idx.id);
}
$("#indices").append(opt);
});
createPathTree("#pathTree");
});
function getDocumentInfo(id) {
return $.getJSON("d/" + id).fail(e => {
console.log(e);
showEsError();
})
}
function handleTreeClick(tree) {
return (node, e) => {
if (e !== "checked") {
return
}
if (node.id === "any") {
if (!node.itree.state.checked) {
tree.deselect();
}
} else {
tree.node("any").deselect();
}
searchDebounced();
}
}
$.jsonPost("es", {
aggs: {
mimeTypes: {
terms: {
field: "mime",
size: 10000
}
}
},
size: 0,
}).then(resp => {
resp["aggregations"]["mimeTypes"]["buckets"].sort((a, b) => a.key > b.key).forEach(bucket => {
let tmp = bucket["key"].split("/");
let category = tmp[0];
let mime = tmp[1];
let category_exists = false;
let child = {
"id": bucket["key"],
"text": `${mime} (${bucket["doc_count"]})`
};
mimeMap.forEach(node => {
if (node.text === category) {
node.children.push(child);
category_exists = true;
}
});
if (!category_exists) {
mimeMap.push({"text": category, children: [child]});
}
});
mimeMap.push({"text": "All", "id": "any"});
mimeTree = new InspireTree({
selection: {
mode: 'checkbox'
},
data: mimeMap
});
new InspireTreeDOM(mimeTree, {
target: '#mimeTree'
});
mimeTree.on("node.state.changed", handleTreeClick(mimeTree));
mimeTree.deselect();
mimeTree.node("any").select();
});
// Tags tree
$.jsonPost("es", {
aggs: {
tags: {
terms: {
field: "tag",
size: 10000
}
}
},
size: 0,
}).then(resp => {
resp["aggregations"]["tags"]["buckets"]
.sort((a, b) => a["key"].localeCompare(b["key"]))
.forEach(bucket => {
addTag(tagMap, bucket["key"], bucket["key"], bucket["doc_count"])
});
tagMap.push({"text": "All", "id": "any"});
tagTree = new InspireTree({
selection: {
mode: 'checkbox'
},
data: tagMap
});
new InspireTreeDOM(tagTree, {
target: '#tagTree'
});
tagTree.on("node.state.changed", handleTreeClick(tagTree));
tagTree.node("any").select();
searchBusy = false;
});
function addTag(map, tag, id, count) {
let tags = tag.split("#")[0].split(".");
let child = {
id: id,
text: tags.length !== 1 ? tags[0] : `${tags[0]} (${count})`,
children: []
};
let found = false;
map.forEach(node => {
if (node.text === child.text) {
found = true;
if (tags.length !== 1) {
addTag(node.children, tags.slice(1).join("."), id, count);
}
}
});
if (!found) {
if (tags.length !== 1) {
addTag(child.children, tags.slice(1).join("."), id, count);
map.push(child);
} else {
map.push(child);
}
}
}
function insertHits(resultContainer, hits) {
for (let i = 0; i < hits.length; i++) {
if (CONF.options.display === "grid") {
resultContainer._brick.append(createDocCard(hits[i]));
} else {
resultContainer.appendChild(createDocLine(hits[i]));
}
docCount++;
}
}
window.addEventListener("scroll", function () {
if (!searchBusy) {
let threshold = 400;
if ((window.innerHeight + window.scrollY) >= document.body.offsetHeight - threshold) {
if (!reachedEnd) {
coolingDown = true;
search(lastDoc);
}
}
}
});
function getSelectedNodes(tree) {
let selectedNodes = [];
let selected = tree.selected();
for (let i = 0; i < selected.length; i++) {
if (selected[i].id === "any") {
return ["any"]
}
//Only get children
if (selected[i].text.indexOf("(") !== -1) {
selectedNodes.push(selected[i].id);
}
}
return selectedNodes
}
function search(after = null) {
lastDoc = null;
if (searchBusy) {
return;
}
searchBusy = true;
let searchResults = document.getElementById("searchResults");
//Clear old search results
let preload;
if (!after) {
while (searchResults.firstChild) {
searchResults.removeChild(searchResults.firstChild);
}
preload = makePreloader();
searchResults.appendChild(preload);
}
let query = searchBar.value;
let empty = query === "";
let condition = empty ? "should" : "must";
let filters = [
{range: {size: {gte: size_min, lte: size_max}}},
{terms: {index: selectedIndices}}
];
let fields = [
"name^8",
"content^3",
"album^8", "artist^8", "title^8", "genre^2", "album_artist^8",
"font_name^6"
];
if (CONF.options.searchInPath) {
fields.push("path.text^5");
}
if ($("#fuzzyToggle").prop("checked")) {
fields.push("content.nGram");
if (CONF.options.searchInPath) {
fields.push("path.nGram");
}
fields.push("name.nGram^3");
}
let path = pathBar.value.replace(/\/$/, "").toLowerCase(); //remove trailing slashes
if (path !== "") {
filters.push([{term: {path: path}}])
}
let mimeTypes = getSelectedNodes(mimeTree);
if (!mimeTypes.includes("any")) {
filters.push([{terms: {"mime": mimeTypes}}]);
}
let tags = getSelectedNodes(tagTree);
if (!tags.includes("any")) {
filters.push([{terms: {"tag": tags}}]);
}
if (date_min && date_max) {
filters.push([{range: {mtime: {gte: date_min, lte: date_max}}}])
} else if (date_min) {
filters.push([{range: {mtime: {gte: date_min}}}])
} else if (date_max) {
filters.push([{range: {mtime: {lte: date_max}}}])
}
let q = {
"_source": {
excludes: ["content", "_tie"]
},
query: {
bool: {
[condition]: {
simple_query_string: {
query: query,
fields: fields,
default_operator: "and"
}
},
filter: filters
}
},
"sort": SORT_MODES[CONF.options.sort].mode,
aggs:
{
total_size: {"sum": {"field": "size"}},
total_count: {"value_count": {"field": "size"}}
},
size: SIZE,
};
if (after) {
q.search_after = [SORT_MODES[CONF.options.sort].key(after), after["_id"]];
}
if (CONF.options.highlight) {
q.highlight = {
pre_tags: ["<mark>"],
post_tags: ["</mark>"],
fields: {
content: {},
// "content.nGram": {},
name: {},
"name.nGram": {},
font_name: {},
}
};
if (CONF.options.searchInPath) {
q.highlight.fields["path.text"] = {};
q.highlight.fields["path.nGram"] = {};
}
}
$.jsonPost("es", q).then(searchResult => {
let hits = searchResult["hits"]["hits"];
if (hits) {
lastDoc = hits[hits.length - 1];
}
if (!after) {
preload.remove();
searchResults.appendChild(makeStatsCard(searchResult));
} else {
let pageIndicator = makePageIndicator(searchResult);
searchResults.appendChild(pageIndicator);
}
//Setup page
let resultContainer = makeResultContainer();
searchResults.appendChild(resultContainer);
if (CONF.options.display === "grid") {
resultContainer._brick = new Bricklayer(resultContainer);
}
if (!after) {
docCount = 0;
}
reachedEnd = hits.length !== SIZE;
insertHits(resultContainer, hits);
searchBusy = false;
});
}
let searchDebounced = _.debounce(function () {
coolingDown = false;
search()
}, 500);
searchBar.addEventListener("keyup", searchDebounced);
pathBar.addEventListener("keyup", searchDebounced);
//Size slider
$("#sizeSlider").ionRangeSlider({
type: "double",
grid: false,
force_edges: true,
min: 0,
max: 3684.03149864,
from: 0,
to: 3684.03149864,
min_interval: 5,
drag_interval: true,
prettify: function (num) {
if (num === 0) {
return "0 B"
} else if (num >= 3684) {
return humanFileSize(num * num * num) + "+";
}
return humanFileSize(num * num * num)
},
onChange: function (e) {
size_min = (e.from * e.from * e.from);
size_max = (e.to * e.to * e.to);
if (e.to >= 3684) {
size_max = 10000000000000;
}
searchDebounced();
}
});
//Date slider
$.jsonPost("es", {
aggs: {
date_min: {min: {field: "mtime"}},
date_max: {max: {field: "mtime"}},
},
size: 0
}).then(resp => {
$("#dateSlider").ionRangeSlider({
type: "double",
grid: false,
force_edges: true,
min: resp["aggregations"]["date_min"]["value"],
max: resp["aggregations"]["date_max"]["value"],
from: resp["aggregations"]["date_min"]["value"],
to: (Date.now() / 1000),
min_interval: 3600 * 24 * 7,
step: 3600 * 24,
drag_interval: true,
prettify: function (num) {
let date = (new Date(num * 1000));
return date.getUTCFullYear() + "-" + ("0" + (date.getUTCMonth() + 1)).slice(-2) + "-" + ("0" + date.getUTCDate()).slice(-2)
},
onFinish: function (e) {
date_min = e.from === e.min ? null : e.from;
date_max = e.to === e.max ? null : e.to;
searchDebounced();
}
});
})
function updateIndices() {
let selected = $('#indices').find('option:selected');
selectedIndices = [];
$(selected).each(function () {
selectedIndices.push($(this).val());
});
searchDebounced();
}
document.getElementById("indices").addEventListener("change", updateIndices);
updateIndices();
window.onkeyup = function (e) {
if (e.key === "/" || e.key === "Escape") {
const bar = document.getElementById("searchBar");
bar.scrollIntoView();
bar.focus();
}
};
function getNextDepth(node) {
let q = {
query: {
bool: {
filter: [
{term: {index: node.index}},
{range: {_depth: {gte: node.depth + 1, lte: node.depth + 3}}},
]
}
},
aggs: {
paths: {
terms: {
field: "path",
size: 10000
}
}
},
size: 0
}
if (node.depth > 0) {
q.query.bool.must = {
prefix: {
path: node.id,
}
};
}
return $.jsonPost("es", q).then(resp => {
const buckets = resp["aggregations"]["paths"]["buckets"];
if (!buckets) {
return false;
}
const paths = [];
return buckets
.filter(bucket => bucket.key.length > node.id.length || node.id.startsWith("/"))
.sort((a, b) => a.key > b.key)
.map(bucket => {
if (paths.some(n => bucket.key.startsWith(n))) {
return null;
}
const name = node.id.startsWith("/") ? bucket.key : bucket.key.slice(node.id.length + 1);
paths.push(bucket.key);
return {
id: bucket.key,
text: `${name}/ (${bucket.doc_count})`,
depth: node.depth + 1,
index: node.index,
children: true,
}
}).filter(x => x !== null)
})
}
function handlePathTreeClick(tree) {
return (event, node, handler) => {
if (node.depth !== 0) {
$("#pathBar").val(node.id);
$("#pathTreeModal").modal("hide");
searchDebounced();
}
handler();
}
}
function createPathTree(target) {
let pathTree = new InspireTree({
data: function (node, resolve, reject) {
return getNextDepth(node);
}
});
selectedIndices.forEach(index => {
pathTree.addNode({
id: "/" + index,
text: `/[${indexMap[index]}]`,
index: index,
depth: 0,
children: true
})
});
new InspireTreeDOM(pathTree, {
target: target
});
pathTree.on("node.click", handlePathTreeClick(pathTree));
}
function updateSettings() {
CONF.options.display = $("#settingDisplay").val();
CONF.options.fuzzy = $("#settingFuzzy").prop("checked");
CONF.options.highlight = $("#settingHighlight").prop("checked");
CONF.options.searchInPath = $("#settingSearchInPath").prop("checked");
CONF.save();
searchDebounced();
$.toast({
heading: "Settings updated",
text: "Settings saved to browser storage",
stack: 3,
bgColor: "#00a4bc",
textColor: "#fff",
position: 'bottom-right',
hideAfter: 3000,
loaderBg: "#08c7e8",
});
}
function loadSettings() {
CONF.load();
$("#settingDisplay").val(CONF.options.display);
$("#settingFuzzy").prop("checked", CONF.options.fuzzy);
$("#settingHighlight").prop("checked", CONF.options.highlight);
$("#settingSearchInPath").prop("checked", CONF.options.searchInPath);
}

