Fix #521

Update README.md

.dockerignore

@@ -0,0 +1,43 @@
+.idea/
+*.sist2
+docs/
+test_i/
+test_i_inc/
+Testing/
+.drone.yml
+**/cmake_install.cmake
+**/CMakeCache.txt
+**/CMakeFiles/
+.cmake
+LICENSE
+Makefile
+**/*.md
+**/*.cbp
+VERSION
+**/node_modules/
+sist2-*-linux-debug
+sist2-*-linux
+sist2_debug
+sist2
+**/libscan-test-files
+**/scan_ub_test
+**/scan_a_test
+**/scan_test
+**/ext_ffmpeg
+**/ext_libmobi
+**/ext_libwpd
+**/core
+*.a
+tmp_scan/
+Dockerfile
+Dockerfile.arm64
+docker-compose.yml
+state.db
+*-journal
+build/
+__pycache__/
+sist2-vue/dist
+sist2-admin/frontend/dist
+*.fts
+.git
+third-party/libscan/third-party/ext_*/*

.drone.yml

@@ -0,0 +1,108 @@
+kind: pipeline
+type: docker
+name: amd64
+
+platform:
+  os: linux
+  arch: amd64
+
+steps:
+  - name: submodules
+    image: alpine/git
+    commands:
+      - git submodule update --init --recursive
+  - name: docker
+    image: plugins/docker
+    depends_on:
+      - submodules
+    settings:
+      username:
+        from_secret: DOCKER_USER
+      password:
+        from_secret: DOCKER_PASSWORD
+      repo: sist2app/sist2
+      context: ./
+      dockerfile: ./Dockerfile
+      auto_tag: true
+      auto_tag_suffix: x64-linux
+      when:
+        event:
+          - tag
+  - name: build
+    image: sist2app/sist2-build
+    depends_on:
+    - submodules
+    commands:
+      - ./scripts/build.sh
+  - name: scp files
+    depends_on:
+      - build
+    image: appleboy/drone-scp
+    settings:
+      host:
+        from_secret: SSH_HOST
+      port:
+        from_secret: SSH_PORT
+      user:
+        from_secret: SSH_USER
+      key:
+        from_secret: SSH_KEY
+      target: ~/files/sist2/${DRONE_REPO_OWNER}_${DRONE_REPO_NAME}/${DRONE_BRANCH}_${DRONE_BUILD_NUMBER}_${DRONE_COMMIT}/
+      source:
+        - ./VERSION
+        - ./sist2-x64-linux
+        - ./sist2-x64-linux-debug
+
+---
+kind: pipeline
+type: docker
+name: arm64
+
+platform:
+  arch: arm64
+
+steps:
+  - name: submodules
+    image: alpine/git
+    commands:
+      - git submodule update --init --recursive
+  - name: docker
+    image: plugins/docker
+    depends_on:
+      - submodules
+    settings:
+      username:
+        from_secret: DOCKER_USER
+      password:
+        from_secret: DOCKER_PASSWORD
+      repo: sist2app/sist2
+      context: ./
+      dockerfile: ./Dockerfile.arm64
+      auto_tag: true
+      auto_tag_suffix: arm64-linux
+      when:
+        event:
+          - tag
+  - name: build
+    image: sist2app/sist2-build-arm64
+    depends_on:
+      - submodules
+    commands:
+      - ./scripts/build_arm64.sh
+  - name: scp files
+    depends_on:
+      - build
+    image: appleboy/drone-scp
+    settings:
+      host:
+        from_secret: SSH_HOST
+      port:
+        from_secret: SSH_PORT
+      user:
+        from_secret: SSH_USER
+      key:
+        from_secret: SSH_KEY
+      target: ~/files/sist2/${DRONE_REPO_OWNER}_${DRONE_REPO_NAME}/arm_${DRONE_BRANCH}_${DRONE_BUILD_NUMBER}_${DRONE_COMMIT}/
+      source:
+        - ./sist2-arm64-linux
+        - ./sist2-arm64-linux-debug

.gitattributes

@@ -1,3 +0,0 @@
-CMakeModules/* linguist-vendored
-web/js/*.min.js linguist-vendored
-web/css/*.min.css linguist-vendored

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,40 @@
+---
+name: "🐞 Bug Report"
+about: Submit a bug report 
+title: ''
+labels: bug
+assignees: ''
+
+---
+
+**Device Information (please complete the following information):**
+ - OS: `[e.g., Ubuntu 20.04, WSL2]`
+ - Deployment: `[Linux, Linux ARM64 or Docker]`
+ - Browser *(if relevant)*: `[e.g., chrome, safari]`
+ - SIST2 Version: `[e.g., v2.9.0]`
+ - Elasticsearch Version *(if relevant)* : ``
+
+**Command with arguments** 
+<!-- `ex: "scan ~/Documents -o ./i2 --threads 3 -q 1.0` -->
+
+**Describe the bug**
+<!-- A clear and concise description of what the bug is. -->
+
+**Steps To Reproduce**
+Please be specific!
+1. Go to '...'
+2. Click on '....'
+3. etc.
+
+**Expected behavior**
+<!-- A clear and concise description of what you expected to happen. -->
+
+**Actual Behavior**
+<!-- A clear and concise description of what actually happens. -->
+
+**Screenshots**
+<!-- If applicable, add screenshots to help explain your problem. -->
+
+**Additional context**
+<!-- Add any other context about the problem here. If applicable, please include why you think the bug is occurring and/or troubleshooting you have already performed. -->
+<!-- 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. -->

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,5 @@
+blank_issues_enabled: false
+contact_links:
+  - name: SIST2 Documentation
+    url: https://github.com/simon987/sist2/blob/master/docs/USAGE.md
+    about: Check out the SIST2 documentation for answers to common questions

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,18 @@
+---
+name: "🚀 Feature Request"
+about: Suggest an idea for SIST2
+title: ''
+assignees: ''
+
+---
+**Which SIST2 component is your Feature Request related to?**
+<!-- e.g., Scan, Index, or Web? -->
+
+**Is your feature request related to a problem? Please describe.**
+<!-- A clear and concise description of what the problem is. e.g., "I'm always frustrated when [...]" -->
+
+**What would you like to see happen?**
+<!-- A clear and concise description of what you want to happen. -->
+
+**Additional context**
+<!-- Add any other context or screenshots about the feature request here. -->

.github/ISSUE_TEMPLATE/issue-template.md

@@ -0,0 +1,18 @@
+---
+name: Issue template
+about: General
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+sist2 version:
+
+Platform (Linux or Docker, x86-64 or arm64):
+
+Elasticsearch version:
+
+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.

.gitignore

@@ -1,18 +1,49 @@
 .idea
 thumbs
-test
 *.cbp
 CMakeCache.txt
 CMakeFiles
+cmake-build-default-event-trace
 cmake-build-debug
 cmake_install.cmake
 Makefile
 *.out
 LOG
 sist2*
-index.sist2/
+!sist2-vue/
+!sist2-admin
+!sist2_admin
+!sist2.py
+*.sist2/
 bundle*.css
 bundle.js
 *.a
 vgcore.*
 build/
+third-party/argparse
+*.idx/
+VERSION
+git_hash.h
+Testing/
+test_i
+test_i_inc
+node_modules/
+.cmake/
+i_inc/
+state.db
+*.pyc
+!sist2-admin/frontend/dist
+*.js.map
+sist2-vue/dist
+sist2-admin/frontend/dist
+.ninja_deps
+.ninja_log
+build.ninja
+src/web/static_generated.c
+src/magic_generated.c
+src/index/static_generated.c
+*.sist2
+*-shm
+*-journal
+.vscode
+*.fts

.gitmodules

@@ -1,45 +1,15 @@
-[submodule "argparse"]
-	path = argparse
-	url = https://github.com/cofyc/argparse
-[submodule "cJSON"]
-	path = cJSON
-	url = https://github.com/DaveGamble/cJSON
-[submodule "lmdb"]
-	path = lmdb
-	url = https://github.com/LMDB/lmdb
-[submodule "utf8.h"]
-	path = utf8.h
+[submodule "third-party/argparse"]
+	path = third-party/argparse
+	url = https://github.com/simon987/argparse
+[submodule "third-party/libscan/third-party/utf8.h"]
+	path = third-party/libscan/third-party/utf8.h
 	url = https://github.com/sheredom/utf8.h
-[submodule "lib/bzip2-1.0.6"]
-	path = lib/bzip2-1.0.6
-	url = https://github.com/enthought/bzip2-1.0.6
-[submodule "lib/libmagic"]
-	path = lib/libmagic
-	url = https://github.com/threatstack/libmagic
-[submodule "lib/harfbuzz"]
-	path = lib/harfbuzz
-	url = https://github.com/harfbuzz/harfbuzz
-[submodule "lib/openjpeg"]
-	path = lib/openjpeg
-	url = https://github.com/uclouvain/openjpeg
-[submodule "lib/ffmpeg"]
-	path = lib/ffmpeg
-	url = https://git.ffmpeg.org/ffmpeg.git
-[submodule "lib/onion"]
-	path = lib/onion
-	url = https://github.com/davidmoreno/onion
-[submodule "lib/mupdf"]
-	path = lib/mupdf
-	url = git://git.ghostscript.com/mupdf.git
-[submodule "lib/tesseract"]
-	path = lib/tesseract
-	url = https://github.com/tesseract-ocr/tesseract
-[submodule "lib/leptonica"]
-	path = lib/leptonica
-	url = https://github.com/danbloomberg/leptonica
-[submodule "lib/libtiff"]
-	path = lib/libtiff
-	url = https://gitlab.com/libtiff/libtiff
-[submodule "lib/libpng"]
-	path = lib/libpng
-	url = https://github.com/glennrp/libpng
+[submodule "third-party/libscan/third-party/antiword"]
+	path = third-party/libscan/third-party/antiword
+	url = https://github.com/simon987/antiword
+[submodule "third-party/libscan/third-party/libmobi"]
+	path = third-party/libscan/third-party/libmobi
+	url = https://github.com/bfabiszewski/libmobi
+[submodule "third-party/libscan/libscan-test-files"]
+	path = third-party/libscan/libscan-test-files
+	url = https://github.com/simon987/libscan-test-files

.teamcity/settings.kts

@@ -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"
-})

CMakeLists.txt

@@ -1,141 +1,165 @@
 cmake_minimum_required(VERSION 3.7)
+
+project(sist2)
 set(CMAKE_C_STANDARD 11)
 
-option(CURL_STATIC "Link to curl statically" on)
+option(SIST_DEBUG "Build a debug executable" on)
+option(SIST_FAST "Enable more optimisation flags" off)
+option(SIST_DEBUG_INFO "Turn on debug information in web interface" on)
 
-project(sist2 C)
-list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_LIST_DIR}/CMakeModules")
+add_compile_definitions(
+        "SIST_PLATFORM=${SIST_PLATFORM}"
+)
+
+if (SIST_DEBUG)
+    add_compile_definitions(
+            "SIST_DEBUG=${SIST_DEBUG}"
+    )
+    set(VCPKG_BUILD_TYPE debug)
+else ()
+    set(VCPKG_BUILD_TYPE release)
+endif ()
+
+if (SIST_DEBUG_INFO)
+    add_compile_definitions(
+            "SIST_DEBUG_INFO=${SIST_DEBUG_INFO}"
+    )
+endif ()
+
+
+add_subdirectory(third-party/libscan)
+set(ARGPARSE_SHARED off)
+add_subdirectory(third-party/argparse)
 
 add_executable(
         sist2
+        # argparse
+        third-party/argparse/argparse.h third-party/argparse/argparse.c
+
         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/parsing/magic_util.c src/parsing/magic_util.h
         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/web/auth_basic.h src/web/auth_basic.c
+        src/web/web_util.c src/web/web_util.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
-        src/parsing/arc.c src/parsing/arc.h
-        src/parsing/doc.c src/parsing/doc.h
+        src/ctx.c src/ctx.h
+        src/types.h
         src/log.c src/log.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
+        src/database/database.c src/database/database.h
+        src/parsing/fs_util.h
 
-        # utf8.h
-        utf8.h/utf8.h
-)
+        src/auth0/auth0_c_api.h src/auth0/auth0_c_api.cpp
+
+        src/database/database_stats.c
+        src/database/database_schema.c
+        src/database/database_fts.c
+        src/web/web_fts.c
+        src/database/database_embeddings.c)
+set_target_properties(sist2 PROPERTIES LINKER_LANGUAGE C)
+
+target_link_directories(sist2 PRIVATE BEFORE ${_VCPKG_INSTALLED_DIR}/${VCPKG_TARGET_TRIPLET}/lib/)
+set(CMAKE_FIND_LIBRARY_SUFFIXES .a .lib)
 
 find_package(PkgConfig REQUIRED)
-set(ENV{PKG_CONFIG_PATH} "$ENV{PKG_CONFIG_PATH}:/usr/local/lib/pkgconfig/")
 
-find_package(Freetype REQUIRED)
+find_package(cJSON CONFIG REQUIRED)
+find_package(unofficial-mongoose CONFIG REQUIRED)
+find_package(CURL CONFIG REQUIRED)
+find_library(MAGIC_LIB NAMES libmagic.a REQUIRED)
+find_package(unofficial-sqlite3 CONFIG REQUIRED)
+find_package(OpenBLAS CONFIG 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(${UUID_CFLAGS_OTHER})
-add_definitions(${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)
 
 target_include_directories(
         sist2 PUBLIC
-        ${GOBJECT_INCLUDE_DIRS}
-        ${GLIB_INCLUDE_DIRS}
-        ${PROJECT_SOURCE_DIR}/lib/ffmpeg/
-        ${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/
-        ${PROJECT_SOURCE_DIR}/include/
-        /usr/include/libxml2/
-        ${PROJECT_SOURCE_DIR}/lib/tesseract/include/
-)
-target_link_directories(
-        sist2 PUBLIC
-        ${UUID_LIBRARY_DIRS}
+        ${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
+target_compile_options(
+        sist2
         PRIVATE
+        -fPIC
+)
+
+if (SIST_DEBUG)
+    target_compile_options(
+            sist2
+            PRIVATE
+            -g
+            -fstack-protector
+            -fno-omit-frame-pointer
+            -fsanitize=address
+            -fno-inline
+            #            -O2
+    )
+    target_link_options(
+            sist2
+            PRIVATE
+            -fsanitize=address
+            -static-libasan
+    )
+    set_target_properties(
+            sist2
+            PROPERTIES
+            OUTPUT_NAME sist2_debug
+    )
+elseif (SIST_FAST)
+    target_compile_options(
+            sist2
+            PRIVATE
+
             -Ofast
             -march=native
-        -fPIC
             -fno-stack-protector
             -fomit-frame-pointer
+            -freciprocal-math
     )
+else ()
+    target_compile_options(
+            sist2
+            PRIVATE
 
-TARGET_LINK_LIBRARIES(
+            -Ofast
+#            -g
+            -fno-stack-protector
+            -fomit-frame-pointer
+            -w
+    )
+endif ()
+
+add_dependencies(
+        sist2
+        scan
+        argparse
+)
+
+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
-
-        # mupdf
-        ${PROJECT_SOURCE_DIR}/lib/libmupdf.a
-        ${PROJECT_SOURCE_DIR}/lib/libmupdf-third.a
-
-        # onion
-        ${PROJECT_SOURCE_DIR}/lib/libonion_static.a
+        m
+        z
+        argparse
+        unofficial::mongoose::mongoose
+        CURL::libcurl
 
         pthread
 
-        # curl
-        ${PROJECT_SOURCE_DIR}/lib/libcurl.a
-        ssl crypto
+        scan
 
-        m
-        bz2
-        ${PROJECT_SOURCE_DIR}/lib/libmagic.a
-        ${PROJECT_SOURCE_DIR}/lib/libharfbuzz.a
-        ${PROJECT_SOURCE_DIR}/lib/libopenjp2.a
-        freetype
-        archive
-
-        xml2
-        ${PROJECT_SOURCE_DIR}/lib/libopc/libmce.a
-        ${PROJECT_SOURCE_DIR}/lib/libopc/libopc.a
-        ${PROJECT_SOURCE_DIR}/lib/libopc/libplib.a
-
-        ${PROJECT_SOURCE_DIR}/lib/libtesseract.a
-        ${PROJECT_SOURCE_DIR}/lib/liblept.a
-        ${PROJECT_SOURCE_DIR}/lib/libtiff.a
-        ${PROJECT_SOURCE_DIR}/lib/libpng16.a
-        stdc++
+        ${MAGIC_LIB}
+        unofficial::sqlite3::sqlite3
+        OpenBLAS::OpenBLAS
 )
 
 add_custom_target(

CMakeModules/FindFFmpeg.cmake

@@ -1,80 +0,0 @@
-# - 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)
-
-

CMakeModules/FindLibMagic.cmake

@@ -1,100 +0,0 @@
-
-#-------------------------------------------------------------------------------
-# 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)

CMakeModules/FindOpenSSL.cmake

@@ -1,478 +0,0 @@
-# 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()

CMakeModules/FindPackageHandleStandardArgs.cmake

@@ -1,268 +0,0 @@
-# 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()

CMakeModules/FindPackageMessage.cmake

@@ -1,48 +0,0 @@
-# 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()

Docker/Dockerfile

@@ -1,19 +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
-
-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
-
-ENTRYPOINT ["/root/sist2"]

Docker/build.sh

@@ -1,10 +0,0 @@
-rm ./sist2
-cp ../sist2 .
-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

Dockerfile

@@ -0,0 +1,52 @@
+FROM sist2app/sist2-build as build
+
+WORKDIR /build/
+
+COPY scripts scripts
+COPY schema schema
+COPY CMakeLists.txt .
+COPY third-party third-party
+COPY src src
+COPY sist2-vue sist2-vue
+COPY sist2-admin sist2-admin
+
+RUN cd sist2-vue/ && npm install && npm run build
+RUN cd sist2-admin/frontend/ && npm install && npm run build
+
+RUN mkdir build && cd build && cmake -DSIST_PLATFORM=x64_linux_docker -DSIST_DEBUG_INFO=on -DSIST_DEBUG=off -DBUILD_TESTS=off -DCMAKE_TOOLCHAIN_FILE=/vcpkg/scripts/buildsystems/vcpkg.cmake ..
+RUN cd build && make -j$(nproc)
+RUN strip build/sist2 || mv build/sist2_debug build/sist2
+
+FROM --platform="linux/amd64" ubuntu@sha256:965fbcae990b0467ed5657caceaec165018ef44a4d2d46c7cdea80a9dff0d1ea
+
+ENV LANG C.UTF-8
+ENV LC_ALL C.UTF-8
+
+ENTRYPOINT ["/root/sist2"]
+
+RUN apt update && DEBIAN_FRONTEND=noninteractive apt install -y curl libasan5 libmagic1 python3  \
+    python3-pip git tesseract-ocr && rm -rf /var/lib/apt/lists/*
+
+RUN mkdir -p /usr/share/tessdata && \
+    cd /usr/share/tessdata/ && \
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/hin.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/hin.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/jpn.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/jpn.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/eng.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/eng.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/fra.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/fra.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/rus.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/rus.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/osd.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/osd.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/spa.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/spa.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/deu.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/deu.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/equ.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/equ.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/pol.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/pol.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/chi_sim.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/chi_sim.traineddata
+
+# sist2
+COPY --from=build /build/build/sist2 /root/sist2
+
+# sist2-admin
+WORKDIR /root/sist2-admin
+COPY sist2-admin/requirements.txt /root/sist2-admin/
+RUN ln /usr/bin/python3 /usr/bin/python
+RUN python -m pip install --no-cache -r /root/sist2-admin/requirements.txt
+COPY --from=build /build/sist2-admin/ /root/sist2-admin/

Dockerfile.arm64

@@ -0,0 +1,53 @@
+FROM sist2app/sist2-build-arm64 as build
+
+WORKDIR /build/
+
+COPY scripts scripts
+COPY schema schema
+COPY CMakeLists.txt .
+COPY third-party third-party
+COPY src src
+COPY sist2-vue sist2-vue
+COPY sist2-admin sist2-admin
+
+RUN cd sist2-vue/ && npm install && npm run build
+RUN cd sist2-admin/frontend/ && npm install && npm run build
+
+WORKDIR /build/
+ADD . /build/
+RUN mkdir build && cd build && cmake -DSIST_PLATFORM=arm64_linux_docker -DSIST_DEBUG_INFO=on -DSIST_DEBUG=off -DBUILD_TESTS=off -DCMAKE_TOOLCHAIN_FILE=/vcpkg/scripts/buildsystems/vcpkg.cmake ..
+RUN cd build && make -j$(nproc)
+RUN strip build/sist2 || mv build/sist2_debug build/sist2
+
+FROM --platform=linux/arm64/v8 ubuntu@sha256:537da24818633b45fcb65e5285a68c3ec1f3db25f5ae5476a7757bc8dfae92a3
+
+WORKDIR /root
+
+ENV LANG C.UTF-8
+ENV LC_ALL C.UTF-8
+
+ENTRYPOINT ["/root/sist2"]
+
+RUN apt update && apt install -y curl libasan5 libmagic1 tesseract-ocr python3-pip python3 git && rm -rf /var/lib/apt/lists/*
+
+RUN mkdir -p /usr/share/tessdata && \
+    cd /usr/share/tessdata/ && \
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/hin.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/hin.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/jpn.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/jpn.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/eng.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/eng.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/fra.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/fra.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/rus.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/rus.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/osd.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/osd.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/spa.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/spa.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/deu.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/deu.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/equ.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/equ.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/pol.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/pol.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/chi_sim.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/chi_sim.traineddata
+
+# sist2
+COPY --from=build /build/build/sist2 /root/sist2
+
+# sist2-admin
+COPY sist2-admin/requirements.txt sist2-admin/
+RUN python3 -m pip install --no-cache -r sist2-admin/requirements.txt
+COPY --from=build /build/sist2-admin/ sist2-admin/

README.md

@@ -1,6 +1,10 @@
-![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/)
+![GitHub](https://img.shields.io/github/license/sist2app/sist2.svg)
+[![CodeFactor](https://www.codefactor.io/repository/github/sist2app/sist2/badge?s=05daa325188aac4eae32c786f3d9cf4e0593f822)](https://www.codefactor.io/repository/github/sist2app/sist2)
+[![Development snapshots](https://ci.simon987.net/api/badges/simon987/sist2/status.svg)](https://files.simon987.net/.gate/sist2/simon987_sist2/)
+
+**Demo**: [sist2.simon987.net](https://sist2.simon987.net/)
+
+**Community URL:** [Discord](https://discord.gg/2PEjDy3Rfs)
 
 # sist2
 
@@ -8,148 +12,218 @@ sist2 (Simple incremental search tool)
 
 *Warning: sist2 is in early development*
 
+![search panel](docs/sist2.gif)
+
 ## Features
 
 * Fast, low memory usage, multi-threaded
-* Portable (all its features are packaged in a single executable)
-* Extracts text from common file types \*
+* Manage & schedule scan jobs with simple web interface (Docker only)
+* Mobile-friendly Web interface
+* Extracts text and metadata from common file types \*
 * Generates thumbnails \*
 * Incremental scanning
-* Automatic tagging from file attributes via [user scripts](scripting/README.md)
+* Manual tagging from the UI and automatic tagging based on file attributes via [user scripts](docs/scripting.md)
 * Recursive scan inside archive files \*\*
 * OCR support with tesseract \*\*\*
-
+* Stats page & disk utilisation visualization
+* Named-entity recognition (client-side) \*\*\*\*
 
 \* See [format support](#format-support)    
 \*\* See [Archive files](#archive-files)    
 \*\*\* See [OCR](#ocr)    
+\*\*\*\* See [Named-Entity Recognition](#NER)
 
 ## Getting Started
 
-1. Have an [Elasticsearch](https://www.elastic.co/downloads/elasticsearch) instance running
-1. 
-    1. Download the [latest sist2 release](https://github.com/simon987/sist2/releases) *
-    1. *(or)* Download an [development snapshot](https://files.simon987.net/artifacts/Sist2/Build/) *(Not recommended!)*
-    1. *(or)* `docker pull simon987/sist2:latest`
+### Using Docker Compose *(Windows/Linux/Mac)*
 
-
-\* *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 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
+```yaml
+services:
+  elasticsearch:
+    image: elasticsearch:7.17.9
+    restart: unless-stopped
+    volumes:
+      # This directory must have 1000:1000 permissions (or update PUID & PGID below)
+      - /data/sist2-es-data/:/usr/share/elasticsearch/data
+    environment:
+      - "discovery.type=single-node"
+      - "ES_JAVA_OPTS=-Xms2g -Xmx2g"
+      - "PUID=1000"
+      - "PGID=1000"
+  sist2-admin:
+    image: sist2app/sist2:x64-linux
+    restart: unless-stopped
+    volumes:
+      - /data/sist2-admin-data/:/sist2-admin/
+      - /<path to index>/:/host
+    ports:
+      - 4090:4090
+      # NOTE: Don't expose this port publicly!
+      - 8080:8080
+    working_dir: /root/sist2-admin/
+    entrypoint: python3
+    command:
+      - /root/sist2-admin/sist2_admin/app.py
 ```
 
-**Push index to Elasticsearch or file**
-```bash
-sist2 index --force-reset ./my_idx
-sist2 index --print ./my_idx > raw_documents.ndjson
-```
+Navigate to http://localhost:8080/ to configure sist2-admin.
 
-**Start web interface**
-```bash
-sist2 web --bind 0.0.0.0 --port 4321 ./my_idx1 ./my_idx2 ./my_idx3
-```
+### Using the executable file *(Linux/WSL only)*
 
-### Use sist2 with docker
+1. Choose search backend (See [comparison](#search-backends)):
+    * **Elasticsearch**: have an Elasticsearch (version >= 6.8.X, ideally >=7.14.0) instance running
+        1. Download [from official website](https://www.elastic.co/downloads/elasticsearch)
+        2. *(or)* Run using docker:
+            ```bash
+            docker run -d -p 9200:9200 -e "discovery.type=single-node" elasticsearch:7.17.9
+            ```
+    * **SQLite**: No installation required
 
-**scan**
-```bash
-docker run -it \
-    -v /path/to/files/:/files \
-    -v $PWD/out/:/out \
-    simon987/sist2 scan -t 4 /files -o /out/my_idx1
-```
-**index**
-```bash
-docker run -it --network host\
-    -v $PWD/out/:/out \
-    simon987/sist2 index /out/my_idx1
-```
+2. Download the [latest sist2 release](https://github.com/sist2app/sist2/releases).
+   Select the file corresponding to your CPU architecture and mark the binary as executable with `chmod +x`.
+3. See [usage guide](docs/USAGE.md) for command line usage.
 
-**web**
-```bash
-docker run --rm --network host -d --name sist2\
-    -v $PWD/out/my_idx:/idx \
-    -v $PWD/my/files:/files
-    simon987/sist2 web --bind 0.0.0.0 /idx
-docker stop sist2
-```
+Example usage:
 
+1. Scan a directory: `sist2 scan ~/Documents --output ./documents.sist2`
+2. Prepare search index:
+    * **Elasticsearch**: `sist2 index --es-url http://localhost:9200 ./documents.sist2`
+    * **SQLite**: `sist2 sqlite-index --search-index ./search.sist2 ./documents.sist2`
+3. Start web interface: 
+   * **Elasticsearch**: `sist2 web ./documents.sist2`
+   * **SQLite**: `sist2 web --search-index ./search.sist2 ./documents.sist2`
 
 ## Format support
 
-File type | Library | Content | Thumbnail | Metadata
-:---|:---|:---|:---|:---
-pdf,xps,cbz,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` | `EXIF:Artist`, `EXIF:ImageDescription` |
-ttf,ttc,cff,woff,fnt,otf | Freetype2 | - | yes, `bmp` | Name & style |
-`text/plain` | *(none)* | yes | no | - |
-tar, zip, rar, 7z, ar ...  | Libarchive | yes\* | - | no |
-docx, xlsx, pptx | libOPC | yes | no | no |
+| File type                                                                 | Library                                                                      | Content  | Thumbnail   | Metadata                                                                                                                               |
+|:--------------------------------------------------------------------------|:-----------------------------------------------------------------------------|:---------|:------------|:---------------------------------------------------------------------------------------------------------------------------------------|
+| pdf,xps,fb2,epub                                                          | MuPDF                                                                        | text+ocr | yes         | author, title                                                                                                                          |
+| cbz,cbr                                                                   | [libscan](https://github.com/sist2app/sist2/tree/master/third-party/libscan) | -        | yes         | -                                                                                                                                      |
+| `audio/*`                                                                 | ffmpeg                                                                       | -        | yes         | ID3 tags                                                                                                                               |
+| `video/*`                                                                 | ffmpeg                                                                       | -        | yes         | title, comment, artist                                                                                                                 |
+| `image/*`                                                                 | ffmpeg                                                                       | ocr      | yes         | [Common EXIF tags](https://github.com/sist2app/sist2/blob/efdde2734eca9b14a54f84568863b7ffd59bdba3/src/parsing/media.c#L190), GPS tags |
+| raw, rw2, dng, cr2, crw, dcr, k25, kdc, mrw, pef, xf3, arw, sr2, srf, erf | LibRaw                                                                       | no       | yes         | Common EXIF tags, GPS tags                                                                                                             |
+| ttf,ttc,cff,woff,fnt,otf                                                  | Freetype2                                                                    | -        | yes, `bmp`  | Name & style                                                                                                                           |
+| `text/plain`                                                              | [libscan](https://github.com/sist2app/sist2/tree/master/third-party/libscan) | yes      | no          | -                                                                                                                                      |
+| html, xml                                                                 | [libscan](https://github.com/sist2app/sist2/tree/master/third-party/libscan) | yes      | no          | -                                                                                                                                      |
+| tar, zip, rar, 7z, ar ...                                                 | Libarchive                                                                   | yes\*    | -           | no                                                                                                                                     |
+| docx, xlsx, pptx                                                          | [libscan](https://github.com/sist2app/sist2/tree/master/third-party/libscan) | yes      | if embedded | creator, modified_by, title                                                                                                            |
+| doc (MS Word 97-2003)                                                     | antiword                                                                     | yes      | no          | author, title                                                                                                                          |
+| mobi, azw, azw3                                                           | libmobi                                                                      | yes      | yes         | author, title                                                                                                                          |
+| wpd (WordPerfect)                                                         | libwpd                                                                       | yes      | no          | *planned*                                                                                                                              |
+| json, jsonl, ndjson                                                       | [libscan](https://github.com/sist2app/sist2/tree/master/third-party/libscan) | yes      | -           | -                                                                                                                                      |
 
 \* *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)
+
+**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.
+
+* Support for parsing media files with formats that require *seek* (e.g. `.gif`, `.mp4` w/ fragmented metadata etc.)
+  is limitted (see `--mem-buffer` option)
 * 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 -`
- 
+  **sist2** is not I/O bound, scans might be faster when larger archives are split into smaller parts.
 
 ### OCR
 
-You can enable OCR support for pdf,xps,cbz,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).
+You can enable OCR support for ebook (pdf,xps,fb2,epub) or image file types with the
+`--ocr-lang <lang>` option in combination with `--ocr-images` and/or `--ocr-ebooks`.
+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` github image comes with common languages 
-(hin, jpn, eng, fra, rus, spa) pre-installed.
+The `sist2app/sist2` image comes with common languages
+(hin, jpn, eng, fra, rus, spa, chi_sim, deu, pol) pre-installed.
+
+You can use the `+` separator to specify multiple languages. The language
+name must be identical to the `*.traineddata` file installed on your system
+(use `chi_sim` rather than `chi-sim`).
+
+Examples:
 
-Examples
 ```bash
-sist2 scan --ocr jpn ~/Books/Manga/
-sist2 scan --ocr eng ~/Books/Textbooks/
+sist2 scan --ocr-ebooks --ocr-lang jpn ~/Books/Manga/
+sist2 scan --ocr-images --ocr-lang eng ~/Images/Screenshots/
+sist2 scan --ocr-ebooks --ocr-images --ocr-lang eng+chi_sim ~/Chinese-Bilingual/
 ```
 
+### Search backends
+
+sist2 v3.0.7+ supports SQLite search backend. The SQLite search backend has
+fewer features and generally comparable query performance for medium-size
+indices, but it uses much less memory and is easier to set up.
+
+|                                              |                       SQLite                        |                                                             Elasticsearch                                                             |
+|----------------------------------------------|:---------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------------------------:|
+| Requires separate search engine installation |                                                     |                                                                   ✓                                                                   |
+| Memory footprint                             |                        ~20MB                        |                                                                >500MB                                                                 |
+| Query syntax                                 |      [fts5](https://www.sqlite.org/fts5.html)       | [query_string](https://www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl-query-string-query.html#query-string-syntax) |
+| Fuzzy search                                 |                                                     |                                                                   ✓                                                                   |
+| Media Types tree real-time updating          |                                                     |                                                                   ✓                                                                   |
+| Manual tagging                               |                          ✓                          |                                                                   ✓                                                                   |
+| User scripts                                 |                          ✓                          |                                                                   ✓                                                                   |
+| Media Type breakdown for search results      |                                                     |                                                                   ✓                                                                   |
+| Embeddings search                            |                      ✓ *O(n)*                       |                                                              ✓ *O(logn)*                                                              |
+
+### NER
+
+sist2 v3.0.4+ supports named-entity recognition (NER). Simply add a supported repository URL to
+**Configuration** > **Machine learning options** > **Model repositories**
+to enable it.
+
+The text processing is done in your browser, no data is sent to any third-party services.
+See [sist2app/sist2-ner-models](https://github.com/sist2app/sist2-ner-models) for more details.
+
+#### List of available repositories:
+
+| URL                                                                                                     | Maintainer                              | Purpose |
+|---------------------------------------------------------------------------------------------------------|-----------------------------------------|---------|
+| [sist2app/sist2-ner-models](https://raw.githubusercontent.com/sist2app/sist2-ner-models/main/repo.json) | [sist2app](https://github.com/sist2app) | General |
+
+<details>
+  <summary>Screenshot</summary>
+
+![ner](docs/ner.png)
+
+</details>
 
 ## Build from source
 
-You can compile **sist2** by yourself if you don't want to use the pre-compiled
-binaries.
+You can compile **sist2** by yourself if you don't want to use the pre-compiled binaries
+
+### Using docker
+
+```bash
+git clone --recursive https://github.com/sist2app/sist2/
+cd sist2
+docker build . -t my-sist2-image
+# Copy sist2 executable from docker image
+docker run --rm --entrypoint cat my-sist2-image /root/sist2 > sist2-x64-linux
+```
+
+### Using a linux computer
 
 1. Install compile-time dependencies
 
-    *(Debian)*
    ```bash
-    apt install git cmake pkg-config libglib2.0-dev \
-        libssl-dev uuid-dev python3 libmagic-dev libfreetype6-dev \
-        libcurl-dev libbz2-dev yasm libharfbuzz-dev ragel \
-        libarchive-dev libtiff5 libpng16-16 libpango1.0-dev
+   apt install gcc g++ python3 yasm ragel automake autotools-dev wget libtool libssl-dev curl zip unzip tar xorg-dev libglu1-mesa-dev libxcursor-dev libxml2-dev libxinerama-dev gettext nasm git nodejs
    ```
 
-2. Build
+2. Install vcpkg using my fork: https://github.com/sist2app/vcpkg
+3. Install vcpkg dependencies
+
     ```bash
-    git clone --recurse-submodules https://github.com/simon987/sist2
-    ./scripts/get_static_libs.sh
-    cmake .
+    vcpkg install openblas curl[core,openssl] sqlite3[core,fts5,json1] cpp-jwt pcre cjson brotli libarchive[core,bzip2,libxml2,lz4,lzma,lzo] pthread tesseract libxml2 libmupdf[ocr] gtest mongoose libmagic libraw gumbo ffmpeg[core,avcodec,avformat,swscale,swresample,webp,opus,mp3lame,vpx,zlib]
+    ```
+
+4. Build
+    ```bash
+    git clone --recursive https://github.com/sist2app/sist2/
+    (cd sist2-vue; npm install; npm run build)
+    (cd sist2-admin/frontend; npm install; npm run build)
+    cmake -DSIST_DEBUG=off -DCMAKE_TOOLCHAIN_FILE=<VCPKG_ROOT>/scripts/buildsystems/vcpkg.cmake .
     make
     ```

argparse

@@ -1 +0,0 @@
-Subproject commit fafc503d23d077bda40c29e8a20ea74707452721

cJSON

@@ -1 +0,0 @@
-Subproject commit 2d4ad841927590198ecfb8b27335a0cd97cf15c1

ci/build.sh

@@ -1,7 +0,0 @@
-#!/usr/bin/env bash
-
-./scripts/get_static_libs.sh
-
-cmake .
-make
-strip sist2

contrib/systemd/Makefile

@@ -0,0 +1,7 @@
+install:
+	install sist2-update-all.sh /usr/bin/sist2-update-all.sh
+	install sist2-update-files.sh /usr/bin/sist2-update-files.sh
+	install sist2-update-nextcloud.sh /usr/bin/sist2-update-nextcloud.sh
+	install sist2-update.service /etc/systemd/system/sist2-update.service
+	install sist2-update.timer /etc/systemd/system/sist2-update.timer
+	systemctl daemon-reload

contrib/systemd/README.md

@@ -0,0 +1,31 @@
+# Systemd integration example
+
+This example contains my (yatli) personal configuration for sist2 auto-updating.
+The following indices are involved in this configuration:
+
+| Index     | Path             | Description                                |
+|-----------|------------------|--------------------------------------------|
+| files     | /zpool/files     | Main file repository                       |
+| nextcloud | /zpool/nextcloud | Externally synchronized to a cloud account |
+
+The systemd integration achieves automatic sist2 scanning & indexing everyday at 3:00AM.
+
+### Tailoring the configuration for yourself
+
+`sist2-update-all.sh` calls update scripts for each sist2 index. Add or remove
+update scripts accordingly to suit your need. Each update script (e.g.
+`sist2-update-files.sh`) has important parameters laid down at the beginning so
+make sure to edit them to point to your files and index locations.
+
+### Installation
+
+```bash
+# install the services and scripts
+sudo make install
+# enable & start the timer
+sudo systemctl enable sist2-update.timer
+sudo systemctl start sist2-update.timer
+# verify that the timer has been enabled
+systemctl list-timers --all
+```
+

contrib/systemd/sist2-update-all.sh

@@ -0,0 +1,9 @@
+#!/bin/bash
+set -e
+__dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+echo "Update index: Files"
+source ${__dir}/sist2-update-files.sh
+echo "Update index: Nextcloud"
+source ${__dir}/sist2-update-nextcloud.sh
+echo "Done. Restarting sist2."
+docker restart sist2-sist2-1

contrib/systemd/sist2-update-files.sh

@@ -0,0 +1,34 @@
+#!/bin/bash
+set -e
+DATE=$(date +%Y_%m_%d)
+CONTENT=/zpool/files
+ORIG=/mnt/ssd/sist-index/files.idx
+NEW=/mnt/ssd/sist-index/files_$DATE.idx
+EXCLUDE='ZArchives|TorrentStore|TorrentDownload|624f0c59-1fef-44f6-95e9-7483296f2833|ubuntu-full-2021-12-07'
+NAME=Files
+#REWRITE_URL="http://localhost:33333/activate?collection=$NAME&path="
+REWRITE_URL=""
+
+sist2 scan \
+  --threads 14 \
+  --mem-throttle 32768 \
+  --thumbnail-quality 2 \
+  --name $NAME \
+  --ocr-lang=eng+chi_sim \
+  --ocr-ebooks \
+  --ocr-images \
+  --exclude=$EXCLUDE \
+  --rewrite-url=$REWRITE_URL \
+  --incremental=$ORIG \
+  --output=$NEW \
+  $CONTENT
+echo ">>> Scan complete"
+rm -rf $ORIG
+mv $NEW $ORIG 
+
+unset http_proxy
+unset https_proxy
+unset HTTP_PROXY
+unset HTTPS_PROXY
+sist2 index $ORIG --incremental-index
+echo ">>> Index complete"

contrib/systemd/sist2-update-nextcloud.sh

@@ -0,0 +1,33 @@
+#!/bin/bash
+set -e
+DATE=$(date +%Y_%m_%d)
+CONTENT=/zpool/nextcloud/v-yadli
+ORIG=/mnt/ssd/sist-index/nextcloud.idx
+NEW=/mnt/ssd/sist-index/nextcloud_$DATE.idx
+EXCLUDE='Yatao|.*263418493\\/Image\\/.*'
+NAME=NextCloud
+# REWRITE_URL="http://localhost:33333/activate?collection=$NAME&path="
+REWRITE_URL=""
+
+sist2 scan \
+  --threads 14 \
+  --mem-throttle 32768 \
+  --thumbnail-quality 2 \
+  --name $NAME \
+  --ocr-lang=eng+chi_sim \
+  --ocr-ebooks \
+  --ocr-images \
+  --exclude=$EXCLUDE \
+  --rewrite-url=$REWRITE_URL \
+  --incremental=$ORIG \
+  --output=$NEW \
+  $CONTENT
+echo ">>> Scan complete"
+rm -rf $ORIG
+mv $NEW $ORIG 
+
+unset http_proxy
+unset https_proxy
+unset HTTP_PROXY
+unset HTTPS_PROXY
+sist2 index $ORIG --incremental-index

contrib/systemd/sist2-update.service

@@ -0,0 +1,6 @@
+[Unit]
+Description=sist2-update
+
+[Service]
+User=yatli
+ExecStart=/bin/bash /usr/bin/sist2-update-all.sh