View File

@@ -1,228 +0,0 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="utf-8">
<title>sist2 - Search</title>
<meta name='viewport' content='width=device-width, initial-scale=1.0, maximum-scale=1.0, user-scalable=no'/>
<link href="css" rel="stylesheet" type="text/css">
</head>
<body>
<nav class="navbar navbar-expand-lg">
<a class="navbar-brand" href="/">sist2</a>
<span class="badge badge-pill version">2.2.0</span>
<span class="tagline">Lightning-fast file system indexer and search tool </span>
<button style="margin-left: auto" class="btn" type="button" data-toggle="modal" data-target="#settings" onclick="loadSettings()">Settings</button>
<a id="theme" class="btn" title="Toggle theme" href="/">Theme</a>
</nav>
<div class="container">
<div class="card">
<div class="card-body">
<div class="input-group">
<div class="input-group-prepend">
<div class="input-group-text">
<span title="Toggle fuzzy searching" onclick="document.getElementById('fuzzyToggle').click()">Fuzzy&nbsp</span>
<input title="Toggle fuzzy searching" type="checkbox" id="fuzzyToggle"
onclick="toggleFuzzy()" checked>
</div>
</div>
<input id="searchBar" type="search" class="form-control" placeholder="Search">
<div class="input-group-append">
<button class="btn btn-outline-secondary small-btn" type="button" data-toggle="modal"
data-target="#help">?
</button>
<button class="btn btn-outline-secondary large-btn" type="button" data-toggle="modal"
data-target="#help">Help
</button>
</div>
</div>
<div class="row">
<div class="col">
<input title="File size" id="sizeSlider" name="size" width="100%">
</div>
<div class="col">
<div class="input-group" style="margin-bottom: 0.5em; margin-top: 1em">
<div class="input-group-prepend">
<button id="pathBarHelper" class="btn btn-outline-secondary" data-toggle="modal" data-target="#pathTreeModal">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 576 512" width="20px"><path d="M288 224h224a32 32 0 0 0 32-32V64a32 32 0 0 0-32-32H400L368 0h-80a32 32 0 0 0-32 32v64H64V8a8 8 0 0 0-8-8H40a8 8 0 0 0-8 8v392a16 16 0 0 0 16 16h208v64a32 32 0 0 0 32 32h224a32 32 0 0 0 32-32V352a32 32 0 0 0-32-32H400l-32-32h-80a32 32 0 0 0-32 32v64H64V128h192v64a32 32 0 0 0 32 32zm0 96h66.74l32 32H512v128H288zm0-288h66.74l32 32H512v128H288z"/></svg>
</button>
</div>
<input id="pathBar" type="search" class="form-control" placeholder="Filter path">
</div>
</div>
</div>
<input title="Date filter" id="dateSlider" name="size" width="100%">
<div class="row">
<div class="col">
<label for="indices">Search in indices</label>
<select class="custom-select" id="indices" multiple size="6"></select>
</div>
<div class="col" id="treeTabs">
<ul class="nav nav-tabs" role="tablist">
<li class="nav-item">
<a class="nav-link active" data-toggle="tab" href="#mime" role="tab" aria-controls="home"
aria-selected="true">Mime Types</a>
</li>
<li class="nav-item">
<a class="nav-link" data-toggle="tab" href="#tag" role="tab" aria-controls="profile"
aria-selected="false" title="User-defined tags">Tags</a>
</li>
</ul>
<div class="tab-content" id="myTabContent">
<div class="tab-pane fade show active" id="mime" role="tabpanel" aria-labelledby="home-tab">
<div id="mimeTree" class="tree"></div>
</div>
<div class="tab-pane fade" id="tag" role="tabpanel" aria-labelledby="profile-tab">
<div id="tagTree" class="tree"></div>
</div>
</div>
</div>
</div>
</div>
</div>
<div class="modal" id="modal" tabindex="-1" role="dialog" aria-labelledby="modal-title" aria-hidden="true">
<div class="modal-dialog modal-lg modal-dialog-centered" role="document">
<div class="modal-content">
<div class="modal-header">
<h5 class="modal-title" id="modal-title"></h5>
<button type="button" class="close" data-dismiss="modal" aria-label="Close">
<span aria-hidden="true">&times;</span>
</button>
</div>
<div class="modal-body" id="modal-body"></div>
</div>
</div>
</div>
<div class="modal" id="help" tabindex="-1" role="dialog" aria-labelledby="modal-title" aria-hidden="true">
<div class="modal-dialog modal-lg modal-dialog-centered" role="document">
<div class="modal-content">
<div class="modal-header">
<h5 class="modal-title">Search help</h5>
<button type="button" class="close" data-dismiss="modal" aria-label="Close">
<span aria-hidden="true">&times;</span>
</button>
</div>
<div class="modal-body">
<table class="table">
<tbody>
<tr>
<td><code>+</code></td>
<td>signifies AND operation</td>
</tr>
<tr>
<td><code>|</code></td>
<td>signifies OR operation</td>
</tr>
<tr>
<td><code>-</code></td>
<td>negates a single token</td>
</tr>
<tr>
<td><code>""</code></td>
<td>wraps a number of tokens to signify a phrase for searching</td>
</tr>
<tr>
<td><code>*</code></td>
<td>at the end of a term signifies a prefix query</td>
</tr>
<tr>
<td><code>(</code> and <code>)</code></td>
<td>signify precedence</td>
</tr>
<tr>
<td><code>~N</code></td>
<td>after a word signifies edit distance (fuzziness)</td>
</tr>
<tr>
<td><code>~N</code></td>
<td>after a phrase signifies slop amount</td>
</tr>
</tbody>
</table>
<p>For example: <code>"fried eggs" +(eggplant | potato) -frittata</code> will match the phrase
<i>fried eggs</i> and either <i>eggplant</i> or <i>potato</i>, but will ignore results
containing <i>frittata</i>.</p>
<p>When neither <code>+</code> or <code>|</code> is specified, the default operator is <code>+</code> (and).</p>
<p>When the <b>Fuzzy</b> option is checked, partial matches are also returned.</p>
<br>
<p>For more information, see <a target="_blank"
href="//www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl-simple-query-string-query.html">Elasticsearch
documentation</a></p>
</div>
</div>
</div>
</div>
<div class="modal" id="settings" tabindex="-1" role="dialog" aria-labelledby="modal-title" aria-hidden="true">
<div class="modal-dialog modal-dialog-centered" role="document">
<div class="modal-content">
<div class="modal-header">
<h5 class="modal-title">Settings</h5>
<button type="button" class="close" data-dismiss="modal" aria-label="Close">
<span aria-hidden="true">&times;</span>
</button>
</div>
<div class="modal-body">
<div class="custom-control custom-checkbox">
<input type="checkbox" class="custom-control-input" id="settingHighlight">
<label class="custom-control-label" for="settingHighlight">Enable highlighting</label>
</div>
<div class="custom-control custom-checkbox">
<input type="checkbox" class="custom-control-input" id="settingFuzzy">
<label class="custom-control-label" for="settingFuzzy">Set fuzzy search by default</label>
</div>
<div class="custom-control custom-checkbox">
<input type="checkbox" class="custom-control-input" id="settingSearchInPath">
<label class="custom-control-label" for="settingSearchInPath">Enable matching query against document path</label>
</div>
<label for="settingDisplay">Display</label>
<select id="settingDisplay" class="form-control form-control-sm">
<option value="grid">Grid</option>
<option value="list">List</option>
</select>
<br>
<button style="float: right" class="btn btn-primary" onclick="updateSettings()">Update settings</button>
</div>
</div>
</div>
</div>
<div class="modal" id="pathTreeModal" tabindex="-1" role="dialog" aria-labelledby="modal-title" aria-hidden="true">
<div class="modal-dialog modal-lg" role="document">
<div class="modal-content">
<div class="modal-header">
<h5 class="modal-title">Select path</h5>
<button type="button" class="close" data-dismiss="modal" aria-label="Close">
<span aria-hidden="true">&times;</span>
</button>
</div>
<div class="modal-body">
<div id="pathTree" class="tree"></div>
</div>
</div>
</div>
</div>
<div id="searchResults"></div>
</div>
<script src="js" type="text/javascript"></script>
</body>
</html>

View File

@@ -1,7 +1,5 @@
#include "tpool.h"
#include "ctx.h"
#include "sist.h"
#include <pthread.h>
typedef void (*thread_func_t)(void *arg);
@@ -27,7 +25,6 @@ typedef struct tpool {
int done_cnt;
int stop;
void (*cleanup_func)();
} tpool_t;
@@ -103,7 +100,7 @@ static void *tpool_worker(void *arg) {
tpool_t *pool = arg;
while (1) {
pthread_mutex_lock(&pool->work_mutex);
pthread_mutex_lock(&(pool->work_mutex));
if (pool->stop) {
break;
}
@@ -116,21 +113,14 @@ static void *tpool_worker(void *arg) {
pthread_mutex_unlock(&(pool->work_mutex));
if (work != NULL) {
if (pool->stop) {
break;
}
work->func(work->arg);
free(work->arg);
free(work);
}
pthread_mutex_lock(&(pool->work_mutex));
if (work != NULL) {
pool->done_cnt++;
}
pool->done_cnt++;
progress_bar_print((double) pool->done_cnt / pool->work_cnt, ScanCtx.stat_tn_size, ScanCtx.stat_index_size);
progress_bar_print((double)pool->done_cnt / pool->work_cnt, ScanCtx.stat_tn_size, ScanCtx.stat_index_size);
if (pool->work_head == NULL) {
pthread_cond_signal(&(pool->working_cond));
@@ -138,7 +128,6 @@ static void *tpool_worker(void *arg) {
pthread_mutex_unlock(&(pool->work_mutex));
}
LOG_INFO("tpool.c", "Executing cleaup function")
pool->cleanup_func();
pthread_cond_signal(&(pool->working_cond));
@@ -147,24 +136,17 @@ static void *tpool_worker(void *arg) {
}
void tpool_wait(tpool_t *pool) {
LOG_INFO("tpool.c", "Waiting for worker threads to finish")
pthread_mutex_lock(&(pool->work_mutex));
while (1) {
if (pool->done_cnt < pool->work_cnt) {
pthread_cond_wait(&(pool->working_cond), &(pool->work_mutex));
} else {
usleep(500000);
if (pool->done_cnt == pool->work_cnt) {
pool->stop = 1;
usleep(1000000);
break;
}
pool->stop = 1;
break;
}
progress_bar_print(100.0, ScanCtx.stat_tn_size, ScanCtx.stat_index_size);
}
progress_bar_print(1.0, ScanCtx.stat_tn_size, ScanCtx.stat_index_size);
pthread_mutex_unlock(&(pool->work_mutex));
LOG_INFO("tpool.c", "Worker threads finished")
}
void tpool_destroy(tpool_t *pool) {
@@ -172,8 +154,6 @@ void tpool_destroy(tpool_t *pool) {
return;
}
LOG_INFO("tpool.c", "Destroying thread pool")
pthread_mutex_lock(&(pool->work_mutex));
tpool_work_t *work = pool->work_head;
while (work != NULL) {
@@ -188,13 +168,10 @@ void tpool_destroy(tpool_t *pool) {
for (size_t i = 0; i < pool->thread_cnt; i++) {
pthread_t thread = pool->threads[i];
if (thread != 0) {
void *_;
pthread_join(thread, &_);
pthread_cancel(thread);
}
}
LOG_INFO("tpool.c", "Final cleanup")
pthread_mutex_destroy(&(pool->work_mutex));
pthread_cond_destroy(&(pool->has_work_cond));
pthread_cond_destroy(&(pool->working_cond));
@@ -211,11 +188,11 @@ tpool_t *tpool_create(size_t thread_cnt, void cleanup_func()) {
tpool_t *pool = malloc(sizeof(tpool_t));
pool->thread_cnt = thread_cnt;
pool->work_cnt = 0;
pool->done_cnt = 0;
pool->work_cnt =0;
pool->done_cnt =0;
pool->stop = 0;
pool->cleanup_func = cleanup_func;
pool->threads = calloc(sizeof(pthread_t), thread_cnt);
pool->threads = malloc(sizeof(pthread_t) * thread_cnt);
pthread_mutex_init(&(pool->work_mutex), NULL);
@@ -225,14 +202,11 @@ tpool_t *tpool_create(size_t thread_cnt, void cleanup_func()) {
pool->work_head = NULL;
pool->work_tail = NULL;
for (size_t i = 0; i < thread_cnt; i++) {
pthread_t thread = pool->threads[i];
pthread_create(&thread, NULL, tpool_worker, pool);
pthread_detach(thread);
}
return pool;
}
void tpool_start(tpool_t *pool) {
LOG_INFOF("tpool.c", "Starting thread pool with %d threads", pool->thread_cnt)
for (size_t i = 0; i < pool->thread_cnt; i++) {
pthread_create(&pool->threads[i], NULL, tpool_worker, pool);
}
}

View File

@@ -9,7 +9,6 @@ typedef struct tpool tpool_t;
typedef void (*thread_func_t)(void *arg);
tpool_t *tpool_create(size_t num, void (*cleanup_func)());
void tpool_start(tpool_t *pool);
void tpool_destroy(tpool_t *tm);
int tpool_add_work(tpool_t *pool, thread_func_t func, void *arg);