contrib/systemd/sist2-update.timer

@@ -0,0 +1,10 @@
+[Unit]
+Description=sist2-update
+
+[Timer]
+OnCalendar=*-*-* 3:00:00
+Persistent=true
+Unit=sist2-update.service
+
+[Install]
+WantedBy=timers.target

docker-compose.yml

@@ -0,0 +1,29 @@
+version: "3"
+
+services:
+  elasticsearch:
+    image: elasticsearch:7.17.9
+    container_name: sist2-es
+    volumes:
+      # This directory must have 1000:1000 permissions (or update PUID & PGID below)
+      - /data/sist2-es-data/:/usr/share/elasticsearch/data
+    environment:
+      - "discovery.type=single-node"
+      - "ES_JAVA_OPTS=-Xms2g -Xmx2g"
+      - "PUID=1000"
+      - "PGID=1000"
+  sist2-admin:
+    build:
+      context: .
+    container_name: sist2-admin
+    volumes:
+      - /data/sist2-admin-data/:/sist2-admin/
+      - /<path to index>/:/host
+    ports:
+      - 4090:4090
+      # NOTE: Don't export this port publicly!
+      - 8080:8080
+    working_dir: /root/sist2-admin/
+    entrypoint: python3
+    command:
+      - /root/sist2-admin/sist2_admin/app.py

docs/USAGE.md

@@ -0,0 +1,232 @@
+# Usage
+
+```
+Usage: sist2 scan [OPTION]... PATH
+   or: sist2 index [OPTION]... INDEX
+   or: sist2 sqlite-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                     Print version and exit.
+    --verbose                         Turn on logging.
+    --very-verbose                    Turn on debug messages.
+    --json-logs                       Output logs in JSON format.
+
+Scan options
+    -t, --threads=<int>               Number of threads. DEFAULT: 1
+    -q, --thumbnail_count-quality=<int>     Thumbnail quality, on a scale of 0 to 100, 100 being the best. DEFAULT: 50
+    --thumbnail_count-size=<int>            Thumbnail size, in pixels. DEFAULT: 552
+    --thumbnail_count-count=<int>           Number of thumbnails to generate. Set a value > 1 to create video previews, set to 0 to disable thumbnails. DEFAULT: 1
+    --content-size=<int>              Number of bytes to be extracted from text documents. Set to 0 to disable. DEFAULT: 32768
+    -o, --output=<str>                Output index file path. DEFAULT: index.sist2
+    --incremental                     If the output file path exists, only scan new or modified files.
+    --optimize-index                  Defragment index file after scan to reduce its file size.
+    --rewrite-url=<str>               Serve files from this url instead of from disk.
+    --name=<str>                      Index display name. DEFAULT: index
+    --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 scan, list: only save file names as text, shallow: don't scan archives inside archives. DEFAULT: recurse
+    --archive-passphrase=<str>        Passphrase for encrypted archive files
+    --ocr-lang=<str>                  Tesseract language (use 'tesseract --list-langs' to see which are installed on your machine)
+    --ocr-images                      Enable OCR'ing of image files.
+    --ocr-ebooks                      Enable OCR'ing of ebook files.
+    -e, --exclude=<str>               Files that match this regex will not be scanned.
+    --fast                            Only index file names & mime type.
+    --treemap-threshold=<str>         Relative size threshold for treemap (see USAGE.md). DEFAULT: 0.0005
+    --mem-buffer=<int>                Maximum memory buffer size per thread in MiB for files inside archives (see USAGE.md). DEFAULT: 2000
+    --read-subtitles                  Read subtitles from media files.
+    --fast-epub                       Faster but less accurate EPUB parsing (no thumbnails, metadata).
+    --checksums                       Calculate file checksums when scanning.
+    --list-file=<str>                 Specify a list of newline-delimited paths to be scanned instead of normal directory traversal. Use '-' to read from stdin.
+
+Index options
+    -t, --threads=<int>               Number of threads. DEFAULT: 1
+    --es-url=<str>                    Elasticsearch url with port. DEFAULT: http://localhost:9200
+    --es-insecure-ssl                 Do not verify SSL connections to Elasticsearch.
+    --es-index=<str>                  Elasticsearch index name. DEFAULT: sist2
+    -p, --print                       Print JSON documents to stdout instead of indexing to elasticsearch.
+    --incremental-index               Conduct incremental indexing. Assumes that the old index is already ingested in Elasticsearch.
+    --script-file=<str>               Path to user script.
+    --mappings-file=<str>             Path to Elasticsearch mappings.
+    --settings-file=<str>             Path to Elasticsearch settings.
+    --async-script                    Execute user script asynchronously.
+    --batch-size=<int>                Index batch size. DEFAULT: 70
+    -f, --force-reset                 Reset Elasticsearch mappings and settings.
+
+sqlite-index options
+    --search-index=<str>              Path to search index. Will be created if it does not exist yet.
+
+Web options
+    --es-url=<str>                    Elasticsearch url. DEFAULT: http://localhost:9200
+    --es-insecure-ssl                 Do not verify SSL connections to Elasticsearch.
+    --search-index=<str>              Path to SQLite search index.
+    --es-index=<str>                  Elasticsearch index name. DEFAULT: sist2
+    --bind=<str>                      Listen for connections on this address. DEFAULT: localhost:4090
+    --auth=<str>                      Basic auth in user:password format
+    --auth0-audience=<str>            API audience/identifier
+    --auth0-domain=<str>              Application domain
+    --auth0-client-id=<str>           Application client ID
+    --auth0-public-key-file=<str>     Path to Auth0 public key file extracted from <domain>/pem
+    --tag-auth=<str>                  Basic auth in user:password format for tagging
+    --tagline=<str>                   Tagline in navbar
+    --dev                             Serve html & js files from disk (for development)
+    --lang=<str>                      Default UI language. Can be changed by the user
+
+Made by simon987 <me@simon987.net>. Released under GPL-3.0
+```
+
+#### Thumbnail database size estimation
+
+See chart below for rough estimate of thumbnail_count size vs. thumbnail_count size & quality arguments:
+
+For example, `--thumbnail_count-size=500`, `--thumbnail_count-quality=50` for a directory with 8 million images will create a thumbnail_count database 
+that is about `8000000 * 11.8kB = 94.4GB`.
+
+![thumbnail_size](thumbnail_size.png)
+
+### Scan examples
+
+Simple scan
+```bash
+sist2 scan ~/Documents
+
+sist2 scan \
+    --threads 4 --content-size 16000000 --thumbnail_count-quality 2 --archive shallow \
+    --name "My Documents" --rewrite-url "http://nas.domain.local/My Documents/" \
+    ~/Documents -o ./documents.sist2
+```
+
+Incremental scan
+
+If the index file does not exist, `--incremental` has no effect.
+```bash
+sist scan ~/Documents -o ./documents.sist2
+sist scan ~/Documents -o ./documents.sist2 --incremental
+# or
+sist scan ~/Documents -o ./documents.sist2 --incremental
+sist scan ~/Documents -o ./documents.sist2 --incremental
+```
+
+### Index documents to Elasticsearch search backend
+
+```bash
+sist2 index --force-reset --batch-size 1000 --es-url http://localhost:9200 ./my_index.sist2
+sist2 index ./my_index.sist2
+```
+
+#### Index documents to SQLite search backend
+```bash
+# The search index will be created if it does not exist already
+sist2 sqlite-index ./index1.sist2 --search-index search.sist2
+sist2 sqlite-index ./index2.sist2 --search-index search.sist2
+```
+
+**Save index in JSON format**
+```bash
+sist2 index --print ./my_index.sist2 > my_index.ndjson
+```
+
+**Inspect contents of an index**
+```bash
+sist2 index --print ./my_index.sist2 | jq | less
+```
+
+## Web
+
+### Web examples
+
+**Single index (Elasticsearch backend)**
+```bash
+sist2 web --auth admin:hunter2 --bind 0.0.0.0:8888 my_index.sist2
+```
+
+**Multiple indices (Elasticsearch backend)**
+```bash
+# Indices will be displayed in this order in the web interface
+sist2 web index1.sist2 index2.sist2 index3.sist2 index4.sist2
+```
+
+**SQLite search backend**
+```bash
+sist2 web --search-index search.sist2 index1.sist2
+```
+
+#### Auth0 authentication
+
+See [auth0.md](auth0.md)
+
+### 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.
+
+# Elasticsearch
+
+Elasticsearch versions >=6.8.0, 7.X.X and 8.X.X are supported by sist2. 
+
+Using a version >=7.14.0 is recommended to enable the following features:
+
+- Bug fix for large documents (See #198)
+
+Using a version >=8.0.0 is recommended to enable the following features:
+
+- Approximate KNN search for Embeddings search (faster queries).
+
+When using a legacy version of ES, a notice will be displayed next to the sist2 version in the web UI.
+If you don't care about the features above, you can ignore it or disable it in the configuration page.
+
+# Embeddings search
+
+Since v3.2.0, User scripts can be used to generate _embeddings_ (vector of float32 numbers) which are stored in the .sist2 index file 
+(see [scripting](scripting.md)). Embeddings can be used for:
+
+* Nearest-neighbor queries (e.g. "return the documents most similar to this one")
+* Semantic searches (e.g. "return the documents that are most closely related to the given topic")
+
+In theory, embeddings can be created for any type of documents (image, text, audio etc.).
+
+For example, the [clip](https://github.com/sist2app/sist2-script-clip) User Script, generates 512-d embeddings of images
+(videos are also supported using the thumbnails generated by sist2). When the user enters a query in the "Embeddings Search"
+textbox, the query's embedding is generated in their browser, leveraging the ONNX web runtime.
+
+<details>
+  <summary>Screenshots</summary>
+ 
+ ![embeddings-1](embeddings-1.png)
+ ![embeddings-2](embeddings-2.png)
+
+1. Embeddings search bar. You can select the model using the dropdown on the left.
+2. This icon appears for indices with embeddings search enabled.
+3. Documents with this icon have embeddings. Click on the icon to perform KNN search.
+</details>
+
+
+# Tagging
+
+### Manual tagging
+
+You can modify tags of individual documents directly from the 
+ `web` interface. Note that you can setup authentication for this feature
+ with the `--tag-auth` option (See [web options](#web-options))
+
+![manual_tag](manual_tag.png)
+
+Tags that are manually added are saved both in the 
+ index folder (in `/tags/`) and in Elasticsearch*. When re-`index`ing, 
+ they are read from the index and automatically applied.
+ 
+You can safely copy the `/tags/` database to another index.
+
+See [Automatic tagging](#automatic-tagging) for information about tag 
+ hierarchies and tag colors.
+
+\* *It can take a few seconds to take effect in new search queries.*
+
+
+### Automatic tagging
+
+See [scripting](scripting.md) documentation.

docs/auth0.md

@@ -0,0 +1,19 @@
+
+# Authentication with Auth0
+
+1. Create a new Auth0 application (Single page app)
+2. Create a new Auth0 API:
+   1. Choose `RS256` signing algorithm
+   2. Set identifier (audience) to `https://sist2`
+3. Download the Auth0 certificate from https://<domain>.auth0.com/pem (you can find the domain Applications->Basic information)
+4. Extract the public key from the certificate using `openssl x509 -pubkey -noout -in cert.pem > pubkey.txt`
+5. Start the sist2 web server
+
+Example options:
+```bash
+sist2 web \
+  --auth0-client-id XXX \
+  --auth0-audience https://sist2 \
+  --auth0-domain YYY.auth0.com \
+  --auth0-public-key-file /ZZZ/pubkey.txt
+```

docs/scripting.md

@@ -1,6 +1,34 @@
 ## User scripts
 
-*This document is under construction, more in-depth guide coming soon*
+User scripts are used to augment your sist2 index with additional metadata, neural network embeddings, tags etc.
+
+
+Since version 3.2.0, user scripts are written in Python, and are ran against the sist2 index file. User scripts do not 
+need a connection to the search backend.
+
+You can create a user script based on a template from the sist2-admin interface:
+
+![sist2-admin-scripts](sist2-admin-scripts.png)
+
+User scripts leverage the [sist2-python](https://github.com/simon987/sist2-python) library to interface with the
+index file*. You can find sist2-python documentation and examples
+here: [sist2-python.readthedocs.io](https://sist2-python.readthedocs.io/).
+
+If you are not using the sist2-admin interface, you can run user scripts manually from the command line:
+
+```
+pip install git+https://github.com/simon987/sist2-python.git
+
+python my_script.py /path/to/my_index.sist2
+```
+
+\* It is possible to manually update the index using raw SQL queries, but the database schema is not stable and
+can change at any time; it is recommended to use the more stable sist2-python wrapper instead.
+
+<hr>
+
+<details>
+  <summary>Legacy user scripts (sist2 version < 3.2.0)</summary>
 
 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
@@ -13,6 +41,7 @@ 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",
@@ -35,11 +64,12 @@ This is the base structure of the documents we're working with:
 
 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())
+    tags.add("genre." + ctx._source.genre.toLowerCase());
 }
 ```
 
@@ -47,26 +77,34 @@ 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))
+    tags.add("year." + m.group(1));
 }
 ```
 
 Use default *Calibre* folder structure to infer author.
+
 ```Java
 ArrayList tags = ctx._source.tag = new ArrayList();
 
@@ -81,6 +119,7 @@ if (ctx._source.name.contains("-") && ctx._source.extension == "pdf") {
 
 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();
 
@@ -97,21 +136,47 @@ if (m.find()) {
 ```
 
 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('/');
+    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
+Parse `EXIF:F Number` 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]);
+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);
+}
+
+```
+
+</details>
+

include/mce/config.h

@@ -1,53 +0,0 @@
-/*
- Copyright (c) 2010, Florian Reuter
- 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.
- * Neither the name of Florian Reuter nor the names of its contributors 
- may be used to endorse or promote products derived from this 
- software without specific prior written permission.
- 
- 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.
- */
-/**@file config/mce/config.h
- */
-#ifndef MCE_CONFIG_H
-#define MCE_CONFIG_H
-
-#include <libxml/xmlstring.h>
-#include <stdio.h>
-#include <plib/plib.h>
-#include <assert.h>
-
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-#define MCE_NAMESPACE_SUBSUMPTION_ENABLED 0
-
-#ifdef __cplusplus
-} /* extern "C" */
-#endif  
-
-#endif /* MCE_CONFIG_H */

include/mce/helper.h

@@ -1,189 +0,0 @@
-/*
- Copyright (c) 2010, Florian Reuter
- 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.
- * Neither the name of Florian Reuter nor the names of its contributors 
-   may be used to endorse or promote products derived from this 
-   software without specific prior written permission.
- 
- 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.
- 
-*/
-/** @file mce/helper.h
-Helper functions needed by mce/textreader.h and mce/textwriter.h to implement MCE:
-- mceQNameLevelAdd(), mceQNameLevelLookup() and mceQNameLevelCleanup() maintain a set of mceQNameLevel_t tuples.
-- mceQNameLevelPush() and mceQNameLevelPopIfMatch() maintain a stack of mceQNameLevel_t tuples.
-- mceCtxInit(), mceCtxCleanup() and mceCtxUnderstandsNamespace() manage a context which holds all information needed to do MCE proprocessing.
- */
-#include <mce/config.h>
-
-#ifndef MCE_HELPER_H
-#define MCE_HELPER_H
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-    /**
-      Tiple (ns, ln, level).
-    */
-    typedef struct MCE_QNAME_LEVEL {
-        xmlChar *ns;
-        xmlChar *ln;
-        puint32_t level;
-        puint32_t flag; // used by mceTextWriter
-    } mceQNameLevel_t;
-
-    /**
-     */
-    typedef enum MCE_SKIP_STATE_ENUM {
-        MCE_SKIP_STATE_IGNORE,
-        MCE_SKIP_STATE_ALTERNATE_CONTENT,
-        MCE_SKIP_STATE_CHOICE_MATCHED
-    } mceSkipState_t;
-
-    /**
-     Represents an intervall of levels which are "skipped" i.e. ignored.
-     */
-    typedef struct MCE_SKIP_ITEM {
-        puint32_t level_start;
-        puint32_t level_end;
-        mceSkipState_t state;
-    } mceSkipItem_t;
-
-    /**
-      Either represents a set of (ns, ln, level) triples.
-    */
-    typedef struct MCE_QNAME_LEVEL_SET {
-        mceQNameLevel_t *list_array;
-        puint32_t list_items;
-        puint32_t max_level;
-    } mceQNameLevelSet_t;
-
-    /**
-     The skip stack.
-     */
-    typedef struct MCE_SKIP_STACK {
-        mceSkipItem_t *stack_array;
-        puint32_t stack_items;
-    } mceSkipStack_t;
-
-
-    typedef enum MCE_ERROR_ENUM {
-        MCE_ERROR_NONE,
-        MCE_ERROR_XML,
-        MCE_ERROR_MUST_UNDERSTAND,
-        MCE_ERROR_VALIDATION,
-        MCE_ERROR_MEMORY
-    } mceError_t;
-
-    /**
-      Holds all information to do MCE preprocessing.
-    */
-    typedef struct MCE_CONTEXT {
-        mceQNameLevelSet_t ignorable_set;
-        mceQNameLevelSet_t understands_set;
-        mceQNameLevelSet_t processcontent_set;
-        mceQNameLevelSet_t suspended_set;
-#if (MCE_NAMESPACE_SUBSUMPTION_ENABLED)
-        mceQNameLevelSet_t subsume_namespace_set;
-        mceQNameLevelSet_t subsume_exclude_set;
-        mceQNameLevelSet_t subsume_prefix_set;
-#endif
-        mceSkipStack_t skip_stack;
-        mceError_t error;
-        pbool_t mce_disabled;        
-        puint32_t suspended_level;
-    } mceCtx_t;
-
-    /**
-      Add a new tiple (ns, ln, level) to the triple set \c qname_level_set.
-      The \c ns_sub string is optional and will not be touched.
-    */
-    pbool_t mceQNameLevelAdd(mceQNameLevelSet_t *qname_level_set, const xmlChar *ns, const xmlChar *ln, puint32_t level);
-
-    /**
-      Lookup a tiple (ns, ln, level) via \c ns and \c ln. If \c ignore_ln is PTRUE then the first tiple matching \c ns will be returned.
-    */
-    mceQNameLevel_t* mceQNameLevelLookup(mceQNameLevelSet_t *qname_level_set, const xmlChar *ns, const xmlChar *ln, pbool_t ignore_ln);
-
-    /**
-      Remove all triples (ns, ln, level) where the level greater or equal to \c level.
-    */
-    pbool_t mceQNameLevelCleanup(mceQNameLevelSet_t *qname_level_set, puint32_t level);
-
-    /**
-      Push a new skip intervall (level_start, level_end, state) on the stack \c skip_stack.
-    */
-    pbool_t mceSkipStackPush(mceSkipStack_t *skip_stack, puint32_t level_start, puint32_t level_end, mceSkipState_t state);
-
-    /**
-      Pop the intervall (ns, ln, level) from the stack \c qname_level_array.
-    */
-    void mceSkipStackPop(mceSkipStack_t *skip_stack);
-
-    /**
-     Returns top item or NULL.
-     */
-    mceSkipItem_t *mceSkipStackTop(mceSkipStack_t *skip_stack);
-
-    /**
-     Returns TRUE, if the \c level is in the top skip intervall.
-     */
-    pbool_t mceSkipStackSkip(mceSkipStack_t *skip_stack, puint32_t level);
-
-    /**
-      Initialize the mceCtx_t \c ctx.
-    */
-    pbool_t mceCtxInit(mceCtx_t *ctx);
-
-    /**
-      Cleanup, i.e. release all resourced from the mceCtx_t \c ctx.
-    */
-    pbool_t mceCtxCleanup(mceCtx_t *ctx);
-
-    /**
-      Register the namespace \ns in \c ctx.
-    */
-    pbool_t mceCtxUnderstandsNamespace(mceCtx_t *ctx, const xmlChar *ns);
-
-    /**
-     Register the namespace \ns in \c ctx.
-     */
-    pbool_t mceCtxSuspendProcessing(mceCtx_t *ctx, const xmlChar *ns, const xmlChar *ln);
-    
-
-
-#if (MCE_NAMESPACE_SUBSUMPTION_ENABLED)
-    /**
-    Subsume namespace \c ns_new with \c ns_old.
-     */
-    pbool_t mceCtxSubsumeNamespace(mceCtx_t *ctx, const xmlChar *prefix_new, const xmlChar *ns_new, const xmlChar *ns_old);
-#endif
-
-#ifdef __cplusplus
-} /* extern "C" */
-#endif
-
-#endif /* MCE_HELPER_H */