View File

@@ -1,19 +1,39 @@
#ifndef SIST2_TYPES_H
#define SIST2_TYPES_H
#define INDEX_TYPE_BIN "binary"
#define INDEX_TYPE_JSON "json"
#define INDEX_VERSION_EXTERNAL "_external_v1"
#define META_INT_MASK 0xF0
#define META_STR_MASK 0xE0
#define META_LONG_MASK 0xD0
#define IS_META_INT(key) (key & META_INT_MASK) == META_INT_MASK
#define IS_META_LONG(key) (key & META_LONG_MASK) == META_LONG_MASK
#define IS_META_STR(meta) (meta->key & META_STR_MASK) == META_STR_MASK
// This is written to file as a 8bit char!
enum metakey {
MetaContent = 1 | META_STR_MASK,
MetaWidth = 2 | META_INT_MASK,
MetaHeight = 3 | META_INT_MASK,
MetaMediaDuration = 4 | META_LONG_MASK,
MetaMediaAudioCodec = 5 | META_INT_MASK,
MetaMediaVideoCodec = 6 | META_INT_MASK,
MetaMediaBitrate = 7 | META_LONG_MASK,
MetaArtist = 8 | META_STR_MASK,
MetaAlbum = 9 | META_STR_MASK,
MetaAlbumArtist = 10 | META_STR_MASK,
MetaGenre = 11 | META_STR_MASK,
MetaTitle = 12 | META_STR_MASK,
MetaFontName = 13 | META_STR_MASK,
};
typedef struct index_descriptor {
char uuid[UUID_STR_LEN];
char version[64];
char version[6];
long timestamp;
char root[PATH_MAX];
char rewrite_url[8196];
short root_len;
char name[1024];
char type[64];
} index_descriptor_t;
typedef struct index_t {
@@ -22,4 +42,46 @@ typedef struct index_t {
char path[PATH_MAX];
} index_t;
typedef struct meta_line {
struct meta_line *next;
enum metakey key;
union {
unsigned long longval;
int intval;
char strval[0];
};
} meta_line_t;
typedef struct document {
unsigned char uuid[16];
unsigned long ino;
unsigned long size;
unsigned int mime;
int mtime;
short base;
short ext;
meta_line_t *meta_head;
meta_line_t *meta_tail;
char *filepath;
} document_t;
typedef struct parse_job_t {
int base;
int ext;
struct stat info;
char filepath[1];
} parse_job_t;
#define APPEND_META(doc, meta) \
meta->next = NULL;\
if (doc->meta_head == NULL) {\
doc->meta_head = meta;\
doc->meta_tail = doc->meta_head;\
} else {\
doc->meta_tail->next = meta;\
doc->meta_tail = meta;\
}
#endif

View File

@@ -1,8 +1,133 @@
#include "util.h"
#include "src/ctx.h"
#include <wordexp.h>
#include <glib.h>
dyn_buffer_t dyn_buffer_create() {
dyn_buffer_t buf;
buf.size = INITIAL_BUF_SIZE;
buf.cur = 0;
buf.buf = malloc(INITIAL_BUF_SIZE);
return buf;
}
void grow_buffer(dyn_buffer_t *buf, size_t size) {
if (buf->cur + size > buf->size) {
do {
buf->size *= 2;
} while (buf->cur + size > buf->size);
buf->buf = realloc(buf->buf, buf->size);
}
}
void grow_buffer_small(dyn_buffer_t *buf) {
if (buf->cur + sizeof(long) > buf->size) {
buf->size *= 2;
buf->buf = realloc(buf->buf, buf->size);
}
}
void dyn_buffer_write(dyn_buffer_t *buf, void *data, size_t size) {
grow_buffer(buf, size);
memcpy(buf->buf + buf->cur, data, size);
buf->cur += size;
}
void dyn_buffer_write_char(dyn_buffer_t *buf, char c) {
grow_buffer_small(buf);
*(buf->buf + buf->cur) = c;
buf->cur += sizeof(c);
}
void dyn_buffer_write_str(dyn_buffer_t *buf, char *str) {
dyn_buffer_write(buf, str, strlen(str));
dyn_buffer_write_char(buf, '\0');
}
void dyn_buffer_write_int(dyn_buffer_t *buf, int d) {
grow_buffer_small(buf);
*(int *) (buf->buf + buf->cur) = d;
buf->cur += sizeof(int);
}
void dyn_buffer_write_short(dyn_buffer_t *buf, short s) {
grow_buffer_small(buf);
*(short *) (buf->buf + buf->cur) = s;
buf->cur += sizeof(short);
}
void dyn_buffer_write_long(dyn_buffer_t *buf, unsigned long l) {
grow_buffer_small(buf);
*(unsigned long *) (buf->buf + buf->cur) = l;
buf->cur += sizeof(unsigned long);
}
void dyn_buffer_destroy(dyn_buffer_t *buf) {
free(buf->buf);
}
void text_buffer_destroy(text_buffer_t *buf) {
dyn_buffer_destroy(&buf->dyn_buffer);
}
text_buffer_t text_buffer_create(int max_size) {
text_buffer_t text_buf;
text_buf.dyn_buffer = dyn_buffer_create();
text_buf.max_size = max_size;
text_buf.last_char_was_whitespace = FALSE;
return text_buf;
}
void text_buffer_terminate_string(text_buffer_t *buf) {
dyn_buffer_write_char(&buf->dyn_buffer, '\0');
}
int text_buffer_append_char(text_buffer_t *buf, int c) {
if (SHOULD_IGNORE_CHAR(c)) {
if (!buf->last_char_was_whitespace) {
dyn_buffer_write_char(&buf->dyn_buffer, ' ');
buf->last_char_was_whitespace = TRUE;
if (buf->dyn_buffer.cur >= buf->max_size) {
return TEXT_BUF_FULL;
}
}
} else {
buf->last_char_was_whitespace = FALSE;
dyn_buffer_write_char(&buf->dyn_buffer, (char) c);
if (buf->dyn_buffer.cur >= buf->max_size) {
return TEXT_BUF_FULL;
}
}
return 0;
}
void incremental_put(GHashTable *table, unsigned long inode_no, int mtime) {
g_hash_table_insert(table, (gpointer) inode_no, GINT_TO_POINTER(mtime));
}
int incremental_get(GHashTable *table, unsigned long inode_no) {
if (table != NULL) {
return GPOINTER_TO_INT(g_hash_table_lookup(table, (gpointer) inode_no));
} else {
return 0;
}
}
int incremental_mark_file_for_copy(GHashTable *table, unsigned long inode_no) {
g_hash_table_insert(table, GINT_TO_POINTER(inode_no), GINT_TO_POINTER(1));
}
#define PBSTR "========================================"
#define PBWIDTH 40
@@ -11,7 +136,7 @@ dyn_buffer_t url_escape(char *str) {
dyn_buffer_t text = dyn_buffer_create();
char *ptr = str;
char * ptr = str;
while (*ptr) {
if (*ptr == '#') {
dyn_buffer_write(&text, "%23", 3);
@@ -33,10 +158,8 @@ char *abspath(const char *path) {
if (abs == NULL) {
return NULL;
}
if (strlen(abs) > 1) {
abs = realloc(abs, strlen(abs) + 2);
strcat(abs, "/");
}
abs = realloc(abs, strlen(abs) + 2);
strcat(abs, "/");
wordfree(&w);
return abs;
@@ -46,7 +169,7 @@ char *expandpath(const char *path) {
wordexp_t w;
wordexp(path, &w, 0);
char *expanded = malloc(strlen(w.we_wordv[0]) + 2);
char * expanded = malloc(strlen(w.we_wordv[0]) + 2);
strcpy(expanded, w.we_wordv[0]);
strcat(expanded, "/");
@@ -98,29 +221,4 @@ GHashTable *incremental_get_table() {
return file_table;
}
const char *find_file_in_paths(const char *paths[], const char *filename) {
for (int i = 0; paths[i] != NULL; i++) {
char *apath = abspath(paths[i]);
if (apath == NULL) {
continue;
}
char path[PATH_MAX];
snprintf(path, sizeof(path), "%s%s", apath, filename);
LOG_DEBUGF("util.c", "Looking for '%s' in folder '%s'", filename, apath)
free(apath);
struct stat info;
int ret = stat(path, &info);
if (ret != -1) {
return paths[i];
}
}
return NULL;
}

View File

@@ -2,45 +2,67 @@
#define SIST2_UTIL_H
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <glib.h>
#define TEXT_BUF_FULL -1
#define INITIAL_BUF_SIZE 1024 * 16
#define SHOULD_IGNORE_CHAR(c) c < '0' || c > 'z'
#include "third-party/utf8.h/utf8.h"
#include "libscan/scan.h"
typedef struct dyn_buffer {
char *buf;
size_t cur;
size_t size;
} dyn_buffer_t;
#include "sist.h"
char *abspath(const char *path);
typedef struct text_buffer {
size_t max_size;
int last_char_was_whitespace;
dyn_buffer_t dyn_buffer;
} text_buffer_t;
char *abspath(const char * path);
char *expandpath(const char *path);
dyn_buffer_t url_escape(char *str);
void progress_bar_print(double percentage, size_t tn_size, size_t index_size);
GHashTable *incremental_get_table();
__always_inline
static void incremental_put(GHashTable *table, unsigned long inode_no, int mtime) {
g_hash_table_insert(table, (gpointer) inode_no, GINT_TO_POINTER(mtime));
}
dyn_buffer_t dyn_buffer_create();
__always_inline
static int incremental_get(GHashTable *table, unsigned long inode_no) {
if (table != NULL) {
return GPOINTER_TO_INT(g_hash_table_lookup(table, (gpointer) inode_no));
} else {
return 0;
}
}
void grow_buffer(dyn_buffer_t *buf, size_t size);
__always_inline
static int incremental_mark_file_for_copy(GHashTable *table, unsigned long inode_no) {
return g_hash_table_insert(table, GINT_TO_POINTER(inode_no), GINT_TO_POINTER(1));
}
void grow_buffer_small(dyn_buffer_t *buf);
void dyn_buffer_write(dyn_buffer_t *buf, void *data, size_t size);
void dyn_buffer_write_char(dyn_buffer_t *buf, char c);
void dyn_buffer_write_str(dyn_buffer_t *buf, char *str);
void dyn_buffer_write_int(dyn_buffer_t *buf, int d);
void dyn_buffer_write_short(dyn_buffer_t *buf, short s);
void dyn_buffer_write_long(dyn_buffer_t *buf, unsigned long l);
void dyn_buffer_destroy(dyn_buffer_t *buf);
void text_buffer_destroy(text_buffer_t *buf);
text_buffer_t text_buffer_create(int max_size);
void text_buffer_terminate_string(text_buffer_t *buf);
int text_buffer_append_char(text_buffer_t *buf, int c);
void incremental_put(GHashTable *table, unsigned long inode_no, int mtime);
int incremental_get(GHashTable *table, unsigned long inode_no);
int incremental_mark_file_for_copy(GHashTable *table, unsigned long inode_no);
const char *find_file_in_paths(const char **paths, const char *filename);
#endif