include/mce/textreader.h

@@ -1,464 +0,0 @@
-/*
- Copyright (c) 2010, Florian Reuter
- 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.
- * Neither the name of Florian Reuter nor the names of its contributors 
-   may be used to endorse or promote products derived from this 
-   software without specific prior written permission.
- 
- 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.
- 
-*/
-/** @file mce/textreader.h
- 
- */
-#ifndef MCE_TEXTREADER_H
-#define MCE_TEXTREADER_H
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-    /**
-      A handle to an MCE-aware libxml2 xmlTextReader.
-    */
-    typedef struct MCE_TEXTREADER mceTextReader_t;
-
-#ifdef __cplusplus
-} /* extern "C" */
-#endif
-
-
-#include <mce/config.h>
-#include <opc/opc.h>
-#include <mce/helper.h>
-#include <libxml/xmlwriter.h>
-
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-    struct MCE_TEXTREADER {
-        xmlTextReaderPtr reader;
-        mceCtx_t mceCtx;
-    };
-
-    /**
-      Wrapper around an libxml2 xmlTextReaderRead function.
-      \see http://xmlsoft.org/html/libxml-xmlreader.html#xmlTextReaderRead
-    */
-    int mceTextReaderRead(mceTextReader_t *mceTextReader);
-
-    /**
-      Wrapper around a libxml2 xmlTextReaderNext function.
-      \see http://xmlsoft.org/html/libxml-xmlreader.html#xmlTextReaderNext
-    */
-    int mceTextReaderNext(mceTextReader_t *mceTextReader);
-
-    /** 
-      Creates an mceTextReader from an XmlTextReader. 
-      \code
-      mceTextReader reader;
-      mceTextReaderInit(&reader, xmlNewTextReaderFilename("sample.xml"));
-      // reader is ready to use.
-      mceTextReaderCleanup(&reader);
-      \endcode
-      \see http://xmlsoft.org/html/libxml-xmlreader.html#xmlNewTextReaderFilename
-    */
-    int mceTextReaderInit(mceTextReader_t *mceTextReader, xmlTextReaderPtr reader);
-
-    /**
-      Cleanup MCE reader, i.e. free all resources. Also calls xmlTextReaderClose and xmlFreeTextReader.
-      \see http://xmlsoft.org/html/libxml-xmlreader.html#xmlTextReaderClose
-      \see http://xmlsoft.org/html/libxml-xmlreader.html#xmlFreeTextReader
-    */
-    int mceTextReaderCleanup(mceTextReader_t *mceTextReader);
-
-    /** 
-      Reads all events \c mceTextReader and pipes them to \writer.
-      \code
-      mceTextReader reader;
-      mceTextReaderInit(&reader, xmlNewTextReaderFilename("sample.xml"));
-      mceTextReaderUnderstandsNamespace(&reader, _X("http://myextension"));
-      xmlTextWriterPtr writer=xmlNewTextWriterFilename("out.xml", 0);
-      mceTextReaderDump(&reader, writer, P_FALSE);
-      xmlFreeTextWriter(writer);
-      mceTextReaderCleanup(&reader);
-      \endcode
-      */
-    int mceTextReaderDump(mceTextReader_t *mceTextReader, xmlTextWriter *writer, pbool_t fragment);
-
-    /**
-      Registers an MCE namespace.
-      \see mceTextReaderDump()
-      */
-    int mceTextReaderUnderstandsNamespace(mceTextReader_t *mceTextReader, const xmlChar *ns);
-
-    /**
-     Disable MCE processing.
-     \return Returns old value.
-     */
-    pbool_t mceTextReaderDisableMCE(mceTextReader_t *mceTextReader, pbool_t flag);
-
-
-    /**
-     Signal an error to the MCE processor.
-     */
-    void mceRaiseError(xmlTextReader *reader, mceCtx_t *ctx, mceError_t error, const xmlChar *str, ...);
-
-    /**
-        Internal function which does the MCE postprocessing. E.g. mceTextReaderRead() is implemented as
-        \code
-        mceTextReaderPostprocess(mceTextReader->reader, &mceTextReader->mceCtx, xmlTextReaderRead(mceTextReader->reader))
-        \endcode
-        This function is exposed to make existing libxm2 xmlTextReader MCE aware.
-    */
-    int mceTextReaderPostprocess(xmlTextReader *reader, mceCtx_t *ctx, int ret);
-
-    /**
-     Get the error code.
-     */
-    mceError_t mceTextReaderGetError(mceTextReader_t *mceTextReader);
-
-/**
- Helper macro to declare a start/end document block in a declarative way:
- \code
-  mce_start_document(reader) {
-  } mce_end_document(reader);
-  \endcode
-  \hideinitializer
-*/
-#define mce_start_document(_reader_) \
-    if (NULL!=(_reader_)) {            \
-        mceTextReaderRead(_reader_); \
-        if (0)                     
-
-/**
-  \see mce_start_document.
-  \hideinitializer
-*/
-#define mce_end_document(_reader_)   \
-    } /* if (NULL!=reader) */        \
-
-
-/**
-  Container for mce_start_element and mce_start_attribute declarations.
-  \see mce_match_element
-  \see mce_match_attribute
-  \hideinitializer
-  */
-#define mce_start_choice(_reader_)  \
-    if (0)                          
-
-/**
-  \see mce_start_choice
-  \hideinitializer
-  */
-#define mce_end_choice(_reader_) 
-
-
-/**
-  Skips the attributes. 
-  \see mce_match_element.
-  \hideinitializer
-*/
-#define mce_skip_attributes(_reader_) \
-    mce_start_attributes(_reader_) {  \
-    } mce_end_attributes(_reader_);   
-
-
-/**
-  Skips the attributes. 
-  \see mce_match_attribute.
-  \hideinitializer
-*/
-#define mce_skip_children(_reader_) \
-    mce_start_children(_reader_) {  \
-    } mce_end_children(_reader_);   
-
-/**
-  \see mce_start_element.
-  \hideinitializer
-*/
-#define mce_start_children(_reader_)                  \
-if (!xmlTextReaderIsEmptyElement((_reader_)->reader)) { \
-    mceTextReaderRead(_reader_); do {                 \
-        if (0)                                        
-
-/**
-  \see mce_start_element.
-  \hideinitializer
-*/
-#define mce_end_children(_reader_)                                                      \
-        else {                                                                          \
-            if (XML_READER_TYPE_END_ELEMENT!=xmlTextReaderNodeType((_reader_)->reader)) { \
-                mceTextReaderNext(_reader_); /*skip unhandled element */                \
-            }                                                                           \
-        }                                                                               \
-    } while(XML_READER_TYPE_END_ELEMENT!=xmlTextReaderNodeType((_reader_)->reader) &&     \
-            XML_READER_TYPE_NONE!=xmlTextReaderNodeType((_reader_)->reader));             \
-} /* if (!xmlTextReaderIsEmptyElement(reader->reader)) */                               
-
-
-/**
-  Helper macro to match an element. Usefull for calling code in a seperate function:
-
-  \code
-  void handleElement(reader) {
-    mce_start_choice(reader) {
-        mce_start_element(reader, _X("ns"), _X("element")) {
-            
-        } mce_end_element(reader)
-    } mce_end_choice(reader);
-  }
-
-  void parse(reader) {
-    mce_start_document(reader) {
-      mce_start_element(reader, _X("ns"), _X("ln")) {
-        mce_skip_attributes(reader);
-        mce_start_children(reader) {
-           mce_match_element(reader, _X("ns"), _X("element")) {
-             handleElement(reader);
-           }
-        } mce_end_children(reader);
-      } mce_end_element();
-    } mce_end_document(reader);
-  }
-  \endcode
-  \hideinitializer
-*/
-#define mce_match_element(_reader_, ns, ln)                                                       \
-    } else if (XML_READER_TYPE_ELEMENT==xmlTextReaderNodeType((_reader_)->reader)                 \
-            && (NULL==ns || 0==xmlStrcmp(ns, xmlTextReaderConstNamespaceUri((_reader_)->reader))) \
-            && (NULL==ln || 0==xmlStrcmp(ln, xmlTextReaderConstLocalName((_reader_)->reader)))) { 
-
-
-/**
- Helper macro to declare a element block in a declarative way:
- \code
-  mce_start_element(reader) {
-    mce_start_attributes(reader) {
-      mce_start_attribute(reader, _X("ns"), _X("lnA")) {
-         // code for handling lnA.
-      } mce_end_attribute(reader);
-      mce_start_attribute(reader, _X("ns"), _X("lnB")) {
-         // code for handling lnB.
-      } mce_end_attribute(reader);
-    } mce_end_attributes(reader);
-    mce_start_children(reader) {
-        mce_start_element(reader, _X("ns"), _X("lnA")) {
-         // code for handling lnA.
-        } mce_end_element(reader);
-        mce_start_element(reader, _X("ns"), _X("lnB")) {
-         // code for handling lnB.
-        } mce_end_element(reader);
-        mce_start_text(reader) {
-         // code for handling text.
-        } mce_end_text(reader);
-    } mce_end_children(reader);
-  } mce_end_element(reader);
-  \endcode
-  \hideinitializer
-*/
-#define mce_start_element(_reader_, ns, ln) \
-    mce_match_element(_reader_, ns, ln)     
-
-/**
-  \see mce_start_element.
-  \hideinitializer
-*/
-#define mce_end_element(_reader_) \
-    mceTextReaderNext(_reader_)   
-
-/**
-  Matches #TEXT without consuming it.
-  \hideinitializer
-*/
-#define mce_match_text(_reader_)                                                                   \
-    } else if (XML_READER_TYPE_TEXT==xmlTextReaderNodeType((_reader_)->reader)                     \
-            || XML_READER_TYPE_SIGNIFICANT_WHITESPACE==xmlTextReaderNodeType((_reader_)->reader)) {
-
-
-/**
-  \see mce_start_element.
-  \hideinitializer
-*/
-#define mce_start_text(_reader_) \
-    mce_match_text(_reader_)      
-
-/**
-  \see mce_start_element.
-  \hideinitializer
-*/
-#define mce_end_text(_reader_) \
-    mceTextReaderNext(_reader_)
-
-/**
-  \see mce_start_element.
-  \hideinitializer
-*/
-#define mce_start_attributes(_reader_)                            \
-    if (1==xmlTextReaderMoveToFirstAttribute((_reader_)->reader)) { \
-        do {                                                      \
-            if (0)                                                
-
-/**
-  \see mce_start_element.
-  \hideinitializer
-*/
-#define mce_end_attributes(_reader_)                                    \
-            else { /* skipped attribute */ }                            \
-        } while(1==xmlTextReaderMoveToNextAttribute((_reader_)->reader)); \
-    xmlTextReaderMoveToElement((_reader_)->reader); }                     
-
-/**
-  Helper macro to match an attribute. Usefull for calling code in a seperate function:
-
-  \code
-  void handleA(reader) {
-    mce_start_choice(reader) {
-        mce_start_attribute(reader, _X("ns"), _X("attr")) {
-
-        } mce_end_attribute(reader);
-    } mce_end_choice(reader);
-  }
-
-  void parse(reader) {
-    mce_start_document(reader) {
-      mce_start_element(reader, _X("ns"), _X("ln")) {
-        mce_start_attributes(reader) {
-           mce_match_attribute(reader, _X("ns"), _X("attr")) {
-             handleA(reader);
-           }
-        } mce_end_attributes(reader);
-        mce_skip_children(reader);
-      } mce_end_element();
-    } mce_end_document(reader);
-  }
-  \endcode
-  \hideinitializer
-*/
-#define mce_match_attribute(_reader_, ns, ln)                                                   \
-    } else if ((NULL==ns || 0==xmlStrcmp(ns, xmlTextReaderConstNamespaceUri((_reader_)->reader))) \
-            && (NULL==ln || 0==xmlStrcmp(ln, xmlTextReaderConstLocalName((_reader_)->reader)))) { 
-
-/**
-  \see mce_start_element.
-  \hideinitializer
-*/
-#define mce_start_attribute(_reader_, ns, ln) \
-    mce_match_attribute(_reader_, ns, ln) 
-
-/**
-  \see mce_start_element.
-  \hideinitializer
-*/
-#define mce_end_attribute(_reader_)
-
-
-/**
-  Error handling for MCE parsers.
-  \code
-   mce_start_element(&reader, NULL, _X("Default")) {
-       const xmlChar *ext=NULL;
-       const xmlChar *type=NULL;
-       mce_start_attributes(&reader) {
-           mce_start_attribute(&reader, NULL, _X("Extension")) {
-               ext=xmlTextReaderConstValue(reader.reader);
-           } mce_end_attribute(&reader);
-           mce_start_attribute(&reader, NULL, _X("ContentType")) {
-               type=xmlTextReaderConstValue(reader.reader);
-           } mce_end_attribute(&reader);
-       } mce_end_attributes(&reader);
-       mce_error_guard_start(&reader) {
-           mce_error(&reader, NULL==ext || ext[0]==0, MCE_ERROR_VALIDATION, "Missing @Extension attribute!");
-           mce_error(&reader, NULL==type || type[0]==0, MCE_ERROR_VALIDATION, "Missing @ContentType attribute!");
-           opcContainerType *ct=insertType(c, type, OPC_TRUE);
-           mce_error(&reader, NULL==ct, MCE_ERROR_MEMORY, NULL);
-           opcContainerExtension *ce=opcContainerInsertExtension(c, ext, OPC_TRUE);
-           mce_error(&reader, NULL==ce, MCE_ERROR_MEMORY, NULL);
-           mce_errorf(&reader, NULL!=ce->type && 0!=xmlStrcmp(ce->type, type), MCE_ERROR_VALIDATION, "Extension \"%s\" is mapped to type \"%s\" as well as \"%s\"", ext, type, ce->type);
-           ce->type=ct->type;
-       } mce_error_guard_end(&reader);
-       mce_skip_children(&reader);
-   } mce_end_element(&reader);
-  \endcode
-  \hideinitializer
-*/
-#define mce_error_guard_start(_reader_) if (MCE_ERROR_NONE==(_reader_)->mceCtx.error) do {
-
-/**
-  \see mce_error_guard_start
-  \hideinitializer
-*/
-#define mce_error_guard_end(_reader_)  } while(0)
-
-/**
-  Signal an error if guard if false.
-  \hideinitializer
-*/
-#define mce_error(_reader_, guard, err, msg) if (guard) { (_reader_)->mceCtx.error=(err); fprintf(stderr, (NULL!=msg?msg:#err));  continue; }
-
-/**
-  Signal an error if guard if false.
-  \hideinitializer
-*/
-#if defined(__GNUC__)
-#define mce_errorf(_reader_, guard, err, msg, ...) if (guard) { mceRaiseError((_reader_)->reader, &(_reader_)->mceCtx, err, _X((NULL!=msg?msg:#err)), ##__VA_ARGS__ );  continue; }
-#else
-#define mce_errorf(_reader_, guard, err, msg, ...) if (guard) { mceRaiseError((_reader_)->reader, &(_reader_)->mceCtx, err, _X((NULL!=msg?msg:#err)), __VA_ARGS__ );  continue; }
-#endif
-
-/**
-  Only issues the error when in "strict mode".
-  \hideinitializer
-*/
-#define mce_error_strict mce_error
-
-/**
-  \see mce_error_strict
-  \hideinitializer
-*/
-#define mce_error_strictf mce_errorf
-
-
-/**
-  Marker for a MCE defintion.
-  \hideinitializer
-*/
-#define mce_def
-
-/**
-  Marker for a MCE reference.
-  \hideinitializer
-*/
-#define mce_ref(r) (r)
-
-
-#ifdef __cplusplus
-} /* extern "C" */
-#endif
-
-#endif /* MCE_TEXTREADER_H */

include/mce/textwriter.h

@@ -1,176 +0,0 @@
-/*
- Copyright (c) 2010, Florian Reuter
- 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.
- * Neither the name of Florian Reuter nor the names of its contributors 
-   may be used to endorse or promote products derived from this 
-   software without specific prior written permission.
- 
- 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.
- 
-*/
-/** @file mce/textwriter.h
-
-*/
-#include <mce/config.h>
-#include <libxml/xmlwriter.h>
-#include <mce/helper.h>
-
-#ifndef MCE_TEXTWRITER_H
-#define MCE_TEXTWRITER_H
-
-#ifdef __cplusplus
-extern "C" {
-#endif    
-
-/**
-  Default flags for an MCE namespace declaration.
-  */
-#define MCE_DEFAULT 0x0
-
-/**
-  Flags MCE namespace declaration "ignorable".
-  */
-#define MCE_IGNORABLE 0x1
-
-/**
-  Flags MCE namespace declaration "must understand".
-  */
-#define MCE_MUSTUNDERSTAND 0x2
-
-    /**
-      The MCE text writer context.
-      */
-    typedef struct MCE_TEXTWRITER_STRUCT mceTextWriter;
-
-    /**
-      Create a new MCE text writer.
-      \see http://xmlsoft.org/html/libxml-xmlIO.html#xmlOutputBufferCreateIO
-      \see http://xmlsoft.org/html/libxml-xmlwriter.html#xmlNewTextWriter
-      */
-    mceTextWriter *mceTextWriterCreateIO(xmlOutputWriteCallback iowrite, xmlOutputCloseCallback  ioclose, void *ioctx, xmlCharEncodingHandlerPtr encoder);
-
-    /**
-      Helper which create a new MCE text writer for a FILE handle.
-      */
-    mceTextWriter *mceNewTextWriterFile(FILE *file);
-
-    /**
-      Free all resources for \w.
-      */
-    int mceTextWriterFree(mceTextWriter *w);
-
-    /**
-      \see http://xmlsoft.org/html/libxml-xmlwriter.html#xmlTextWriterStartDocument
-      */
-    int mceTextWriterStartDocument(mceTextWriter *w);
-
-    /**
-      \see http://xmlsoft.org/html/libxml-xmlwriter.html#xmlTextWriterEndDocument
-      */
-    int mceTextWriterEndDocument(mceTextWriter *w);
-
-    /**
-      Start a new XML element. If ns==NULL then there is no namespace and ""==ns means the default namespace.
-      \see http://xmlsoft.org/html/libxml-xmlwriter.html#xmlTextWriterStartElement
-      \see http://xmlsoft.org/html/libxml-xmlwriter.html#xmlTextWriterStartElementNS
-      */
-    int mceTextWriterStartElement(mceTextWriter *w, const xmlChar *ns, const xmlChar *ln);
-
-    /**
-      \see http://xmlsoft.org/html/libxml-xmlwriter.html#xmlTextWriterEndElement
-      */
-    int mceTextWriterEndElement(mceTextWriter *w, const xmlChar *ns, const xmlChar *ln);
-
-    /**
-      \see http://xmlsoft.org/html/libxml-xmlwriter.html#xmlTextWriterWriteString
-      */
-    int mceTextWriterWriteString(mceTextWriter *w, const xmlChar *content);
-
-    /**
-      Register a namespace. Must be called before mceTextWriterStartElement.
-      \see MCE_DEFAULT
-      \see MCE_IGNORABLE
-      \see MCE_MUSTUNDERSTAND
-      */
-    const xmlChar *mceTextWriterRegisterNamespace(mceTextWriter *w, const xmlChar *ns, const xmlChar *prefix, int flags);
-
-    /**
-      Register qname (ns, ln) as a "process content" element wrt. MCE. Must be called before mceTextWriterStartElement.
-      */
-    int mceTextWriterProcessContent(mceTextWriter *w, const xmlChar *ns, const xmlChar *ln);
-
-    /**
-      Writes a formatted attribute.
-      \see http://xmlsoft.org/html/libxml-xmlwriter.html#xmlTextWriterWriteFormatAttribute
-      */
-    int mceTextWriterAttributeF(mceTextWriter *w, const xmlChar *ns, const xmlChar *ln, const char *value, ...);
-
-    /**
-      Starts an MCE alternate content section.
-      */
-    int mceTextWriterStartAlternateContent(mceTextWriter *w);
-
-    /**
-      Ends an MCE alternate content section.
-      */
-    int mceTextWriterEndAlternateContent(mceTextWriter *w);
-
-    /**
-      Start an MCE choice.
-      */
-    int mceTextWriterStartChoice(mceTextWriter *w, const xmlChar *ns);
-
-    /**
-      Ends an MCE choice.
-      */
-    int mceTextWriterEndChoice(mceTextWriter *w);
-
-    /**
-      Start an MCE fallback.
-      */
-    int mceTextWriterStartFallback(mceTextWriter *w);
-
-    /**
-      Ends an MCE fallback.
-      */
-    int mceTextWriterEndFallback(mceTextWriter *w);
-
-
-    /**
-      Returns the underlying xmlTextWriter.
-      */
-    xmlTextWriterPtr mceTextWriterIntern(mceTextWriter *w);
-
-    /**
-      Helper which create a new xmlTextWriterPtr for a FILE handle.
-      */
-    xmlTextWriterPtr xmlNewTextWriterFile(FILE *file);
-
-
-#ifdef __cplusplus
-} /* extern "C" */
-#endif    
-
-#endif /* MCE_TEXTWRITER_H */