View File

@@ -1,41 +1,16 @@
#include "serve.h"
#include "src/sist.h"
#include "src/io/store.h"
#include "static_generated.c"
#include "src/index/elastic.h"
#include "src/index/web.h"
#include <src/ctx.h>
#include <onion/types_internal.h>
#include <mongoose.h>
#include "static_generated.c"
#define CHUNK_SIZE 1024 * 1024 * 10
static int has_prefix(const struct mg_str *str, const struct mg_str *prefix) {
return str->len > prefix->len && memcmp(str->p, prefix->p, prefix->len) == 0;
__always_inline
void set_default_headers(onion_response *res) {
onion_response_set_header(res, "Server", "sist2");
}
static int is_equal(const struct mg_str *s1, const struct mg_str *s2) {
return s1->len == s2->len && memcmp(s1->p, s2->p, s2->len) == 0;
}
static void send_response_line(struct mg_connection *nc, int status_code, int length, char *extra_headers) {
mg_printf(
nc,
"HTTP/1.1 %d %s\r\n"
"Server: sist2\r\n"
"Content-Length: %d\r\n"
"Connection: close\r\n"
"%s\r\n\r\n",
status_code, "OK",
length,
extra_headers
);
}
index_t *get_index_by_id(const char *index_id) {
for (int i = WebCtx.index_count; i >= 0; i--) {
if (strcmp(index_id, WebCtx.indices[i].desc.uuid) == 0) {
@@ -53,124 +28,268 @@ store_t *get_store(const char *index_id) {
return NULL;
}
void search_index(struct mg_connection *nc) {
send_response_line(nc, 200, sizeof(search_html), "Content-Type: text/html");
mg_send(nc, search_html, sizeof(search_html));
nc->flags |= MG_F_SEND_AND_CLOSE;
int search_index(void *p, onion_request *req, onion_response *res) {
set_default_headers(res);
onion_response_set_header(res, "Content-Type", "text/html");
onion_response_set_length(res, sizeof(search_html));
onion_response_write(res, search_html, sizeof(search_html));
return OCS_PROCESSED;
}
void javascript(struct mg_connection *nc) {
send_response_line(nc, 200, sizeof(bundle_js), "Content-Type: application/javascript");
mg_send(nc, bundle_js, sizeof(bundle_js));
nc->flags |= MG_F_SEND_AND_CLOSE;
int javascript(void *p, onion_request *req, onion_response *res) {
onion_response_set_header(res, "Content-Type", "text/javascript");
onion_response_set_length(res, sizeof(bundle_js));
onion_response_write(res, bundle_js, sizeof(bundle_js));
return OCS_PROCESSED;
}
int client_requested_dark_theme(struct http_message *hm) {
struct mg_str *cookie_header = mg_get_http_header(hm, "cookie");
if (cookie_header == NULL) {
int client_requested_dark_theme(onion_request *req) {
const char *cookie = onion_request_get_cookie(req, "sist");
if (cookie == NULL) {
return FALSE;
}
char buf[4096];
char *sist_cookie = buf;
if (mg_http_parse_header2(cookie_header, "sist", &sist_cookie, sizeof(buf)) == 0) {
return FALSE;
}
int ret = strcmp(sist_cookie, "dark") == 0;
if (sist_cookie != buf) {
free(sist_cookie);
}
return ret;
return strcmp(cookie, "dark") == 0;
}
void style(struct mg_connection *nc, struct http_message *hm) {
int style(void *p, onion_request *req, onion_response *res) {
set_default_headers(res);
if (client_requested_dark_theme(hm)) {
send_response_line(nc, 200, sizeof(bundle_dark_css), "Content-Type: text/css");
mg_send(nc, bundle_dark_css, sizeof(bundle_dark_css));
onion_response_set_header(res, "Content-Type", "text/css");
if (client_requested_dark_theme(req)) {
onion_response_set_length(res, sizeof(bundle_dark_css));
onion_response_write(res, bundle_dark_css, sizeof(bundle_dark_css));
} else {
send_response_line(nc, 200, sizeof(bundle_css), "Content-Type: text/css");
mg_send(nc, bundle_css, sizeof(bundle_css));
onion_response_set_length(res, sizeof(bundle_css));
onion_response_write(res, bundle_css, sizeof(bundle_css));
}
nc->flags |= MG_F_SEND_AND_CLOSE;
return OCS_PROCESSED;
}
void img_sprite_skin_flat(struct mg_connection *nc, struct http_message *hm) {
if (client_requested_dark_theme(hm)) {
send_response_line(nc, 200, sizeof(sprite_skin_flat_dark_png), "Content-Type: image/png");
mg_send(nc, sprite_skin_flat_dark_png, sizeof(sprite_skin_flat_dark_png));
int img_sprite_skin_flag(void *p, onion_request *req, onion_response *res) {
set_default_headers(res);
onion_response_set_header(res, "Content-Type", "image/png");
if (client_requested_dark_theme(req)) {
onion_response_set_length(res, sizeof(sprite_skin_flat_dark_png));
onion_response_write(res, sprite_skin_flat_dark_png, sizeof(sprite_skin_flat_dark_png));
} else {
send_response_line(nc, 200, sizeof(sprite_skin_flat_png), "Content-Type: image/png");
mg_send(nc, sprite_skin_flat_png, sizeof(sprite_skin_flat_png));
onion_response_set_length(res, sizeof(sprite_skin_flat_png));
onion_response_write(res, sprite_skin_flat_png, sizeof(sprite_skin_flat_png));
}
nc->flags |= MG_F_SEND_AND_CLOSE;
return OCS_PROCESSED;
}
void thumbnail(struct mg_connection *nc, struct http_message *hm, struct mg_str *path) {
if (path->len != UUID_STR_LEN * 2 + 2) {
LOG_DEBUGF("serve.c", "Invalid thumbnail path: %.*s", (int) path->len, path->p)
nc->flags |= MG_F_SEND_AND_CLOSE;
return;
int thumbnail(void *p, onion_request *req, onion_response *res) {
int flags = onion_request_get_flags(req);
if ((flags & OR_METHODS) != OR_GET) {
return OCS_NOT_PROCESSED;
}
const char *arg_index = onion_request_get_query(req, "1");
const char *arg_uuid = onion_request_get_query(req, "2");
char arg_uuid[UUID_STR_LEN];
char arg_index[UUID_STR_LEN];
memcpy(arg_index, hm->uri.p + 3, UUID_STR_LEN);
*(arg_index + UUID_STR_LEN - 1) = '\0';
memcpy(arg_uuid, hm->uri.p + 3 + UUID_STR_LEN, UUID_STR_LEN);
*(arg_uuid + UUID_STR_LEN - 1) = '\0';
if (arg_uuid == NULL || arg_index == NULL) {
return OCS_NOT_PROCESSED;
}
uuid_t uuid;
int ret = uuid_parse(arg_uuid, uuid);
if (ret != 0) {
LOG_DEBUGF("serve.c", "Invalid thumbnail UUID: %s", arg_uuid)
nc->flags |= MG_F_SEND_AND_CLOSE;
return;
}
uuid_parse(arg_uuid, uuid);
store_t *store = get_store(arg_index);
if (store == NULL) {
LOG_DEBUGF("serve.c", "Could not get store for index: %s", arg_index)
nc->flags |= MG_F_SEND_AND_CLOSE;
return;
return OCS_NOT_PROCESSED;
}
set_default_headers(res);
onion_response_set_header(res, "Content-Type", "image/jpeg");
size_t data_len = 0;
char *data = store_read(store, (char *) uuid, sizeof(uuid_t), &data_len);
if (data_len != 0) {
send_response_line(nc, 200, data_len, "Content-Type: image/jpeg");
mg_send(nc, data, data_len);
free(data);
onion_response_set_length(res, data_len);
int written = onion_response_write(res, data, data_len);
onion_response_flush(res);
if (written != data_len || data_len == 0) {
printf("Couldn't write thumb\n");
}
nc->flags |= MG_F_SEND_AND_CLOSE;
free(data);
return OCS_PROCESSED;
}
void search(struct mg_connection *nc, struct http_message *hm) {
/**
* Modified version of onion_shortcut_response_file that allows
* browsers to seek media files.
*/
int chunked_response_file(const char *filename, const char *mime,
int partial, onion_request *request, onion_response *res) {
int fd = open(filename, O_RDONLY | O_CLOEXEC);
struct stat st;
if (hm->body.len == 0) {
LOG_DEBUG("serve.c", "Client sent empty body, ignoring request")
nc->flags |= MG_F_SEND_AND_CLOSE;
return;
if (fd < 0 || stat(filename, &st) != 0 || S_ISDIR(st.st_mode)) {
close(fd);
return OCS_NOT_PROCESSED;
}
char *body = malloc(hm->body.len + 1);
memcpy(body, hm->body.p, hm->body.len);
*(body + hm->body.len) = '\0';
size_t length = st.st_size;
size_t ends;
const char *range = onion_request_get_header(request, "Range");
if (partial && range && strncmp(range, "bytes=", 6) == 0) {
onion_response_set_header(res, "Accept-Ranges", "bytes");
onion_response_set_code(res, HTTP_PARTIAL_CONTENT);
char tmp[1024];
if (strlen(range + 6) >= sizeof(tmp)) {
close(fd);
return OCS_INTERNAL_ERROR;
}
strncpy(tmp, range + 6, sizeof(tmp) - 1);
char *start = tmp;
char *end = tmp;
while (*end != '-' && *end) {
end++;
}
if (*end == '-') {
*end = '\0';
end++;
size_t starts;
starts = atol(start);
if (*end) {
// %d-%d
ends = atol(end);
} else {
// %d-
ends = MIN(starts + CHUNK_SIZE, length);
}
if (ends > length || starts >= length || starts < 0) {
close(fd);
return OCS_INTERNAL_ERROR;
}
length = ends - starts;
if (starts != 0) {
lseek(fd, starts, SEEK_SET);
}
snprintf(tmp, sizeof(tmp), "bytes %ld-%ld/%ld",
starts, ends - 1, st.st_size);
onion_response_set_header(res, "Content-Range", tmp);
}
}
onion_response_set_length(res, length);
onion_response_set_header(res, "Content-Type", mime);
onion_response_write_headers(res);
if ((onion_request_get_flags(request) & OR_HEAD) == OR_HEAD) {
length = 0;
}
if (length) {
int bytes_read = 0, bytes_written;
size_t total_read = 0;
char buf[4046];
if (length > sizeof(buf)) {
size_t max = length - sizeof(buf);
while (total_read < max) {
bytes_read = read(fd, buf, sizeof(buf));
if (bytes_read < 0) {
break;
}
total_read += bytes_read;
bytes_written = onion_response_write(res, buf, bytes_read);
if (bytes_written != bytes_read) {
break;
}
}
}
if (sizeof(buf) >= (length - total_read)) {
bytes_read = read(fd, buf, length - total_read);
onion_response_write(res, buf, bytes_read);
}
}
close(fd);
return OCS_PROCESSED;
}
int search(void *p, onion_request *req, onion_response *res) {
int flags = onion_request_get_flags(req);
if ((flags & OR_METHODS) != OR_POST) {
return OCS_NOT_PROCESSED;
}
char *scroll_param;
const char *scroll = onion_request_get_query(req, "scroll");
if (scroll != NULL) {
scroll_param = "?scroll=3m";
} else {
scroll_param = "";
}
const struct onion_block_t *block = onion_request_get_data(req);
if (block == NULL) {
return OCS_NOT_PROCESSED;
}
char url[4096];
snprintf(url, 4096, "%s/sist2/_search", WebCtx.es_url);
snprintf(url, 4096, "%s/sist2/_search%s", WebCtx.es_url, scroll_param);
response_t *r = web_post(url, onion_block_data(block), "Content-Type: application/json");
nc->user_data = web_post_async(url, body);
free(body);
set_default_headers(res);
onion_response_set_header(res, "Content-Type", "application/json");
onion_response_set_length(res, r->size);
if (r->status_code == 200) {
onion_response_write(res, r->body, r->size);
}
free_response(r);
return OCS_PROCESSED;
}
int serve_file_from_url(cJSON *json, index_t *idx, struct mg_connection *nc) {
int scroll(void *p, onion_request *req, onion_response *res) {
int flags = onion_request_get_flags(req);
if ((flags & OR_METHODS) != OR_GET) {
return OCS_NOT_PROCESSED;
}
char url[4096];
snprintf(url, 4096, "%s/_search/scroll", WebCtx.es_url);