include/opc/config.h

@@ -1,189 +0,0 @@
-/*
- Copyright (c) 2010, Florian Reuter
- 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.
- * Neither the name of Florian Reuter nor the names of its contributors 
- may be used to endorse or promote products derived from this 
- software without specific prior written permission.
- 
- 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.
- */
-/**@file config/opc/config.h
- */
-#ifndef OPC_CONFIG_H
-#define OPC_CONFIG_H
-
-#include <libxml/xmlstring.h>
-#include <plib/plib.h>
-#include <assert.h>
-
-#ifdef __cplusplus
-extern "C" {
-#endif   
-
-
-/**
-  Assert expression e is true. Will be removed entirely in release mode.
-  \hideinitializer
- */
-#define OPC_ASSERT(e) assert(e)
-
-/**
-  Assert expression e is true. Expression will be executed in release mode too.
-  \hideinitializer
- */
-#ifdef NDEBUG
-#define OPC_ENSURE(e) (void)(e)
-#else
-#define OPC_ENSURE(e) assert(e)
-#endif
-
-
-/**
-  Constant for boolean true.
-  \hideinitializer
- */
-#define OPC_TRUE (0==0)
-
-/**
-  Constant for boolean false.
-  \hideinitializer
- */
-#define OPC_FALSE (0==1)
-
-    /** 
-      Boolean type.
-      \hideinitializer
-      */
-    typedef pbool_t opc_bool_t;
-
-    /** 
-      Type which represents an offset in e.g. a file.
-      \hideinitializer
-      */
-    typedef pofs_t opc_ofs_t;
-
-    /** 
-      8-bit unsigned integer.
-      \hideinitializer
-      */
-    typedef puint8_t opc_uint8_t;
-
-    /** 
-      16-bit unsigned integer.
-      \hideinitializer
-      */
-    typedef puint16_t opc_uint16_t;
-
-    /** 
-      32-bit unsigned integer.
-      \hideinitializer
-      */
-    typedef puint32_t opc_uint32_t;
-
-    /** 
-      64-bit unsigned integer.
-      \hideinitializer
-      */
-    typedef puint64_t opc_uint64_t;
-
-    /** 
-      8-bit signed integer.
-      \hideinitializer
-      */
-    typedef pint8_t opc_int8_t;
-
-    /** 
-      16-bit signed integer.
-      \hideinitializer
-      */
-    typedef pint16_t opc_int16_t;
-
-    /** 
-      32-bit signed integer.
-      \hideinitializer
-      */
-    typedef pint32_t opc_int32_t;
-
-    /** 
-      64-bit signed integer.
-      \hideinitializer
-      */
-    typedef pint64_t opc_int64_t;
-
-/**
-  Default size fo the deflate buffer used by zlib.
-  */
-#define OPC_DEFLATE_BUFFER_SIZE 4096
-
-/**
-  Max system path len.
-  */
-#define OPC_MAX_PATH 512
-
-    /**
-      Error codes for the OPC module.
-      */
-    typedef enum OPC_ERROR_ENUM {
-        OPC_ERROR_NONE,
-        OPC_ERROR_STREAM,
-        OPC_ERROR_SEEK, // can't seek
-        OPC_ERROR_UNSUPPORTED_DATA_DESCRIPTOR,
-        OPC_ERROR_UNSUPPORTED_COMPRESSION,
-        OPC_ERROR_DEFLATE,
-        OPC_ERROR_HEADER,
-        OPC_ERROR_MEMORY,
-        OPC_ERROR_XML, 
-        OPC_ERROR_USER // user triggered an abort
-    } opc_error_t;
-    
-    /**
-      Compression options for OPC streams.
-      */
-    typedef enum OPC_COMPRESSIONOPTION_ENUM {
-        OPC_COMPRESSIONOPTION_NONE,
-        OPC_COMPRESSIONOPTION_NORMAL,
-        OPC_COMPRESSIONOPTION_MAXIMUM,
-        OPC_COMPRESSIONOPTION_FAST,
-        OPC_COMPRESSIONOPTION_SUPERFAST
-    } opcCompressionOption_t;
-
-
-/**
-  Helper for debug logs.
-  \hideinitializer
-  */
-#define opc_logf printf
-
-/**
-  Abstraction for memset(m, 0, s).
-  \hideinitializer
- */
-#define opc_bzero_mem(m,s) memset(m, 0, s)
-
-#ifdef __cplusplus
-} /* extern "C" */
-#endif  
-
-#endif /* OPC_CONFIG_H */

include/opc/container.h

@@ -1,300 +0,0 @@
-/*
- Copyright (c) 2010, Florian Reuter
- 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.
- * Neither the name of Florian Reuter nor the names of its contributors 
-   may be used to endorse or promote products derived from this 
-   software without specific prior written permission.
- 
- 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.
- 
-*/
-/** @file opc/container.h
-
- The container.h module has the fundamental methods for dealing with ZIP-based OPC container. 
- 
- OPC container can be opened in READ-ONLY mode, WRITE-ONLY mode, READ/WRITE mode, TEMPLATE mode and TRANSITION mode. 
- The most notable mode is the READ/WRITE mode, which gives you concurrent stream-based READ and WRITE access to a 
- single ZIP-based OPC container. This is achieved without the use of temporary files by taking advantage of the 
- OPC specific “interleave” mode. \see http://standards.iso.org/ittf/PubliclyAvailableStandards/c051459_ISOIEC_29500-2_2008(E).zip
- 
- The TEMPLATE mode allows very fast customized "cloning" of ZIP-based OPC container by using "RAW access" to the ZIP streams. 
- The TRANSITION mode is a special version of the TEMPLATE mode, which allows transition-based READ/WRITE access to the 
- ZIP-based OPC container using a temporary file.
- 
- */
-#include <opc/config.h>
-#include <opc/file.h>
-
-#ifndef OPC_CONTAINER_H
-#define OPC_CONTAINER_H
-
-#ifdef __cplusplus
-extern "C" {
-#endif    
-    /**
-     Handle to an OPC container created by \ref opcContainerOpen.
-     \see opcContainerOpen.
-     */
-    typedef struct OPC_CONTAINER_STRUCT opcContainer;
-    
-    /**
-     Modes for opcContainerOpen();
-     \see opcContainerOpen
-     */
-    typedef enum {
-        /**
-         Opens the OPC container denoted by \a fileName in READ-ONLY mode. The \a destName parameter must be \a NULL.
-         \hideinitializer
-         */
-        OPC_OPEN_READ_ONLY=0, 
-        /**
-         Opens the OPC container denoted by \a fileName in WRITE-ONLY mode. The \a destName parameter must be \a NULL.
-         \hideinitializer
-         */
-        OPC_OPEN_WRITE_ONLY=1,
-        /**
-         Opens the OPC container denoted by \a fileName in READ/WRITE mode. The \a destName parameter must be \a NULL.
-         \hideinitializer
-         */
-        OPC_OPEN_READ_WRITE=2,
-        /**
-         This mode will open the container denoted by \a fileName in READ-ONLY mode and the container denoted by 
-         \a destName in write-only mode. Any modifications will be written to the container denoted by \a destName 
-         and the unmodified streams from \a fileName will be written to \a destName on closing.
-         \warning Currently not implemented.
-         \hideinitializer
-         */
-        OPC_OPEN_TEMPLATE=3,
-        /**
-         Like the OPC_OPEN_TEMPLATE mode, but the \a destName will be renamed to the \a fileName on closing. If \a destName 
-         is \a NULL, then the name of the temporary file will be generated automatically.
-         \warning Currently not implemented.
-         \hideinitializer
-         */
-        OPC_OPEN_TRANSITION=4
-    } opcContainerOpenMode; 
-    
-    /** Modes for opcContainerClose.
-     \see opcContainerClose.
-     */
-    typedef enum {
-        /**
-         Close the OPC container without any further postprocessing.
-         \hideinitializer
-         */
-        OPC_CLOSE_NOW = 0,
-        /**
-         Close the OPC container and trim the file by removing unused fragments like e.g. 
-         deleted parts.
-         \hideinitializer
-         */
-        OPC_CLOSE_TRIM = 1,
-        /**
-         Close the OPC container like in \a OPC_CLOSE_TRIM mode, but additionally remove any 
-         "interleaved" parts by reordering them.
-         \warning Currently not implemented. Same semantic as OPC_CLOSE_TRIM.       
-         \hideinitializer
-         */
-        OPC_CLOSE_DEFRAG = 2
-    } opcContainerCloseMode;
-    
-    /**
-     Opens a ZIP-based OPC container.
-     @param[in] fileName. For more details see \ref opcContainerOpenMode.
-     @param[in] mode. For more details see \ref opcContainerOpenMode.
-     @param[in] userContext. Will not be modified by libopc. Can be used to e.g. store the "this" pointer for C++ bindings.
-     @param[in] destName. For more details see \ref opcContainerOpenMode.
-     @return \a NULL if failed. 
-     \see opcContainerOpenMode
-     \see opcContainerDump
-     */
-    opcContainer* opcContainerOpen(const xmlChar *fileName, 
-                                   opcContainerOpenMode mode, 
-                                   void *userContext, 
-                                   const xmlChar *destName);
-
-    /**
-     Opens a ZIP-based OPC container from memory.
-     @param[in] data. 
-     @param[in] data_len.
-     @param[in] userContext. Will not be modified by libopc. Can be used to e.g. store the "this" pointer for C++ bindings.
-     @param[in] mode. For more details see \ref opcContainerOpenMode.
-     @return \a NULL if failed. 
-     */
-    opcContainer* opcContainerOpenMem(const opc_uint8_t *data, opc_uint32_t data_len,
-                                      opcContainerOpenMode mode, 
-                                      void *userContext);
-
-    /**
-     Opens a ZIP-based OPC container from memory.
-     @param[in] ioread. 
-     @param[in] iowrite. 
-     @param[in] ioclose. 
-     @param[in] ioseek. 
-     @param[in] iotrim. 
-     @param[in] ioflush. 
-     @param[in] iocontext. 
-     @param[in] file_size. 
-     @param[in] userContext. Will not be modified by libopc. Can be used to e.g. store the "this" pointer for C++ bindings.
-     @param[in] mode. For more details see \ref opcContainerOpenMode.
-     @return \a NULL if failed. 
-     */
-    opcContainer* opcContainerOpenIO(opcFileReadCallback *ioread,
-                                     opcFileWriteCallback *iowrite,
-                                     opcFileCloseCallback *ioclose,
-                                     opcFileSeekCallback *ioseek,
-                                     opcFileTrimCallback *iotrim,
-                                     opcFileFlushCallback *ioflush,
-                                     void *iocontext,
-                                     pofs_t file_size,
-                                     opcContainerOpenMode mode, 
-                                     void *userContext);
-    
-    /**
-     Close an OPC container.
-     @param[in] c. \ref opcContainer openered by \ref opcContainerOpen.
-     @param[in] mode. For more information see \ref opcContainerCloseMode.
-     @return Non-zero if successful.
-     \see opcContainerOpen
-     \see opcContainerCloseMode
-     */
-    opc_error_t opcContainerClose(opcContainer *c, opcContainerCloseMode mode);
-    
-    /**
-     Returns the unmodified user context passed to \ref opcContainerOpen.
-     \see opcContainerOpen
-     */
-    void *opcContainerGetUserContext(opcContainer *c);
-    
-    /**
-     List all types, relations and parts of the container \a c to \a out.
-     \par Sample:
-     \include opc_dump.c
-     */
-    opc_error_t opcContainerDump(opcContainer *c, FILE *out);
-    
-    /**
-     Exports the OPC container to "Flat OPC" (http://blogs.msdn.com/b/ericwhite/archive/2008/09/29/the-flat-opc-format.aspx).
-     The flat versions of an OPC file are very important when dealing with e.g XSL(T)-based or Javascript-based transformations.
-     \see opcContainerFlatImport.
-     \todo Implementation needed.
-     */
-    int opcContainerFlatExport(opcContainer *c, const xmlChar *fileName);
-    
-    /**
-     Imports the flat version of an OPC container. 
-     \see opcContainerFlatExport.
-     \todo Implementation needed.
-     */
-    int opcContainerFlatImport(opcContainer *c, const xmlChar *fileName);
-    
-    /**
-     Iterate all types.
-     \code
-     for(xmlChar *type=opcContentTypeFirst(c);
-         NULL!=type;
-         type=opcContentTypeNext(c, type)) {
-        printf("%s\n", type);
-     }
-     \endcode
-    */
-    const xmlChar *opcContentTypeFirst(opcContainer *container);
-    
-    /**
-     \see opcContentTypeNext()
-    */
-    const xmlChar *opcContentTypeNext(opcContainer *container, const xmlChar *type);
-
-    /**
-     Iterate extensions.
-     \code
-     for(const xmlChar *ext=opcExtensionFirst(c);
-         NULL!=ext;
-         ext=opcExtensionNext(ext)) {
-        printf("%s\n", ext);
-     }
-     \endcode
-    */
-    const xmlChar *opcExtensionFirst(opcContainer *container);
-    
-    /**
-     \see opcExtensionFirst()
-     */
-    const xmlChar *opcExtensionNext(opcContainer *container, const xmlChar *ext);
-    
-    /**
-     Get registered type for extension.
-     \see opcExtensionRegister()
-     */
-    const xmlChar *opcExtensionGetType(opcContainer *container, const xmlChar *ext);
-
-    /**
-     Register a mime-type and and extension.
-     \see opcExtensionGetType()
-     */
-    const xmlChar *opcExtensionRegister(opcContainer *container, const xmlChar *ext, const xmlChar *type);
-
-
-    /**
-     Iterator through all relation types of the container:
-     \code
-     for(xmlChar *type=opcRelationTypeFirst(c);
-         NULL!=type;
-         type=opcRelationTypeNext(c, type)) {
-        printf("%s\n", type);
-     }
-     \endcode
-     */
-    const xmlChar *opcRelationTypeFirst(opcContainer *container);
-
-    /**
-     \see opcRelationTypeFirst()
-    */
-    const xmlChar *opcRelationTypeNext(opcContainer *container, const xmlChar *type);
-
-
-    /**
-     Iterator through all relation types of the container:
-     \code
-     for(xmlChar *target=opcExternalTargetFirst(c);
-         NULL!=target;
-         type=opcExternalTargetNext(c, target)) {
-        printf("%s\n", target);
-     }
-     \endcode
-     */
-    const xmlChar *opcExternalTargetFirst(opcContainer *container);
-
-    /**
-     \see opcExternalTargetFirst()
-    */
-    const xmlChar *opcExternalTargetNext(opcContainer *container, const xmlChar *target);
-
-
-#ifdef __cplusplus
-} /* extern "C" */
-#endif    
-        
-#endif /* OPC_CONTAINER_H */

include/opc/file.h

@@ -1,200 +0,0 @@
-/*
- Copyright (c) 2010, Florian Reuter
- 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.
- * Neither the name of Florian Reuter nor the names of its contributors 
-   may be used to endorse or promote products derived from this 
-   software without specific prior written permission.
- 
- 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.
- 
-*/
-/** @file opc/file.h
- The opc module contains the file library functions.
-*/
-#include <opc/config.h>
-
-#ifndef OPC_FILE_H
-#define OPC_FILE_H
-
-#ifdef __cplusplus
-extern "C" {
-#endif    
-
-/**
-  Flag for READ access.
-  \hideinitializer
-*/
-#define OPC_FILE_READ  (1<<0)
-
-/**
-  Flag for WRITE access.
-  \hideinitializer
-*/
-#define OPC_FILE_WRITE (1<<1)
-
-/**
-  Flag indicates that file will be truncated when opened.
-  \hideinitializer
-*/
-#define OPC_FILE_TRUNC  (1<<2)
-
-
-    /** 
-      Abstraction for see modes.
-      */
-    typedef enum OPC_FILESEEKMODE_ENUM {
-        opcFileSeekSet = SEEK_SET,
-        opcFileSeekCur = SEEK_CUR,
-        opcFileSeekEnd = SEEK_END
-    } opcFileSeekMode;
-
-     /**
-      Callback to read a file. E.g. for a FILE * context this can be implemented as
-      \code
-      static int opcFileRead(void *iocontext, char *buffer, int len) {
-          return fread(buffer, sizeof(char), len, (FILE*)iocontext);
-      }
-      \endcode
-      */
-    typedef int opcFileReadCallback(void *iocontext, char *buffer, int len);
-
-     /**
-      Callback to write a file. E.g. for a FILE * context this can be implemented as
-      \code
-      static int opcFileWrite(void *iocontext, const char *buffer, int len) {
-          return fwrite(buffer, sizeof(char), len, (FILE*)iocontext);
-      }
-      \endcode
-      */
-    typedef int opcFileWriteCallback(void *iocontext, const char *buffer, int len);
-
-     /**
-      Callback to close a file. E.g. for a FILE * context this can be implemented as
-      \code
-      static int opcFileClose(void *iocontext) {
-          return fclose((FILE*)iocontext);
-      }
-      \endcode
-      */
-    typedef int opcFileCloseCallback(void *iocontext);
-
-     /**
-      Callback to seek a file. E.g. for a FILE * context this can be implemented as
-      \code
-      static opc_ofs_t opcFileSeek(void *iocontext, opc_ofs_t ofs) {
-          int ret=fseek((FILE*)iocontext, ofs, SEEK_SET);
-          if (ret>=0) {
-              return ftell((FILE*)iocontext);
-          } else {
-              return ret;
-          }
-      }
-      \endcode
-      */
-    typedef opc_ofs_t opcFileSeekCallback(void *iocontext, opc_ofs_t ofs);
-
-     /**
-      Callback to trim a file. E.g. for a FILE * context this can be implemented as
-      \code
-      static int opcFileTrim(void *iocontext, opc_ofs_t new_size) {
-      #ifdef WIN32
-          return _chsize(fileno((FILE*)iocontext), new_size);
-      #else
-          return ftruncate(fileno((FILE*)iocontext), new_size);
-      #endif
-      }
-      \endcode
-      */
-    typedef int opcFileTrimCallback(void *iocontext, opc_ofs_t new_size);
-
-     /**
-      Callback to flush a file. E.g. for a FILE * context this can be implemented as
-      \code
-      static int opcFileFlush(void *iocontext) {
-          return fflush((FILE*)iocontext);
-      }
-      \endcode
-      */
-    typedef int opcFileFlushCallback(void *iocontext);
-
-    /**
-      Represents a state of a file, i.e. file position (buf_pos) and error status (err).
-      */
-    typedef struct OPC_FILERAWSTATE_STRUCT {
-        opc_error_t err;
-        opc_ofs_t   buf_pos; // current pos in file
-    } opcFileRawState;
-
-    /**
-     File IO context.
-     */
-    typedef struct OPC_IO_STRUCT {
-        opcFileReadCallback *_ioread;
-        opcFileWriteCallback *_iowrite;
-        opcFileCloseCallback *_ioclose;
-        opcFileSeekCallback *_ioseek;
-        opcFileTrimCallback *_iotrim;
-        opcFileFlushCallback *_ioflush;
-        void *iocontext;
-        int flags;
-        opcFileRawState state;
-        opc_ofs_t file_size;
-    } opcIO_t;
-
-    /**
-      Initialize an IO context.
-      */
-    opc_error_t opcFileInitIO(opcIO_t *io,
-                              opcFileReadCallback *ioread,
-                              opcFileWriteCallback *iowrite,
-                              opcFileCloseCallback *ioclose,
-                              opcFileSeekCallback *ioseek,
-                              opcFileTrimCallback *iotrim,
-                              opcFileFlushCallback *ioflush,
-                              void *iocontext,
-                              pofs_t file_size,
-                              int flags);
-
-    /**
-      Initialize an IO context for a file.
-      */
-    opc_error_t opcFileInitIOFile(opcIO_t *io, const xmlChar *filename, int flags);
-
-    /**
-      Initialize an IO for memory.
-      \warning Currently supports READ-ONLY file access.
-      */
-    opc_error_t opcFileInitIOMemory(opcIO_t *io, const opc_uint8_t *data, opc_uint32_t data_len, int flags);
-
-    /**
-      Cleanup an IO context, i.e. release all system resources.
-      */
-    opc_error_t opcFileCleanupIO(opcIO_t *io);
-
-#ifdef __cplusplus
-} /* extern "C" */
-#endif    
-        
-#endif /* OPC_FILE_H */

include/opc/helper.h

@@ -1,60 +0,0 @@
-/*
- Copyright (c) 2010, Florian Reuter
- 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.
- * Neither the name of Florian Reuter nor the names of its contributors 
-   may be used to endorse or promote products derived from this 
-   software without specific prior written permission.
- 
- 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.
- 
-*/
-/** @file opc/helper.h
-  Contains helper functions for the opc module.
-*/
-#include <opc/config.h>
-
-#ifndef OPC_HELPER_H
-#define OPC_HELPER_H
-
-#ifdef __cplusplus
-extern "C" {
-#endif    
-
-
-#ifdef __cplusplus
-} /* extern "C" */
-#endif    
-
-    /**
-      Constructs a segment name.
-      */
-    opc_uint16_t opcHelperAssembleSegmentName(char *out, opc_uint16_t out_size, const xmlChar *name, opc_uint32_t segment_number, opc_uint32_t next_segment_id, opc_bool_t rels_segment, opc_uint16_t *out_max);
-
-    /**
-      Splits a filename into the segment informations.
-      */
-    opc_error_t opcHelperSplitFilename(opc_uint8_t *filename, opc_uint32_t filename_length, opc_uint32_t *segment_number, opc_bool_t *last_segment, opc_bool_t *rel_segment);
-
-#endif /* OPC_HELPER_H */

include/opc/inputstream.h

@@ -1,74 +0,0 @@
-/*
- Copyright (c) 2010, Florian Reuter
- 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.
- * Neither the name of Florian Reuter nor the names of its contributors 
-   may be used to endorse or promote products derived from this 
-   software without specific prior written permission.
- 
- 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.
- 
-*/
-/** @file opc/inputstream.h
- 
- */
-#include <opc/config.h>
-
-#ifndef OPC_INPUTSTREAM_H
-#define OPC_INPUTSTREAM_H
-
-#ifdef __cplusplus
-extern "C" {
-#endif    
-    /**
-      Internal type which represents a binary input stream.
-      */
-    typedef struct OPC_CONTAINER_INPUTSTREAM_STRUCT opcContainerInputStream;
-
-    /**
-      Opens the part \c name of the \c container for reading.
-      */
-    opcContainerInputStream* opcContainerOpenInputStream(opcContainer *container, const xmlChar *name);
-
-    /**
-     Reads maximal \c buffer_len bytes from the input \c stream to \c buffer. 
-     \return The number of byes read or "0" in case of an error or end-of-stream.
-     */
-    opc_uint32_t opcContainerReadInputStream(opcContainerInputStream* stream, opc_uint8_t *buffer, opc_uint32_t buffer_len);
-
-    /**
-      Closes the input stream and releases all system resources.
-      */
-    opc_error_t opcContainerCloseInputStream(opcContainerInputStream* stream);
-
-    /**
-      Returns the type of compression used for the stream.
-      */
-    opcCompressionOption_t opcContainerGetInputStreamCompressionOption(opcContainerInputStream* stream);
-
-#ifdef __cplusplus
-} /* extern "C" */
-#endif    
-        
-#endif /* OPC_INPUTSTREAM_H */

include/opc/opc.h

@@ -1,73 +0,0 @@
-/*
- Copyright (c) 2010, Florian Reuter
- 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.
- * Neither the name of Florian Reuter nor the names of its contributors 
-   may be used to endorse or promote products derived from this 
-   software without specific prior written permission.
- 
- 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.
- 
-*/
-/** @file opc/opc.h
- The opc module contains the basic library functions.
-*/
-#include <opc/config.h>
-#include <opc/container.h>
-#include <opc/part.h>
-#include <opc/relation.h>
-#include <opc/inputstream.h>
-#include <opc/outputstream.h>
-#include <opc/zip.h>
-#include <opc/xmlreader.h>
-#include <opc/xmlwriter.h>
-#include <opc/properties.h>
-
-#ifndef OPC_OPC_H
-#define OPC_OPC_H
-
-#ifdef __cplusplus
-extern "C" {
-#endif    
-    
-    /**
-     * Initialize libopc.
-     * Sample:
-     * \include opc_helloworld.c
-     * @return Non-zero if successful.
-     */
-    opc_error_t opcInitLibrary();
-
-    /**
-     * Free libopc. Clean up all resources.
-     * @return Non-zero if successful.
-     * \see opcInitLibrary.
-     */
-    opc_error_t opcFreeLibrary();
-
-#ifdef __cplusplus
-} /* extern "C" */
-#endif    
-        
-#endif /* OPC_OPC_H */

include/opc/outputstream.h

@@ -1,71 +0,0 @@
-/*
- Copyright (c) 2010, Florian Reuter
- 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.
- * Neither the name of Florian Reuter nor the names of its contributors 
-   may be used to endorse or promote products derived from this 
-   software without specific prior written permission.
- 
- 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.
- 
-*/
-/** @file opc/outputstream.h
- 
- */
-#include <opc/config.h>
-
-#ifndef OPC_OUTPUTSTREAM_H
-#define OPC_OUTPUTSTREAM_H
-
-#ifdef __cplusplus
-extern "C" {
-#endif    
-    /**
-      Internal type which represents a binary output stream.
-      */
-    typedef struct OPC_CONTAINER_OUTPUTSTREAM_STRUCT opcContainerOutputStream;
-
-    /** 
-      Open the part \c name or writing in \c container with compression \c compression_option.
-      \note Make sure the part exists! 
-      \see opcPartCreate.
-      */
-    opcContainerOutputStream* opcContainerCreateOutputStream(opcContainer *container, const xmlChar *name, opcCompressionOption_t compression_option);
-
-    /**
-      Write \c buffer_len bytes from \c buffer to \c stream. 
-      \return Returns the number of bytes written.
-      */
-    opc_uint32_t opcContainerWriteOutputStream(opcContainerOutputStream* stream, const opc_uint8_t *buffer, opc_uint32_t buffer_len);
-
-    /**
-      Close the \c stream and free all associated resources.
-      */
-    opc_error_t opcContainerCloseOutputStream(opcContainerOutputStream* stream);
-        
-#ifdef __cplusplus
-} /* extern "C" */
-#endif    
-        
-#endif /* OPC_OUTPUTSTREAM_H */

include/opc/part.h

@@ -1,118 +0,0 @@
-/*
- Copyright (c) 2010, Florian Reuter
- 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.
- * Neither the name of Florian Reuter nor the names of its contributors 
-   may be used to endorse or promote products derived from this 
-   software without specific prior written permission.
- 
- 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.
- 
-*/
-/** @file opc/part.h
- 
- */
-#include <opc/config.h>
-
-#ifndef OPC_PART_H
-#define OPC_PART_H
-
-#ifdef __cplusplus
-extern "C" {
-#endif    
-    /**
-     Handle to an OPC part created by \ref opcPartOpen.
-     \see opcPartOpen.
-     */
-    typedef xmlChar* opcPart;
-
-/**
-  Represents an invalid (resp. NULL) part.
-  In releations OPC_PART_INVALID also represents the root part.
-  \hideinitializer
-  */
-#define OPC_PART_INVALID NULL
-
-    /**
-     Find a part in a \ container by \c absolutePath and/or \c type.
-     Currently no flags are supported.
-     */
-    opcPart opcPartFind(opcContainer *container, 
-                        const xmlChar *absolutePath, 
-                        const xmlChar *type,
-                        int flags);
-
-    /**
-     Creates a part in a \ container with \c absolutePath and \c type.
-     Currently no flags are supported.
-     */
-    opcPart opcPartCreate(opcContainer *container, 
-                          const xmlChar *absolutePath, 
-                          const xmlChar *type,
-                          int flags);
-
-    /**
-      Returns the type of the container.
-      The string is interned and must not be freed.
-      */
-    const xmlChar *opcPartGetType(opcContainer *c, opcPart part);
-
-    /**
-      Returns the type of the container. 
-      If \c override_only then the return value will be NULL for parts not having an override type.
-      The string is interned and must not be freed.
-      */
-    const xmlChar *opcPartGetTypeEx(opcContainer *c, opcPart part, opc_bool_t override_only);
-
-    /**
-     Deleted that part \c absolutePath in the \c container.
-     */
-    opc_error_t opcPartDelete(opcContainer *container, const xmlChar *absolutePath);
-
-    /**
-      Get the first part.
-      \code
-      for(opcPart part=opcPartGetFirst(c);OPC_PART_INVALID!=part;part=opcPartGetNext(c, part)) {
-        printf("%s; \n", part, opcPartGetType(c, part));
-      }
-      \endcode 
-      */
-    opcPart opcPartGetFirst(opcContainer *container);
-
-    /**
-     Get the next part.
-     \see opcPartGetFirst
-      */
-    opcPart opcPartGetNext(opcContainer *container, opcPart part);
-
-    /**
-      Returns the size in bytes of the \c part.
-      */
-    opc_ofs_t opcPartGetSize(opcContainer *c, opcPart part);
-
-#ifdef __cplusplus
-} /* extern "C" */
-#endif    
-        
-#endif /* OPC_PART_H */

include/opc/properties.h

@@ -1,121 +0,0 @@
-/*
- Copyright (c) 2010, Florian Reuter
- 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.
- * Neither the name of Florian Reuter nor the names of its contributors 
-   may be used to endorse or promote products derived from this 
-   software without specific prior written permission.
- 
- 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.
- 
-*/
-/** @file opc/properties.h
- 
- */
-#include <opc/config.h>
-#include <opc/container.h>
-
-#ifndef OPC_PROPERTIES_H
-#define OPC_PROPERTIES_H
-
-#ifdef __cplusplus
-extern "C" {
-#endif    
-
-    /** 
-      Represents a simple Dublin Core type.
-      */
-    typedef struct OPC_DC_SIMPLE_TYPE {
-        xmlChar *str;
-        xmlChar *lang;
-    } opcDCSimpleType_t;
-
-    /** 
-      Represents the core properties of an OPC container.
-      */
-    typedef struct OPC_PROPERTIES_STRUCT {
-        xmlChar *category;                /* xsd:string     */
-        xmlChar *contentStatus;           /* xsd:string     */
-        xmlChar *created;                 /* dc:date        */
-        opcDCSimpleType_t creator;        /* dc:any         */
-        opcDCSimpleType_t description;    /* dc:any         */
-        opcDCSimpleType_t identifier;     /* dc:any         */
-        opcDCSimpleType_t *keyword_array; /* cp:CT_Keywords */
-        opc_uint32_t keyword_items;
-        opcDCSimpleType_t language;       /* dc:any         */
-        xmlChar *lastModifiedBy;          /* xsd:string     */
-        xmlChar *lastPrinted;             /* xsd:dateTime   */
-        xmlChar *modified;                /* dc:date        */
-        xmlChar *revision;                /* xsd:string     */
-        opcDCSimpleType_t subject;        /* dc:any         */
-        opcDCSimpleType_t title;          /* dc:any         */
-        xmlChar *version;                 /* xsd:string     */
-    } opcProperties_t;
-
-    /**
-      Initialize the core properties \c cp.
-      \see opcCorePropertiesSetString
-      */
-    opc_error_t opcCorePropertiesInit(opcProperties_t *cp);
-
-    /**
-      Cleanup the core properties \c cp, i.e. release all resources.
-      \see opcCorePropertiesSetString
-      */
-    opc_error_t opcCorePropertiesCleanup(opcProperties_t *cp);
-
-    /**
-      Rease the core properties \c cp from the container \c.
-      */
-    opc_error_t opcCorePropertiesRead(opcProperties_t *cp, opcContainer *c);
-
-
-    /**
-      Write/Update the core properties \c cp in the container \c.
-      */
-    opc_error_t opcCorePropertiesWrite(opcProperties_t *cp, opcContainer *c);
-
-    /**
-      Update a string in the core properties the right way.
-      \code
-      opcProperties_t cp;
-      opcCorePropertiesInit(&cp);
-      opcCorePropertiesSetString(&cp.revision, "1");
-      opcCorePropertiesSetStringLang(&cp.creator, "Florian Reuter", NULL);
-      opcCorePropertiesCleanup(&cp);
-      \endcode
-      */
-    opc_error_t opcCorePropertiesSetString(xmlChar **prop, const xmlChar *str);
-
-    /** 
-      Update a core properties the right way.
-      \see opcCorePropertiesSetString
-      */
-    opc_error_t opcCorePropertiesSetStringLang(opcDCSimpleType_t *prop, const xmlChar *str, const xmlChar *lang);
-
-#ifdef __cplusplus
-} /* extern "C" */
-#endif    
-        
-#endif /* OPC_PROPERTIES_H */

include/opc/relation.h

@@ -1,140 +0,0 @@
-/*
- Copyright (c) 2010, Florian Reuter
- 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.
- * Neither the name of Florian Reuter nor the names of its contributors 
-   may be used to endorse or promote products derived from this 
-   software without specific prior written permission.
- 
- 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.
- 
-*/
-/** @file opc/relation.h
- 
- */
-#include <opc/config.h>
-
-#ifndef OPC_RELATION_H
-#define OPC_RELATION_H
-
-#ifdef __cplusplus
-extern "C" {
-#endif    
-
-    /**
-     Indentifier for an OPC relation.
-     */
-    typedef opc_uint32_t opcRelation;
-
-/**
-  Constant which represents an invalid relation.
-*/
-#define OPC_RELATION_INVALID (-1)
-
-    /**
-      Find a relation originating from \c part in \c container with \c relationId and/or \c mimeType.
-      If \c part is OPC_PART_INVALID then part represents the root part.
-      @param[in] relationId The relationId (e.g. "rId1") or NULL.
-      @param[in] mimeType The mimeType or NULL.
-      */
-    opcRelation opcRelationFind(opcContainer *container, opcPart part, const xmlChar *relationId, const xmlChar *mimeType);
-
-    /**
-      Deleted the relation from the container.
-      \see opcRelationFind.
-      */
-    opc_error_t opcRelationDelete(opcContainer *container, opcPart part, const xmlChar *relationId, const xmlChar *mimeType);
-
-    /**
-      Returns the first relation.
-      The following code will dump all relations:
-      \code
-        for(opcPart part=opcPartGetFirst(c);OPC_PART_INVALID!=part;part=opcPartGetNext(c, part)) {
-           for(opcRelation rel=opcRelationFirst(part, c);
-               OPC_PART_INVALID!=rel;
-               rel=opcRelationNext(c, rel)) {
-               opcPart internal_target=opcRelationGetInternalTarget(c, part, rel);
-               const xmlChar *external_target=opcRelationGetExternalTarget(c, part, rel);
-               const xmlChar *target=(NULL!=internal_target?internal_target:external_target);
-               const xmlChar *prefix=NULL;
-               opc_uint32_t counter=-1;
-               const xmlChar *type=NULL;
-               opcRelationGetInformation(c, part, rel, &prefix, &counter, &type);        
-               if (-1==counter) { // no counter after prefix
-                  printf("%s;%s;%s;%s\n", part, prefix, target, type);
-               } else {
-                  printf("%s;%s%i;%s;%s\n", part, prefix, counter, target, type);
-               }
-           }
-        }
-      \endcode
-      */
-    opcRelation opcRelationFirst(opcContainer *container, opcPart part);
-
-    /**
-      \see opcRelationFirst
-      */
-    opcRelation opcRelationNext(opcContainer *container, opcPart part, opcRelation relation);
-    
-    /**
-      Returns the internal target.
-      \note To test for an external target use opcRelationGetExternalTarget.
-      \see opcRelationGetExternalTarget
-      */
-    opcPart opcRelationGetInternalTarget(opcContainer *container, opcPart part, opcRelation relation);
-
-    /**
-      Returns the external target or NULL if it is an internal target.
-      The string is interned. Must not be freed.
-      \see opcRelationGetExternalTarget
-      */
-    const xmlChar *opcRelationGetExternalTarget(opcContainer *container, opcPart part, opcRelation relation);
-
-    /**
-      Returns the relations type.
-      The string is interned. Must not be freed.
-      */
-    const xmlChar *opcRelationGetType(opcContainer *container, opcPart part, opcRelation relation);
-
-    /** 
-      Get information about a relation.
-      \see opcRelationFirst
-      */
-    void opcRelationGetInformation(opcContainer *container, opcPart part, opcRelation relation, const xmlChar **prefix, opc_uint32_t *counter, const xmlChar **type);
-
-    /** 
-      Add a relation to \c container from \c src part to \c dest part with id \c rid and type \c type.
-      */
-    opc_uint32_t opcRelationAdd(opcContainer *container, opcPart src, const xmlChar *rid, opcPart dest, const xmlChar *type);
-
-    /** 
-      Add an external relation to \c container from \c src part to \c target URL with id \c rid and type \c type.
-      */
-    opc_uint32_t opcRelationAddExternal(opcContainer *container, opcPart src, const xmlChar *rid, const xmlChar *target, const xmlChar *type);
-
-#ifdef __cplusplus
-} /* extern "C" */
-#endif    
-
-#endif /* OPC_RELATION_H */

include/opc/xmlreader.h

@@ -1,69 +0,0 @@
-/*
- Copyright (c) 2010, Florian Reuter
- 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.
- * Neither the name of Florian Reuter nor the names of its contributors 
-   may be used to endorse or promote products derived from this 
-   software without specific prior written permission.
- 
- 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.
- 
-*/
-/** @file opc/xmlreader.h
- 
- */
-
-#ifndef OPC_XMLREADER_H
-#define OPC_XMLREADER_H
-
-#include <opc/config.h>
-#include <libxml/xmlreader.h>
-#include <mce/textreader.h>
-
-
-#ifdef __cplusplus
-extern "C" {
-#endif    
-
-    /** 
-      Open an MCE reader for \c partName. Parameters \c URL, \c encoding and \c options will be passed unmodified to 
-      http://xmlsoft.org/html/libxml-xmlreader.html#xmlReaderForIO and they can we NULL, NULL, 0.
-      \note Make sure the part exists.
-      \see opcPartFind
-      */
-    opc_error_t opcXmlReaderOpen(opcContainer *container, mceTextReader_t *mceTextReader, const xmlChar *partName, const char * URL, const char * encoding, int options);
-
-    /**
-      Returns an libxml DOM document. Parameters \c URL, \c encoding and \c options will be passed unmodified to 
-      http://xmlsoft.org/html/libxml-parser.html#xmlReadIO and they can we NULL, NULL, 0.
-      \note Make sure the part exists.
-      \see opcPartFind
-      */
-    xmlDocPtr opcXmlReaderReadDoc(opcContainer *container, const xmlChar *partName, const char * URL, const char * encoding, int options);
-
-#ifdef __cplusplus
-} /* extern "C" */
-#endif    
-        
-#endif /* OPC_XMLREADER_H */

include/opc/xmlwriter.h

@@ -1,57 +0,0 @@
-/*
- Copyright (c) 2010, Florian Reuter
- 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.
- * Neither the name of Florian Reuter nor the names of its contributors 
-   may be used to endorse or promote products derived from this 
-   software without specific prior written permission.
- 
- 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.
- 
-*/
-/** @file opc/xmlwriter.h
- 
- */
-#include <opc/config.h>
-#include <mce/textwriter.h>
-
-#ifndef OPC_XMLWRITER_H
-#define OPC_XMLWRITER_H
-
-#ifdef __cplusplus
-extern "C" {
-#endif    
-
-    /**
-      Create an MCE text writer for \c part in \c container with compression \c compression_option.
-      \note Make sure the part exists.
-      \see opcPartFind
-      */
-    mceTextWriter *mceTextWriterOpen(opcContainer *c, opcPart part, opcCompressionOption_t compression_option);
-
-#ifdef __cplusplus
-} /* extern "C" */
-#endif    
-        
-#endif /* OPC_XMLWRITER_H */