const char *scroll_id = onion_request_get_query(req, "scroll_id");
cJSON *json = cJSON_CreateObject();
cJSON_AddStringToObject(json, "scroll_id", scroll_id);
cJSON_AddStringToObject(json, "scroll", "3m");
char *json_str = cJSON_PrintUnformatted(json);
response_t *r = web_post(url, json_str, "Content-Type: application/json");
cJSON_Delete(json);
cJSON_free(json_str);
if (r->status_code != 200) {
free_response(r);
return OCS_NOT_PROCESSED;
}
set_default_headers(res);
onion_response_set_header(res, "Content-Type", "application/json");
onion_response_set_header(res, "Content-Disposition", "application/json");
onion_response_set_length(res, r->size);
onion_response_write(res, r->body, r->size);
free_response(r);
return OCS_PROCESSED;
}
int serve_file_from_url(cJSON *json, index_t *idx, onion_request *req, onion_response *res) {
const char *path = cJSON_GetObjectItem(json, "path")->valuestring;
const char *name = cJSON_GetObjectItem(json, "name")->valuestring;
@@ -182,16 +301,12 @@ int serve_file_from_url(cJSON *json, index_t *idx, struct mg_connection *nc) {
idx->desc.rewrite_url, path, name, strlen(ext) == 0 ? "" : ".", ext);
dyn_buffer_t encoded = url_escape(url);
mg_http_send_redirect(
nc, 308,
(struct mg_str) MG_MK_STR_N(encoded.buf, encoded.cur),
(struct mg_str) MG_NULL_STR
);
int ret = onion_shortcut_redirect(encoded.buf, req, res);
dyn_buffer_destroy(&encoded);
nc->flags |= MG_F_SEND_AND_CLOSE;
return ret;
}
void serve_file_from_disk(cJSON *json, index_t *idx, struct mg_connection *nc, struct http_message *hm) {
int serve_file_from_disk(cJSON *json, index_t *idx, onion_request *req, onion_response *res) {
const char *path = cJSON_GetObjectItem(json, "path")->valuestring;
const char *name = cJSON_GetObjectItem(json, "name")->valuestring;
@@ -199,23 +314,24 @@ void serve_file_from_disk(cJSON *json, index_t *idx, struct mg_connection *nc, s
const char *mime = cJSON_GetObjectItem(json, "mime")->valuestring;
char full_path[PATH_MAX];
snprintf(full_path, PATH_MAX, "%s%s%s%s%s%s",
idx->desc.root, path, strlen(path) == 0 ? "" : "/",
name, strlen(ext) == 0 ? "" : ".", ext);
LOG_DEBUGF("serve.c", "Serving file from disk: %s", full_path)
snprintf(full_path, PATH_MAX, "%s%s/%s%s%s",
idx->desc.root, path, name, strlen(ext) == 0 ? "" : ".", ext);
char disposition[8196];
snprintf(disposition, sizeof(disposition), "Content-Disposition: inline; filename=\"%s%s%s\"",
snprintf(disposition, sizeof(disposition), "inline; filename=\"%s%s%s\"",
name, strlen(ext) == 0 ? "" : ".", ext);
onion_response_set_header(res, "Content-Disposition", disposition);
mg_http_serve_file(nc, hm, full_path, mg_mk_str(mime), mg_mk_str(disposition));
return chunked_response_file(full_path, mime, 1, req, res);
}
void index_info(struct mg_connection *nc) {
int index_info(void *p, onion_request *req, onion_response *res) {
cJSON *json = cJSON_CreateObject();
cJSON *arr = cJSON_AddArrayToObject(json, "indices");
set_default_headers(res);
onion_response_set_header(res, "Content-Type", "application/json");
for (int i = 0; i < WebCtx.index_count; i++) {
index_t *idx = &WebCtx.indices[i];
@@ -228,224 +344,74 @@ void index_info(struct mg_connection *nc) {
}
char *json_str = cJSON_PrintUnformatted(json);
send_response_line(nc, 200, strlen(json_str), "Content-Type: application/json");
mg_send(nc, json_str, strlen(json_str));
onion_response_write0(res, json_str);
free(json_str);
cJSON_Delete(json);
nc->flags |= MG_F_SEND_AND_CLOSE;
return OCS_PROCESSED;
}
int file(void *p, onion_request *req, onion_response *res) {
void document_info(struct mg_connection *nc, struct http_message *hm, struct mg_str *path) {
if (path->len != UUID_STR_LEN + 2) {
LOG_DEBUGF("serve.c", "Invalid document_info path: %.*s", (int) path->len, path->p)
nc->flags |= MG_F_SEND_AND_CLOSE;
return;
const char *arg_uuid = onion_request_get_query(req, "1");
if (arg_uuid == NULL) {
return OCS_PROCESSED;
}
char arg_uuid[UUID_STR_LEN];
memcpy(arg_uuid, hm->uri.p + 3, UUID_STR_LEN);
*(arg_uuid + UUID_STR_LEN - 1) = '\0';
cJSON *doc = elastic_get_document(arg_uuid);
cJSON *source = cJSON_GetObjectItem(doc, "_source");
cJSON *index_id = cJSON_GetObjectItem(source, "index");
if (index_id == NULL) {
cJSON_Delete(doc);
nc->flags |= MG_F_SEND_AND_CLOSE;
return;
}
index_t *idx = get_index_by_id(index_id->valuestring);
if (idx == NULL) {
cJSON_Delete(doc);
nc->flags |= MG_F_SEND_AND_CLOSE;
return;
}
char *json_str = cJSON_PrintUnformatted(source);
send_response_line(nc, 200, (int) strlen(json_str), "Content-Type: application/json");
mg_send(nc, json_str, (int) strlen(json_str));
free(json_str);
cJSON_Delete(doc);
nc->flags |= MG_F_SEND_AND_CLOSE;
}
void file(struct mg_connection *nc, struct http_message *hm, struct mg_str *path) {
if (path->len != UUID_STR_LEN + 2) {
LOG_DEBUGF("serve.c", "Invalid file path: %.*s", (int) path->len, path->p)
nc->flags |= MG_F_SEND_AND_CLOSE;
return;
}
char arg_uuid[UUID_STR_LEN];
memcpy(arg_uuid, hm->uri.p + 3, UUID_STR_LEN);
*(arg_uuid + UUID_STR_LEN - 1) = '\0';
const char *next = arg_uuid;
cJSON *doc = NULL;
cJSON *index_id = NULL;
cJSON *source = NULL;
while (true) {
doc = elastic_get_document(next);
source = cJSON_GetObjectItem(doc, "_source");
index_id = cJSON_GetObjectItem(source, "index");
if (index_id == NULL) {
cJSON_Delete(doc);
nc->flags |= MG_F_SEND_AND_CLOSE;
return;
}
cJSON *parent = cJSON_GetObjectItem(source, "parent");
if (parent == NULL) {
break;
}
next = parent->valuestring;
return OCS_NOT_PROCESSED;
}
index_t *idx = get_index_by_id(index_id->valuestring);
if (idx == NULL) {
cJSON_Delete(doc);
nc->flags |= MG_F_SEND_AND_CLOSE;
return;
return OCS_NOT_PROCESSED;
}
int ret;
if (strlen(idx->desc.rewrite_url) == 0) {
serve_file_from_disk(source, idx, nc, hm);
ret = serve_file_from_disk(source, idx, req, res);
} else {
serve_file_from_url(source, idx, nc);
ret = serve_file_from_url(source, idx, req, res);
}
cJSON_Delete(doc);
return ret;
}
void status(struct mg_connection *nc) {
char *status = elastic_get_status();
if (strcmp(status, "open") == 0) {
send_response_line(nc, 204, 0, "Content-Type: application/json");
} else {
send_response_line(nc, 500, 0, "Content-Type: application/json");
}
void serve(const char *hostname, const char *port) {
onion *o = onion_new(O_POOL);
onion_set_timeout(o, 3500);
free(status);
onion_set_hostname(o, hostname);
onion_set_port(o, port);
nc->flags |= MG_F_SEND_AND_CLOSE;
}
static void ev_router(struct mg_connection *nc, int ev, void *p) {
struct mg_str scheme;
struct mg_str user_info;
struct mg_str host;
unsigned int port;
struct mg_str path;
struct mg_str query;
struct mg_str fragment;
if (ev == MG_EV_HTTP_REQUEST) {
struct http_message *hm = (struct http_message *) p;
if (mg_parse_uri(hm->uri, &scheme, &user_info, &host, &port, &path, &query, &fragment) != 0) {
nc->flags |= MG_F_SEND_AND_CLOSE;
return;
}
if (WebCtx.auth_enabled == TRUE) {
char user[256] = {0,};
char pass[256] = {0,};
int ret = mg_get_http_basic_auth(hm, user, sizeof(user), pass, sizeof(pass));
if (ret == -1 || strcmp(user, WebCtx.auth_user) != 0 || strcmp(pass, WebCtx.auth_pass) != 0) {
mg_printf(nc, "HTTP/1.1 401 Unauthorized\r\n"
"WWW-Authenticate: Basic realm=\"sist2\"\r\n"
"Content-Length: 0\r\n\r\n");
nc->flags |= MG_F_SEND_AND_CLOSE;
return;
}
}
if (is_equal(&path, &((struct mg_str) MG_MK_STR("/")))) {
search_index(nc);
} else if (is_equal(&path, &((struct mg_str) MG_MK_STR("/css")))) {
style(nc, hm);
} else if (is_equal(&path, &((struct mg_str) MG_MK_STR("/js")))) {
javascript(nc);
} else if (is_equal(&path, &((struct mg_str) MG_MK_STR("/img/sprite-skin-flat.png")))) {
img_sprite_skin_flat(nc, hm);
} else if (is_equal(&path, &((struct mg_str) MG_MK_STR("/es")))) {
search(nc, hm);
} else if (is_equal(&path, &((struct mg_str) MG_MK_STR("/i")))) {
index_info(nc);
} else if (is_equal(&path, &((struct mg_str) MG_MK_STR("/status")))) {
status(nc);
} else if (has_prefix(&path, &((struct mg_str) MG_MK_STR("/f/")))) {
file(nc, hm, &path);
} else if (has_prefix(&path, &((struct mg_str) MG_MK_STR("/t/")))) {
thumbnail(nc, hm, &path);
} else if (has_prefix(&path, &((struct mg_str) MG_MK_STR("/d/")))) {
document_info(nc, hm, &path);
} else {
nc->flags |= MG_F_SEND_AND_CLOSE;
}
} else if (ev == MG_EV_POLL) {
if (nc->user_data != NULL) {
//Waiting for ES reply
subreq_ctx_t *ctx = (subreq_ctx_t *) nc->user_data;
mg_mgr_poll(&ctx->mgr, 0);
if (ctx->ev_data.done == TRUE) {
response_t *r = ctx->ev_data.resp;
if (r->status_code == 200) {
send_response_line(nc, 200, r->size, "Content-Type: application/json");
mg_send(nc, r->body, r->size);
} else if (r->status_code == 0) {
sist_log("serve.c", SIST_ERROR, "Could not connect to elasticsearch!");
} else {
sist_logf("serve.c", SIST_WARNING, "ElasticSearch error during query (%d)", r->status_code);
if (r->size != 0) {
char *tmp = malloc(r->size + 1);
memcpy(tmp, r->body, r->size);
*(tmp + r->size) = '\0';
cJSON *json = cJSON_Parse(tmp);
char *json_str = cJSON_Print(json);
sist_log("serve.c", SIST_WARNING, json_str);
free(json_str);
free(tmp);
}
//todo return error code
}
free_response(r);
nc->flags |= MG_F_SEND_AND_CLOSE;
nc->user_data = NULL;
}
}
}
}
void serve(const char *listen_address) {
printf("Starting web server @ http://%s\n", listen_address);
struct mg_mgr mgr;
mg_mgr_init(&mgr, NULL);
struct mg_connection *nc = mg_bind(&mgr, listen_address, ev_router);
if (nc == NULL) {
LOG_FATALF("serve.c", "Couldn't bind web server on address %s", listen_address)
}
mg_set_protocol_http_websocket(nc);
for (;;) {
mg_mgr_poll(&mgr, 10);
}
onion_url *urls = onion_root_url(o);
// Static paths
onion_url_add(urls, "", search_index);
onion_url_add(urls, "css", style);
onion_url_add(urls, "js", javascript);
onion_url_add(urls, "img/sprite-skin-flat.png", img_sprite_skin_flag);
onion_url_add(urls, "es", search);
onion_url_add(urls, "scroll", scroll);
onion_url_add(
urls,
"^t/([a-fA-F0-9]{8}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{12})/"
"([a-fA-F0-9]{8}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{12})$",
thumbnail
);
onion_url_add(urls, "^f/([a-fA-F0-9]{8}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{12})$", file);
onion_url_add(urls, "i", index_info);
printf("Starting web server @ http://%s:%s\n", hostname, port);
onion_listen(o);
onion_free(o);
}