include/opc/zip.h

@@ -1,255 +0,0 @@
-/*
- Copyright (c) 2010, Florian Reuter
- 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.
- * Neither the name of Florian Reuter nor the names of its contributors 
-   may be used to endorse or promote products derived from this 
-   software without specific prior written permission.
- 
- 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.
- 
-*/
-/** @file opc/zip.h
-  The ZIP file backend of an OPC container.
- */
-#include <opc/config.h>
-#include <opc/file.h>
-#include <opc/container.h>
-
-#ifndef OPC_ZIP_H
-#define OPC_ZIP_H
-
-#ifdef __cplusplus
-extern "C" {
-#endif    
-
-    /**
-     Default growth hint of an OPC stream.
-     */
-    #define OPC_DEFAULT_GROWTH_HINT 512
-
-    /**
-     Handle to a ZIP archive.
-     \see internal.h
-     */
-    typedef struct OPC_ZIP_STRUCT opcZip;
-
-    /**
-      Handle to a raw ZIP input stream.
-     \see internal.h
-      */
-    typedef struct OPC_ZIPINPUTSTREAM_STRUCT opcZipInputStream;
-
-    /**
-      Handle to a raw ZIP output stream.
-     \see internal.h
-      */
-    typedef struct OPC_ZIPOUTPUTSTREAM_STRUCT opcZipOutputStream;
-
-    /**
-     Holds all information of a ZIP segment.
-     */
-    typedef struct OPC_ZIP_SEGMENT_INFO_STRUCT {
-        xmlChar name[OPC_MAX_PATH]; 
-        opc_uint32_t name_len;
-        opc_uint32_t segment_number;
-        opc_bool_t   last_segment;
-        opc_bool_t   rels_segment;
-        opc_uint32_t header_size;
-        opc_uint32_t min_header_size;
-        opc_uint32_t trailing_bytes;
-        opc_uint32_t compressed_size;
-        opc_uint32_t uncompressed_size;
-        opc_uint16_t bit_flag;
-        opc_uint32_t data_crc;
-        opc_uint16_t compression_method;
-        opc_ofs_t    stream_ofs;
-        opc_uint16_t growth_hint;
-    } opcZipSegmentInfo_t;
-
-    /**
-      \see opcZipLoader
-      */
-    typedef int opcZipLoaderOpenCallback(void *iocontext);
-    /**
-      \see opcZipLoader
-      */
-    typedef int opcZipLoaderSkipCallback(void *iocontext);
-    /**
-      \see opcZipLoader
-      */
-    typedef int opcZipLoaderReadCallback(void *iocontext, char *buffer, int len);
-    /**
-      \see opcZipLoader
-      */
-    typedef int opcZipLoaderCloseCallback(void *iocontext);
-
-    /**
-      \see opcZipLoader
-      */
-    typedef opc_error_t (opcZipLoaderSegmentCallback_t)(void *iocontext, void *userctx, opcZipSegmentInfo_t *info, opcZipLoaderOpenCallback *open, opcZipLoaderReadCallback *read, opcZipLoaderCloseCallback *close, opcZipLoaderSkipCallback *skip);
-
-    /**
-      Walks every segment in a ZIP archive and calls the \c segmentCallback callback method.
-      The implementer \c segmentCallback method must then eiher use the passed \c open, \c read and \c close methods
-      to read the stream or the passed \c skip methods to skip the stream.
-      This method can be used to e.g. read ZIP file in stream mode.
-      */
-    opc_error_t opcZipLoader(opcIO_t *io, void *userctx, opcZipLoaderSegmentCallback_t *segmentCallback);
-
-    /**
-      \see opcZipClose
-     */
-    typedef opc_error_t (opcZipSegmentReleaseCallback)(opcZip *zip, opc_uint32_t segment_id);
-
-    /** 
-     Closes the ZIP archive \c zip and will call \c releaseCallback for every segment to give the implementer a chance
-     to free user resources.
-     */
-    void opcZipClose(opcZip *zip, opcZipSegmentReleaseCallback* releaseCallback);
-
-    /**
-      Creates an empty ZIP archive with the given \c io.
-      */
-    opcZip *opcZipCreate(opcIO_t *io);
-
-    /**
-      Commits all buffers and writes the ZIP archives local header directories.
-      if \c trim is true then padding bytes will be removed, i.e. the ZIP file size fill be minimalized.
-     */
-    opc_error_t opcZipCommit(opcZip *zip, opc_bool_t trim);
-
-    /**
-      Garbage collection on the passed \c zip archive. This will e.g. make deleted files available as free space.
-      */
-    opc_error_t opcZipGC(opcZip *zip);
-
-    /**
-      Load segment information into \c info.
-      If \c rels_segment is -1 then load the info for part with name \c partName.
-      Otherwise load the segment information for the ".rels." segment of \c partName.
-      \return Returns the segment_id.
-      */
-    opc_uint32_t opcZipLoadSegment(opcZip *zip, const xmlChar *partName, opc_bool_t rels_segment, opcZipSegmentInfo_t *info);
-
-    /**
-      Create a segment with the given parameters.
-      \return Returns the segment_id.
-      */
-    opc_uint32_t opcZipCreateSegment(opcZip *zip, 
-                                     const xmlChar *partName, 
-                                     opc_bool_t relsSegment, 
-                                     opc_uint32_t segment_size, 
-                                     opc_uint32_t growth_hint,
-                                     opc_uint16_t compression_method,
-                                     opc_uint16_t bit_flag);
-
-    /**
-      Creates an input stream for the segment with \c segment_id.
-      \see opcZipLoadSegment
-      \see opcZipCreateSegment
-      */
-    opcZipInputStream *opcZipOpenInputStream(opcZip *zip, opc_uint32_t segment_id);
-
-    /**
-     Free all resources of the input stream.
-     */
-    opc_error_t opcZipCloseInputStream(opcZip *zip, opcZipInputStream *stream);
-
-    /**
-     Read maximal \c buf_len bytes from the input stream into \buf. 
-     \return Returns the number of bytes read.
-     */
-    opc_uint32_t opcZipReadInputStream(opcZip *zip, opcZipInputStream *stream, opc_uint8_t *buf, opc_uint32_t buf_len);
-
-
-    /**
-      Creates an output stream for the segment with \c segment_id.
-      If \c *segment_id is -1 then a new segment will be created. 
-      Otherwise the segment with \c *segment_id will be overwritten.
-     */
-    opcZipOutputStream *opcZipCreateOutputStream(opcZip *zip, 
-                                             opc_uint32_t *segment_id, 
-                                             const xmlChar *partName, 
-                                             opc_bool_t relsSegment, 
-                                             opc_uint32_t segment_size, 
-                                             opc_uint32_t growth_hint,
-                                             opc_uint16_t compression_method,
-                                             opc_uint16_t bit_flag);
-
-    /**
-      Opens an existing ouput stream for reading.
-      The \c *segment_id will be set to -1 and reset on opcZipCloseOutputStream.
-      \see opcZipCloseOutputStream
-     */
-    opcZipOutputStream *opcZipOpenOutputStream(opcZip *zip, opc_uint32_t *segment_id);
-
-    /** 
-      Will close the stream and free all resources. Additionally the new segment id will be stored in \c *segment_id.
-      \see opcZipOpenOutputStream
-      */
-    opc_error_t opcZipCloseOutputStream(opcZip *zip, opcZipOutputStream *stream, opc_uint32_t *segment_id);
-
-    /**
-     Write \c buf_len bytes to \c buf. 
-     \return Returns the number of bytes written.
-     */
-    opc_uint32_t opcZipWriteOutputStream(opcZip *zip, opcZipOutputStream *stream, const opc_uint8_t *buf, opc_uint32_t buf_len);
-
-    /**
-     Returns the first segment id or -1.
-     Use the following code to iterarte through all segments.
-     \code 
-     for(opc_uint32_t segment_id=opcZipGetFirstSegmentId(zip);
-         -1!=segment_id;
-         segment_id=opcZipGetNextSegmentId(zip, segment_id) {
-        ...
-     }
-     \endcode
-     \see opcZipGetNextSegmentId
-     */
-    opc_uint32_t opcZipGetFirstSegmentId(opcZip *zip);
-
-    /**
-     Returns the next segment id or -1.
-     \see opcZipGetFirstSegmentId
-     */
-    opc_uint32_t opcZipGetNextSegmentId(opcZip *zip, opc_uint32_t segment_id);
-
-    /**
-     Returns info about the given segment id.
-     */
-    opc_error_t opcZipGetSegmentInfo(opcZip *zip, opc_uint32_t segment_id, const xmlChar **name, opc_bool_t *rels_segment, opc_uint32_t *crc);
-
-    /**
-     Marks a given segments as deleted.
-     \see opcZipGC
-     */
-    opc_bool_t opcZipSegmentDelete(opcZip *zip, opc_uint32_t *first_segment, opc_uint32_t *last_segment, opcZipSegmentReleaseCallback* releaseCallback);
-
-#ifdef __cplusplus
-} /* extern "C" */
-#endif    
-        
-#endif /* OPC_ZIP_H */

include/plib/plib.h

@@ -1,168 +0,0 @@
-/* include/plib/plib.h.  Generated from plib.h by configure.  */
-/*
- Copyright (c) 2010, Florian Reuter
- 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.
- * Neither the name of Florian Reuter nor the names of its contributors 
-   may be used to endorse or promote products derived from this 
-   software without specific prior written permission.
- 
- 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.
- 
-*/
-#ifndef _PLIB_PLIB_H_
-#define _PLIB_PLIB_H_
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-#define HAVE_STDINT_H 1
-#define HAVE_STDDEF_H 1
-#define HAVE_STDIO_H 1
-#define HAVE_STRING_H 1
-#define HAVE_LIMITS_H 1
-#define HAVE_STDLIB_H 1
-/* #undef HAVE_IO_H */
-#define HAVE_UNISTD_H 1
-#define HAVE_SYS_TYPES_H 1
-#define IS_CONFIGURED 1
-
-#if !defined(IS_CONFIGURED)
-#if defined(WIN32)
-#define HAVE_STRING_H 1
-#define HAVE_STDINT_H 1
-#define HAVE_LIMITS_H 1
-#define HAVE_STDDEF_H 1
-#define HAVE_STDIO_H 1
-#define HAVE_STDLIB_H 1
-#define HAVE_IO_H
-#define snprintf _snprintf
-#else
-#error "configure not executed and we are not on a win32 machine? please run configure or define WIN32 is you are on a WIN32 platform."
-#endif
-#endif
-
-#ifdef HAVE_STDDEF_H
-#include <stddef.h>
-typedef size_t pofs_t; // maximum file offset for eg. read write ops
-#else
-#error "system types can not be determined"
-#endif
-
-#ifdef HAVE_STDIO_H
-#include <stdio.h>
-#else
-#error "system io can not be determined"
-#endif
-
-#ifdef HAVE_STDINT_H
-#include <stdint.h>
-
-typedef int8_t pint8_t;
-typedef uint8_t puint8_t;
-
-typedef int16_t pint16_t;
-typedef uint16_t puint16_t;
-
-typedef int32_t pint32_t;
-typedef uint32_t puint32_t;
-
-typedef int64_t pint64_t;
-typedef uint64_t puint64_t;
-
-typedef int pbool_t;
-
-typedef size_t psize_t;
-
-// INTN_MAX, INTN_MIN, UINTN_MAX
-#else
-#error "system types can not be determined"
-#endif
-
-#ifdef HAVE_STRING_H
-#include <string.h>
-#endif
-
-#ifdef HAVE_LIMITS_H
-#include <limits.h>
-#define PUINT8_MAX UCHAR_MAX 
-#define PINT32_MAX INT_MAX 
-#define PINT32_MIN INT_MIN 
-#define PUINT32_MAX UINT_MAX 
-#define PUINT32_MIN 0 
-#define PUINT16_MAX	USHRT_MAX 
-#define PUINT16_MIN 0 
-#else
-#error "limits can not be determined"
-#endif
-
-#ifdef HAVE_STDLIB_H
-#include <stdlib.h>
-#endif
-
-#ifdef HAVE_IO_H
-#include <io.h>
-#endif
-
-#ifdef HAVE_UNISTD_H
-#include <unistd.h>
-#endif
-
-#ifdef HAVE_SYS_TYPES_H
-#include <sys/types.h>
-#endif
-
-/**
- Converts an ASCII string to a xmlChar string. This only works for ASCII strings.
- */
-#ifndef _X
-#define _X(s) BAD_CAST(s) 
-#endif
-
-
-/**
- Converts an xmlChar string to an ASCII string. This only works for ASCII charsets.
- */
-#ifndef _X2C
-#define _X2C(s) ((char*)(s))
-#endif
-
-
-#define PASSERT(e) assert(e)
-#ifdef NDEBUG
-#define PENSURE(e) (void)(e)
-#else
-#define PENSURE(e) assert(e)
-#endif
-#define PTRUE (0==0)
-#define PFALSE (0==1)
-
-
-#ifdef __cplusplus
-} /* extern "C" */
-#endif
-
-
-#endif /* _PLIB_PLIB_H_ */

lib/bzip2-1.0.6

@@ -1 +0,0 @@
-Subproject commit 288acf97a15d558f96c24c89f578b724d6e06b0c

lib/ffmpeg

@@ -1 +0,0 @@
-Subproject commit 8887991a3109f94b7d019a11a86e6cd900105258

lib/harfbuzz

@@ -1 +0,0 @@
-Subproject commit b28c282585afd3bff844e84eae7f29e1a1267aef

lib/leptonica

@@ -1 +0,0 @@
-Subproject commit cc03be70fded1ad6a8cedad656456386a1bd08e8

lib/libmagic

@@ -1 +0,0 @@
-Subproject commit 1249b5cd02c3b6fb9b917d16c76bc76c862932b6

lib/libpng

@@ -1 +0,0 @@
-Subproject commit 301f7a14295a3bdfaf406dbb5004d0784dc137ea

lib/libtiff

@@ -1 +0,0 @@
-Subproject commit 3db0ff91bc6db20fc4cb035be366a9bbb4e701cf

lib/mupdf

@@ -1 +0,0 @@
-Subproject commit c50ac19e412fe7830dfef5d1cbc71e9da3405c96

lib/onion

@@ -1 +0,0 @@
-Subproject commit 73329b61eb82d65b827e92ab46b2db7da85163c7

lib/openjpeg

@@ -1 +0,0 @@
-Subproject commit ac3737372a00b8778b528094dd5bd58a74f67d42

lib/tesseract

@@ -1 +0,0 @@
-Subproject commit f268e6615e619a7140de78d9db3f8240fa8c68bd

lmdb

@@ -1 +0,0 @@
-Subproject commit 5c012bbe033f9bbb273078b07dded59f080d348d

schema/mappings.json

@@ -1,17 +1,47 @@
 {
   "properties": {
+    "_tie": {
+      "type": "keyword",
+      "doc_values": true
+    },
+    "checksum": {
+      "type": "keyword",
+      "index": false
+    },
+    "_depth": {
+      "type": "integer"
+    },
     "path": {
       "type": "text",
       "analyzer": "path_analyzer",
-      "copy_to": "suggest-path"
+      "copy_to": "suggest-path",
+      "fielddata": true,
+      "fields": {
+        "nGram": {
+          "type": "text",
+          "analyzer": "my_nGram"
+        },
+        "text": {
+          "type": "text",
+          "analyzer": "content_analyzer"
+        }
+      }
     },
     "suggest-path": {
       "type": "completion",
-      "analyzer": "keyword"
+      "analyzer": "case_insensitive_kw_analyzer"
     },
     "mime": {
       "type": "keyword"
     },
+    "parent": {
+      "type": "keyword",
+      "index": false
+    },
+    "thumbnail": {
+      "type": "integer",
+      "index": false
+    },
     "videoc": {
       "type": "keyword",
       "index": false
@@ -21,7 +51,7 @@
       "index": false
     },
     "duration": {
-      "type": "float",
+      "type": "integer",
       "index": false
     },
     "width": {
@@ -32,8 +62,13 @@
       "type": "integer",
       "index": false
     },
+    "pages": {
+      "type": "integer",
+      "index": false
+    },
     "mtime": {
-      "type": "integer"
+      "type": "date",
+      "format": "epoch_second"
     },
     "size": {
       "type": "long"
@@ -44,6 +79,7 @@
     "name": {
       "analyzer": "content_analyzer",
       "type": "text",
+      "fielddata": true,
       "fields": {
         "nGram": {
           "type": "text",
@@ -104,7 +140,108 @@
       }
     },
     "tag": {
+      "type": "text",
+      "fielddata": true,
+      "analyzer": "tag_analyzer",
+      "copy_to": "suggest-tag"
+    },
+    "suggest-tag": {
+      "type": "completion",
+      "analyzer": "case_insensitive_kw_analyzer"
+    },
+    "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"
+    },
+    "exif_gps_longitude_ref": {
+      "type": "keyword",
+      "index": false
+    },
+    "exif_gps_longitude_dms": {
+      "type": "keyword",
+      "index": false
+    },
+    "exif_gps_longitude_dec": {
+      "type": "keyword",
+      "index": false
+    },
+    "exif_gps_latitude_ref": {
+      "type": "keyword",
+      "index": false
+    },
+    "exif_gps_latitude_dms": {
+      "type": "keyword",
+      "index": false
+    },
+    "exif_gps_latitude_dec": {
+      "type": "keyword",
+      "index": false
+    },
+    "author": {
+      "type": "text"
+    },
+    "modified_by": {
+      "type": "text"
+    },
+    "emb.384.*": {
+      "type": "dense_vector",
+      "dims": 384
+    },
+    "emb.idx_384.*": {
+      "type": "dense_vector",
+      "dims": 384,
+      "index": true,
+      "similarity": "cosine"
+    },
+    "emb.idx_512.clip": {
+      "type": "dense_vector",
+      "dims": 512,
+      "index": true,
+      "similarity": "cosine"
+    },
+    "emb.512.*": {
+      "type": "dense_vector",
+      "dims": 512
+    },
+    "emb.idx_768.*": {
+      "type": "dense_vector",
+      "dims": 768,
+      "index": true,
+      "similarity": "cosine"
+    },
+    "emb.768.*": {
+      "type": "dense_vector",
+      "dims": 768
+    },
+    "emb.idx_1024.*": {
+      "type": "dense_vector",
+      "dims": 1024,
+      "index": true,
+      "similarity": "cosine"
+    },
+    "emb.1024.*": {
+      "type": "dense_vector",
+      "dims": 1024
     }
   }
 }

schema/pipeline.json

@@ -0,0 +1,10 @@
+{
+  "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();"
+      }
+    }
+  ]
+}

schema/settings.json

@@ -1,15 +1,22 @@
 {
   "index": {
     "refresh_interval": "30s",
-    "codec": "best_compression"
+    "codec": "best_compression",
+    "number_of_replicas": 0,
+    "highlight.max_analyzed_offset": 1000000
   },
   "analysis": {
     "tokenizer": {
       "path_tokenizer": {
-        "type": "path_hierarchy"
+        "type": "path_hierarchy",
+        "delimiter": "/"
+      },
+      "tag_tokenizer": {
+        "type": "path_hierarchy",
+        "delimiter": "."
       },
       "my_nGram_tokenizer": {
-        "type": "nGram",
+        "type": "ngram",
         "min_gram": 3,
         "max_gram": 3
       }
@@ -21,6 +28,18 @@
           "lowercase"
         ]
       },
+      "tag_analyzer": {
+        "tokenizer": "tag_tokenizer",
+        "filter": [
+          "lowercase"
+        ]
+      },
+      "case_insensitive_kw_analyzer": {
+        "tokenizer": "keyword",
+        "filter": [
+          "lowercase"
+        ]
+      },
       "my_nGram": {
         "tokenizer": "my_nGram_tokenizer",
         "filter": [

schema/settings_legacy.json

@@ -0,0 +1,58 @@
+{
+  "index": {
+    "refresh_interval": "30s",
+    "codec": "best_compression",
+    "number_of_replicas": 0
+  },
+  "analysis": {
+    "tokenizer": {
+      "path_tokenizer": {
+        "type": "path_hierarchy",
+        "delimiter": "/"
+      },
+      "tag_tokenizer": {
+        "type": "path_hierarchy",
+        "delimiter": "."
+      },
+      "my_nGram_tokenizer": {
+        "type": "nGram",
+        "min_gram": 3,
+        "max_gram": 3
+      }
+    },
+    "analyzer": {
+      "path_analyzer": {
+        "tokenizer": "path_tokenizer",
+        "filter": [
+          "lowercase"
+        ]
+      },
+      "tag_analyzer": {
+        "tokenizer": "tag_tokenizer",
+        "filter": [
+          "lowercase"
+        ]
+      },
+      "case_insensitive_kw_analyzer": {
+        "tokenizer": "keyword",
+        "filter": [
+          "lowercase"
+        ]
+      },
+      "my_nGram": {
+        "tokenizer": "my_nGram_tokenizer",
+        "filter": [
+          "lowercase",
+          "asciifolding"
+        ]
+      },
+      "content_analyzer": {
+        "tokenizer": "standard",
+        "filter": [
+          "lowercase",
+          "asciifolding"
+        ]
+      }
+    }
+  }
+}

scripts/before_build.sh

@@ -1,17 +1,13 @@
 #!/usr/bin/env bash
 
-rm -rf index.sist2/
+(
+  cd ..
+  rm -rf index.sist2
 
-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
+  python3 scripts/mime.py > src/parsing/mime_generated.c
+  python3 scripts/serve_static.py > src/web/static_generated.c
+  python3 scripts/index_static.py > src/index/static_generated.c
+  python3 scripts/magic_static.py > src/magic_generated.c
 