View File

@@ -3,6 +3,6 @@
#include "src/sist.h"
void serve(const char *listen_address);
void serve(const char *hostname, const char *port);
#endif

File diff suppressed because one or more lines are too long

Submodule third-party/argparse deleted from 4ed6099cb3

1
third-party/libscan vendored

Submodule third-party/libscan deleted from f363659936

View File

@@ -0,0 +1,9 @@
.autocomplete-suggestions {
text-align: left; cursor: default; border: 1px solid #ccc; border-top: 0; background: #fff; box-shadow: -1px 1px 3px rgba(0,0,0,.1);
/* core styles should not be changed */
position: absolute; display: none; z-index: 9999; max-height: 254px; overflow: hidden; overflow-y: auto; box-sizing: border-box;
}
.autocomplete-suggestion { position: relative; padding: 0 .6em; line-height: 23px; white-space: nowrap; overflow: hidden; text-overflow: ellipsis; font-size: 1.02em; color: #333; }
.autocomplete-suggestion b { font-weight: normal; color: #1f8dd6; }
.autocomplete-suggestion.selected { background: #f0f0f0; }

240
web/css/dark.css Normal file
View File

@@ -0,0 +1,240 @@
a {
color: #00BCD4;
}
body {
overflow-y: scroll;
background: black;
}
.progress {
margin-top: 1em;
}
.card {
margin-top: 1em;
background: #212121;
color: #e0e0e0;
}
.navbar-brand {
font-size: 1.75rem;
padding: 0;
color: #f5f5f5;
}
.navbar {
background: #546b7a;
}
.navbar a:hover {
color: #fff;
}
.navbar span {
color: #eee;
}
.document {
padding: 0.5rem;
}
.document p {
margin-bottom: 0;
}
.document:hover p {
text-decoration: underline;
}
.badge-video {
color: #FFFFFF;
background-color: #F27761;
}
.badge-image {
color: #FFFFFF;
background-color: #AA99C9;
}
.badge-audio {
color: #FFFFFF;
background-color: #00ADEF;
}
.badge-resolution {
color: #212529;
background-color: #B0BEC5;
}
.badge-text {
color: #FFFFFF;
background-color: #FAAB3C;
}
.card-img-overlay {
pointer-events: none;
padding: 0.75rem;
bottom: unset;
top: 0;
left: unset;
right: unset;
}
.file-title {
font-size: 10pt;
white-space: nowrap;
text-overflow: ellipsis;
overflow: hidden;
}
.badge {
margin-right: 3px;
}
.fit {
display: block;
min-width: 64px;
max-width: 100%;
max-height: 175px;
margin: 0 auto 0;
padding: 3px 3px 0 3px;
width: auto;
height: auto;
}
.audio-fit {
height: 39px;
vertical-align: bottom;
display: inline;
width: 100%;
}
@media (min-width: 1200px) {
.card-columns {
column-count: 4;
}
}
@media (min-width: 1500px) {
.container {
max-width: 1440px;
}
.card-columns {
column-count: 5;
}
}
@media (min-width: 1800px) {
.container {
max-width: 1550px;
}
}
mark {
background: #fff217;
border-radius: 0;
padding: 1px 0;
}
.content-div {
font-family: SFMono-Regular, Menlo, Monaco, Consolas, "Liberation Mono", "Courier New", monospace;
font-size: 13px;
padding: 1em;
background-color: #37474F;
border: 1px solid #616161;
border-radius: 4px;
margin: 3px;
}
.irs-single, .irs-from, .irs-to {
font-size: 13px;
background-color: #00BCD4;
}
.irs-slider {
cursor: col-resize;
}
.irs {
margin-top: 1em;
margin-bottom: 1em;
}
.custom-select {
overflow: auto;
background-color: #37474F;
border: 1px solid #616161;
color: #bdbdbd;
}
.custom-select:focus {
border-color: #757575;
outline: 0;
box-shadow: 0 0 0 .2rem rgba(0, 123, 255, .25);
}
option {
outline: none;
}
.form-control {
background-color: #37474F;
border: 1px solid #616161;
color: #fff;
}
.form-control:focus {
background-color: #546E7A;
color: #fff;
}
.input-group-text {
background: #263238;
border: 1px solid #616161;
color: #dbdbdb;
}
::placeholder {
color: #BDBDBD !important;
opacity: 1;
}
.inspire-tree .selected > .wholerow, .inspire-tree .selected > .title-wrap:hover + .wholerow {
background: none;
}
.inspire-tree .icon-expand::before, .inspire-tree .icon-collapse::before {
background-color: black;
}
.inspire-tree .title {
color: #eee;
}
.inspire-tree {
font-weight: 400;
font-size: 14px;
font-family: Helvetica, Nueue, Verdana, sans-serif;
max-height: 350px;
overflow: auto;
}
.page-indicator {
line-height: 1rem;
padding: 0.5rem;
background: #212121;
color: #eee;
}
.btn-xs {
padding: .1rem .3rem;
font-size: .875rem;
border-radius: .2rem;
}
.btn {
color: #eee;
}

170
web/css/light.css Normal file
View File

@@ -0,0 +1,170 @@
body {overflow-y:scroll;}
.progress {
margin-top: 1em;
}
.card {
margin-top: 1em;
}
.navbar-brand {
font-size: 1.75rem;
padding: 0;
}
.navbar {
background: #F7F7F7; border-bottom: solid 1px #dfdfdf;
}
.document {
padding: 0.5rem;
}
.document p {
margin-bottom: 0;
}
.document:hover p {
text-decoration: underline;
}
.badge-video {
color: #FFFFFF;
background-color: #F27761;
}
.badge-image {
color: #FFFFFF;
background-color: #AA99C9;
}
.badge-audio {
color: #FFFFFF;
background-color: #00ADEF;
}
.badge-resolution {
color: #212529;
background-color: #FFC107;
}
.badge-text {
color: #FFFFFF;
background-color: #FAAB3C;
}
.card-img-overlay {
pointer-events: none;
padding: 0.75rem;
bottom: unset;
top: 0;
left: unset;
right: unset;
}
.file-title {
font-size: 10pt;
white-space: nowrap;
text-overflow: ellipsis;
overflow: hidden;
}
.badge {
margin-right: 3px;
}
.fit {
display: block;
min-width: 64px;
max-width: 100%;
max-height: 175px;
margin: 0 auto 0;
padding: 3px 3px 0 3px;
width: auto;
height: auto;
}
.audio-fit {
height: 39px;
vertical-align: bottom;
display: inline;
width: 100%;
}
@media (min-width: 1200px) {
.card-columns {
column-count: 4;
}
}
@media (min-width: 1500px) {
.container {
max-width: 1440px;
}
.card-columns {
column-count: 5;
}
}
@media (min-width: 1800px) {
.container {
max-width: 1550px;
}
}
mark {
background: #fff217;
border-radius: 0;
padding: 1px 0;
}
.content-div {
font-family: SFMono-Regular,Menlo,Monaco,Consolas,"Liberation Mono","Courier New",monospace;
font-size: 13px;
padding: 1em;
background-color: #f5f5f5;
border: 1px solid #ccc;
border-radius: 4px;
margin: 3px;
}
.irs-single, .irs-from, .irs-to {
font-size: 13px;
}
.irs-slider {
cursor: col-resize;
}
.custom-select {
overflow: auto;
}
.irs {
margin-top: 1em;
margin-bottom: 1em;
}
.inspire-tree .selected > .wholerow, .inspire-tree .selected > .title-wrap:hover + .wholerow
{
background: none;
}
.inspire-tree {
font-weight: 400;
font-size: 14px;
font-family: Helvetica, Nueue, Verdana, sans-serif;
max-height: 350px;
overflow: auto;
}
.page-indicator {
line-height: 1rem;
padding: 0.5rem;
background: #212121;
}
.btn-xs {
padding: .1rem .3rem;
font-size: .875rem;
border-radius: .2rem;
}

View File

Before

Width:  |  Height:  |  Size: 595 B

After

Width:  |  Height:  |  Size: 595 B

View File

Before

Width:  |  Height:  |  Size: 669 B

After

Width:  |  Height:  |  Size: 669 B

Some files were not shown because too many files have changed in this diff Show More