-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
-python3 scripts/index_static.py > src/index/static_generated.c
+  printf "static const char *const Sist2CommitHash = \"%s\";\n" $(git rev-parse HEAD) > src/git_hash.h
+)

scripts/build.sh

@@ -0,0 +1,35 @@
+#!/usr/bin/env bash
+
+VCPKG_ROOT="/vcpkg"
+
+(
+  cd sist2-vue/
+  npm install
+  npm run build
+) &
+
+(
+  cd sist2-admin/frontend/
+  npm install
+  npm run build
+) &
+
+wait
+
+mkdir build
+(
+  cd build
+  cmake -DSIST_PLATFORM=x64_linux -DSIST_DEBUG_INFO=on -DSIST_DEBUG=off -DBUILD_TESTS=off -DCMAKE_TOOLCHAIN_FILE="${VCPKG_ROOT}/scripts/buildsystems/vcpkg.cmake" ..
+  make -j $(nproc)
+  strip sist2
+  ./sist2 -v > VERSION
+)
+mv build/sist2 sist2-x64-linux
+
+(
+  cd build
+  rm -rf CMakeFiles CMakeCache.txt
+  cmake -DSIST_PLATFORM=x64_linux -DSIST_DEBUG_INFO=on -DSIST_DEBUG=on -DBUILD_TESTS=off -DCMAKE_TOOLCHAIN_FILE="${VCPKG_ROOT}/scripts/buildsystems/vcpkg.cmake" ..
+  make -j  $(nproc)
+)
+mv build/sist2_debug sist2-x64-linux-debug

scripts/build_arm64.sh

@@ -0,0 +1,36 @@
+#!/usr/bin/env bash
+
+VCPKG_ROOT="/vcpkg"
+
+git submodule update --init --recursive
+
+(
+  cd sist2-vue/
+  npm install
+  npm run build
+) &
+
+(
+  cd sist2-admin/frontend/
+  npm install
+  npm run build
+) &
+
+wait
+
+mkdir build
+(
+  cd build
+  cmake -DSIST_PLATFORM=arm64_linux -DSIST_DEBUG_INFO=on -DSIST_DEBUG=off -DBUILD_TESTS=off -DCMAKE_TOOLCHAIN_FILE="${VCPKG_ROOT}/scripts/buildsystems/vcpkg.cmake" ..
+  make -j $(nproc)
+  strip sist2
+)
+mv build/sist2 sist2-arm64-linux
+
+rm -rf CMakeFiles CMakeCache.txt
+(
+  cd build
+  cmake -DSIST_PLATFORM=arm64_linux -DSIST_DEBUG_INFO=on -DSIST_DEBUG=on -DBUILD_TESTS=off -DCMAKE_TOOLCHAIN_FILE="${VCPKG_ROOT}/scripts/buildsystems/vcpkg.cmake" ..
+  make -j $(nproc)
+)
+mv build/sist2_debug sist2-arm64-linux-debug

scripts/get_static_libs.sh

@@ -1,117 +0,0 @@
-#!/usr/bin/env bash
-
-THREADS=$(nproc)
-
-cd lib
-
-cd mupdf
-CFLAGS=-fPIC make USE_SYSTEM_HARFBUZZ=yes USE_SYSTEM_OPENJPEG=yes HAVE_X11=no HAVE_GLUT=no -j $THREADS
-cd ..
-
-mv mupdf/build/release/libmupdf.a .
-mv mupdf/build/release/libmupdf-third.a .
-
-# openjp2
-cd openjpeg
-cmake . -DCMAKE_BUILD_TYPE=Release -DCMAKE_C_FLAGS="-O3 -march=native -DNDEBUG -fPIC"
-make -j $THREADS
-cd ..
-mv openjpeg/bin/libopenjp2.a .
-
-# harfbuzz
-cd harfbuzz
-./autogen.sh
-CFLAGS=-fPIC ./configure --disable-shared --enable-static
-make -j $THREADS
-cd ..
-mv harfbuzz/src/.libs/libharfbuzz.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\
- --extra-cflags=-fPIC
-make -j $THREADS
-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 $THREADS
-cd ../..
-
-mv onion/build/src/onion/libonion_static.a .
-
-#bzip2
-cd bzip2-1.0.6
-make -j $THREADS
-cd ..
-mv bzip2-1.0.6/libbz2.a .
-
-# magic
-cd libmagic
-./autogen.sh
-./configure --enable-static --disable-shared
-make -j $THREADS
-cd ..
-mv libmagic/src/.libs/libmagic.a .
-
-# tesseract
-cd tesseract
-mkdir build
-cd build
-cmake -DSTATIC=on -DBUILD_TRAINING_TOOLS=off -DBUILD_TESTS=off -DCMAKE_BUILD_TYPE=Release \
-  -DCMAKE_CXX_FLAGS="-fPIC"  ..
-make -j $THREADS
-cd ../..
-mv tesseract/build/libtesseract.a .
-
-# leptonica
-cd leptonica
-./autogen.sh
-CFLAGS="-fPIC" ./configure --without-zlib --without-jpeg --without-giflib \
-  --without-giflib --without-libwebp --without-libwebpmux --without-libopenjpeg \
-  --enable-static --disable-shared
-make -j $THREADS
-cd ..
-mv leptonica/src/.libs/liblept.a .
-
-# tiff
-cd libtiff
-./autogen.sh
-CFLAGS="-fPIC" CXXFLAGS="-fPIC" CXX_FLAGS="-fPIC" ./configure --enable-static --disable-shared --disable-lzw --disable-jpeg --disable-webp \
-  --disable-lzma --disable-zstd --disable-jbig
-make -j $THREADS
-cd ..
-mv libtiff/libtiff/.libs/libtiff.a .
-
-# png
-cd libpng
-CFLAGS="-fPIC" ./configure --enable-static --disable-shared
-make -j $THREADS
-cd ..
-mv libpng/.libs/libpng16.a .
-
-# curl
-wget -nc https://curl.haxx.se/download/curl-7.68.0.tar.gz
-tar -xzf curl-7.68.0.tar.gz
-cd curl-7.68.0
-./configure --disable-ldap --disable-ldaps --without-librtmp --disable-rtsp --disable-crypto-auth \
-  --disable-smtp --enable-static --disable-shared
-make -j $THREADS
-cd ..
-mv curl-7.68.0/lib/.libs/libcurl.a .

scripts/index_static.py

@@ -1,6 +1,10 @@
+import json
+
 files = [
     "schema/mappings.json",
     "schema/settings.json",
+    "schema/settings_legacy.json",
+    "schema/pipeline.json",
 ]
 
 
@@ -9,6 +13,7 @@ def clean(filepath):
 
 
 for file in files:
-    with open(file, "rb") as f:
-        data = f.read()
+    with open(file, "r") as f:
+        data = json.dumps(json.load(f), separators=(",", ":")).encode()
+    data += b'\0'
     print("char %s[%d] = {%s};" % (clean(file), len(data), ",".join(str(int(b)) for b in data)))

scripts/magic_static.py

@@ -0,0 +1,16 @@
+
+MAGIC_PATHS = [
+    "/vcpkg/installed/x64-linux/share/libmagic/misc/magic.mgc",
+    "/work/vcpkg/installed/x64-linux/share/libmagic/misc/magic.mgc",
+    "/usr/lib/file/magic.mgc"
+]
+
+for path in MAGIC_PATHS:
+    try:
+        with open(path, "rb") as f:
+            data = f.read()
+        break
+    except:
+        continue
+
+print("char magic_database_buffer[%d] = {%s};" % (len(data), ",".join(str(int(b)) for b in data)))

scripts/mime.csv

@@ -1,15 +1,20 @@
+application/x-matlab-data,mat
 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
-application/gzip, gz
+application/gzip, gz|tgz
 application/hta, hta
 application/i-deas, unv
 application/iges, iges|igs
@@ -17,17 +22,19 @@ application/inf, inf
 application/java-archive, jar
 application/java, class
 application/javascript,
-application/x-archive, a
 application/json, json
+application/ndjson, jsonl|ndjson
 application/marc, mrc
 application/mbedlet, mbd
 application/mime, aps
 application/mspowerpoint, ppz
 application/msword, doc|dot|w6w|wiz|word
 application/netmc, mcp
-application/octet-stream, bin|dump|gpg
+application/octet-stream, bin|dump|gpg|pack|idx
 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
@@ -43,6 +50,10 @@ 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
@@ -54,45 +65,73 @@ 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/wordperfect6.0, w60
-application/wordperfect6.1, w61
-application/wordperfect, wp|wp5|wp6|wpd
+application/warc, warc
+application/winhelp, hlp
+application/wordperfect, wp|wp5|wp6|wpd|w60|w61
 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-director, 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
@@ -102,46 +141,67 @@ 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-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
@@ -149,12 +209,17 @@ 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
@@ -163,24 +228,33 @@ 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/mpeg, m2a|mpa
+audio/mp4, m4b
+audio/mpeg, m2a|mpa|mpga
 audio/ogg, ogg
 audio/s3m, s3m
 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
@@ -194,17 +268,24 @@ 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
@@ -213,6 +294,9 @@ 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
@@ -220,9 +304,15 @@ 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
@@ -236,32 +326,33 @@ 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/tiff,
+image/x-win-bitmap,
 !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/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/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|make|log|markdown|yaml
+text/x-script.python, pyx
+text/csv,
+application/vnd.coffeescript, coffee
 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
@@ -273,6 +364,7 @@ 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++
@@ -287,23 +379,31 @@ 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-python, py
+text/x-po, po
+text/x-python, py|pyi
 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
@@ -318,101 +418,35 @@ 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
+video/x-ms-asf, asf|asx|wmv
+video/x-msvideo, divx
 video/x-qtc, qtc
 video/x-sgi-movie, movie|mv
-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
-application/x-atari-7800-rom, a78
-application/x-nes-rom, nes
-application/x-font-pfm, pfm
-application/x-gettext-translation,
-image/wmf,
-application/pgp-keys,
-image/x-3ds, 3ds
-application/x-lz4, lz4
-application/vnd.openxmlformats-officedocument.presentationml.presentation, pptx
-application/vnd.oasis.opendocument.presentation, odp
-application/x-msaccess, accdb
-application/vnd.oasis.opendocument.spreadsheet, ods
-audio/x-aiff, aiff|aif
-text/x-ms-regedit, reg
-application/x-gamecube-rom,
-application/x-nintendo-ds-rom,
-text/x-objective-c,
-application/x-font-gdos,
-application/x-apple-diskimage,
-application/x-zstd, zst
-video/x-m4v, m4v
-message/news,
-application/vnd.symbian.install,
-application/x-lzh-compressed,
-application/x-dosdriver,
-application/vnd.tcpdump.pcap, pcap
 x-epoc/x-sisx-app,
-application/x-avira-qua,
-video/MP2T,
-application/x-snappy-framed,
-application/x-lz4+json, jsonlz4
-application/x-dmp, dmp
-application/zlib, z
-application/x-pgp-keyring,
-application/x-gdbm,
-application/x-font-pf2, pf2
-application/x-zip,
-application/x-coredump,
-application/x-java-jmod, jmod
-application/x-terminfo,
-application/x-terminfo2,
-application/x-arc,
-application/vnd.lotus-1-2-3,
-image/x-win-bitmap,
-application/x-maxis-dbpf,
-text/PGP,
-audio/x-hx-aac-adts,
-application/x-chrome-extension,
-image/heic, heic
-image/x-gem,
-application/x-lzma, lzma
-application/warc, warc
-application/x-lz4, lz4
-application/x-lzip, lz
-application/x-lzop, lzo
+application/x-zstd-dictionary,
+application/vnd.ms-outlook, msg
+image/x-olympus-orf, orf
+image/x-nikon-nef, nef
+image/x-fuji-raf, raf
+image/x-panasonic-raw, rw2|raw
+image/x-adobe-dng, dng
+image/x-canon-cr2, cr2
+image/x-canon-crw, crw
+image/x-dcraw,
+image/x-kodak-dcr, dcr
+image/x-kodak-k25, k25
+image/x-kodak-kdc, kdc
+image/x-minolta-mrw, mrw
+image/x-pentax-pef, pef
+image/x-sigma-x3f, xf3
+image/x-sony-arw, arw
+image/x-sony-sr2, sr2
+image/x-sony-srf, srf
+image/x-epson-erf, erf

scripts/mime.py

@@ -1,8 +1,12 @@
+import zlib
+
 mimes = {}
 noparse = set()
 ext_in_hash = set()
+mime_ids = {}
 
 major_mime = {
+    "sist2": 0,
     "model": 1,
     "example": 2,
     "message": 3,
@@ -18,7 +22,6 @@ major_mime = {
 
 pdf = (
     "application/pdf",
-    "application/x-cbz",
     "application/epub+zip",
     "application/vnd.ms-xpsdocument",
 )
@@ -62,10 +65,47 @@ doc = (
     "application/vnd.openxmlformats-officedocument.presentationml.presentation"
 )
 
+mobi = (
+    "application/x-mobipocket-ebook",
+    "application/vnd.amazon.mobi8-ebook"
+)
+
+markup = (
+    "text/xml",
+    "text/html",
+    "text/x-sgml"
+)
+
+raw = (
+    "image/x-olympus-orf",
+    "image/x-nikon-nef",
+    "image/x-fuji-raf",
+    "image/x-panasonic-raw",
+    "image/x-adobe-dng",
+    "image/x-canon-cr2",
+    "image/x-canon-crw",
+    "image/x-dcraw",
+    "image/x-kodak-dcr",
+    "image/x-kodak-k25",
+    "image/x-kodak-kdc",
+    "image/x-minolta-mrw",
+    "image/x-pentax-pef",
+    "image/x-sigma-x3f",
+    "image/x-sony-arw",
+    "image/x-sony-sr2",
+    "image/x-sony-srf",
+    "image/x-minolta-mrw",
+    "image/x-pentax-pef",
+    "image/x-epson-erf",
+)
+
 cnt = 1
 
 
 def mime_id(mime):
+    if mime in mime_ids:
+        return mime_ids[mime]
+
     global cnt
     major = mime.split("/")[0]
     mime_id = str((major_mime[major] << 16) + cnt)
@@ -82,8 +122,16 @@ def mime_id(mime):
         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 in raw:
+        mime_id += " | 0x00800000"
     elif mime == "application/x-empty":
+        cnt -= 1
         return "1"
+    mime_ids[mime] = mime_id
     return mime_id
 
 
@@ -91,24 +139,40 @@ def clean(t):
     return t.replace("/", "_").replace(".", "_").replace("+", "_").replace("-", "_")
 
 
-with open("mime.csv") as f:
+def crc(s):
+    return zlib.crc32(s.encode()) & 0xffffffff
+
+
+with open("scripts/mime.csv") as f:
     for l in f:
         mime, ext_list = l.split(",")
         if l.startswith("!"):
             mime = mime[1:]
             noparse.add(mime)
-        ext = [x.strip() for x in ext_list.split("|")]
+        ext = [x.strip() for x in ext_list.split("|") if x.strip() != ""]
         mimes[mime] = ext
 
+    seen_crc = set()
+    for ext in mimes.values():
+        for e in ext:
+            if crc(e) in seen_crc:
+                raise Exception("CRC32 collision")
+            seen_crc.add(crc(e))
+
+    seen_crc = set()
+    for mime in mimes.keys():
+        if crc(mime) in seen_crc:
+            raise Exception("CRC32 collision")
+        seen_crc.add(crc(mime))
+
     print("// **Generated by mime.py**")
     print("#ifndef MIME_GENERATED_C")
     print("#define MIME_GENERATED_C")
-    print("#include <glib-2.0/glib.h>\n")
     print("#include <stdlib.h>\n")
     # Enum
     print("enum mime {")
     for mime, ext in sorted(mimes.items()):
-        print("    " + clean(mime) + "=" + mime_id(mime) + ",")
+        print(f"{clean(mime)}={mime_id(mime)},")
     print("};")
 
     # Enum -> string
@@ -119,20 +183,28 @@ with open("mime.csv") as f:
     print("default: return NULL;}}")
 
     # Ext -> Enum
-    print("GHashTable *mime_get_ext_table() {"
-          "GHashTable *ext_table = g_hash_table_new(g_str_hash, g_str_equal);")
+    print("unsigned int mime_extension_lookup(unsigned long extension_crc32) {"
+          "switch (extension_crc32) {")
     for mime, ext in mimes.items():
-        for e in [e for e in ext if e]:
-            print("g_hash_table_insert(ext_table, \"" + e + "\", (gpointer)" + clean(mime) + ");")
-            if e in ext_in_hash:
-                raise Exception("extension already in hash: " + e)
-            ext_in_hash.add(e)
-    print("return ext_table;}")
+        if len(ext) > 0:
+            for e in ext:
+                print(f"case {crc(e)}:", end="")
+            print(f"return {clean(mime)};")
+    print("default: return 0;}}")
 
     # string -> Enum
-    print("GHashTable *mime_get_mime_table() {"
-          "GHashTable *mime_table = g_hash_table_new(g_str_hash, g_str_equal);")
-    for mime, ext in mimes.items():
-        print("g_hash_table_insert(mime_table, \"" + mime + "\", (gpointer)" + clean(mime) + ");")
-    print("return mime_table;}")
+    print("unsigned int mime_name_lookup(unsigned long mime_crc32) {"
+          "switch (mime_crc32) {")
+    for mime in mimes.keys():
+        print(f"case {crc(mime)}: return {clean(mime)};")
+
+    print("default: return 0;}}")
+
+    # mime list
+
+    mime_list = ",".join(mime_id(x) for x in mimes.keys()) + ",0"
+
+    print(f"unsigned int mime_ids[] = {{{mime_list}}};")
+    print("unsigned int* get_mime_ids() { return mime_ids; }")
+
     print("#endif")

scripts/serve_static.py

@@ -1,10 +1,10 @@
 files = [
-    "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",
+    "sist2-vue/src/assets/favicon.ico",
+    "sist2-vue/dist/css/chunk-vendors.css",
+    "sist2-vue/dist/css/index.css",
+    "sist2-vue/dist/js/chunk-vendors.js",
+    "sist2-vue/dist/js/index.js",
+    "sist2-vue/dist/index.html",
 ]
 
 
@@ -13,6 +13,10 @@ def clean(filepath):
 
 
 for file in files:
+    try:
         with open(file, "rb") as f:
             data = f.read()
+    except:
+        data = bytes([])
+
     print("char %s[%d] = {%s};" % (clean(file), len(data), ",".join(str(int(b)) for b in data)))

scripts/sqlite_extension.c

@@ -0,0 +1,84 @@
+#include <sqlite3ext.h>
+#include <string.h>
+#include <stdlib.h>
+
+SQLITE_EXTENSION_INIT1
+
+static int sep_rfind(const char *str) {
+    for (int i = (int) strlen(str); i >= 0; i--) {
+        if (str[i] == '/') {
+            return i;
+        }
+    }
+    return -1;
+}
+
+void path_parent_func(sqlite3_context *ctx, int argc, sqlite3_value **argv) {
+    if (argc != 1 || sqlite3_value_type(argv[0]) != SQLITE_TEXT) {
+        sqlite3_result_error(ctx, "Invalid parameters", -1);
+    }
+
+    const char *value = (const char *) sqlite3_value_text(argv[0]);
+
+    int stop = sep_rfind(value);
+    if (stop == -1) {
+        sqlite3_result_null(ctx);
+        return;
+    }
+    char parent[4096 * 3];
+    strncpy(parent, value, stop);
+
+    sqlite3_result_text(ctx, parent, stop, SQLITE_TRANSIENT);
+}
+
+void random_func(sqlite3_context *ctx, int argc, sqlite3_value **argv) {
+    if (argc != 1 || sqlite3_value_type(argv[0]) != SQLITE_INTEGER) {
+        sqlite3_result_error(ctx, "Invalid parameters", -1);
+    }
+
+    char state_buf[32] = {0,};
+    struct random_data buf;
+    int result;
+
+    long seed = sqlite3_value_int64(argv[0]);
+
+    initstate_r((int) seed, state_buf, sizeof(state_buf), &buf);
+
+    random_r(&buf, &result);
+
+    sqlite3_result_int(ctx, result);
+}
+
+
+int sqlite3_extension_init(
+        sqlite3 *db,
+        char **pzErrMsg,
+        const sqlite3_api_routines *pApi
+) {
+    SQLITE_EXTENSION_INIT2(pApi);
+
+
+    sqlite3_create_function(
+            db,
+            "path_parent",
+            1,
+            SQLITE_UTF8,
+            NULL,
+            path_parent_func,
+            NULL,
+            NULL
+    );
+
+    sqlite3_create_function(
+            db,
+            "random_seeded",
+            1,
+            SQLITE_UTF8,
+            NULL,
+            random_func,
+            NULL,
+            NULL
+    );
+
+    return SQLITE_OK;
+}

scripts/sqlite_extension_compile.sh

@@ -0,0 +1 @@
+gcc -I/mnt/work/vcpkg/installed/x64-linux/include -g -fPIC -shared sqlite_extension.c -o sist2funcs.so

scripts/start_dev_es.sh

@@ -0,0 +1,3 @@
+docker run --rm -it --name "sist2-dev-es3"\
+       	-p 9200:9200 -e "discovery.type=single-node" \
+	-e "ES_JAVA_OPTS=-Xms8g -Xmx8g" elasticsearch:7.17.9

scripts/start_dev_es_6.sh

@@ -0,0 +1,3 @@
+docker run --rm -it --name "sist2-dev-es-6"\
+       	-p 9202:9200 -e "discovery.type=single-node" \
+	-e "ES_JAVA_OPTS=-Xms8g -Xmx8g" elasticsearch:6.8.0

scripts/start_dev_es_8.sh

@@ -0,0 +1,3 @@
+docker run --rm -it --name "sist2-dev-es3"\
+       	-p 9200:9200 -p 9300:9300 -e "discovery.type=single-node" \
+	-e "ES_JAVA_OPTS=-Xms8g -Xmx8g" elasticsearch:8.7.0

scripts/test_in_docker.sh

@@ -0,0 +1,7 @@
+docker build . -t tmp
+
+docker run --rm -it\
+  -v $(pwd):/host \
+  tmp \
+  scan --ocr-lang eng --ocr-ebooks -t6 --incremental --very-verbose \
+  -o /host/docker.sist2 /host/third-party/libscan/libscan-test-files/test_files/

sist2-admin/frontend/babel.config.js

@@ -0,0 +1,5 @@
+module.exports = {
+  presets: [
+    '@vue/cli-plugin-babel/preset'
+  ]
+}

sist2-admin/frontend/package.json

@@ -0,0 +1,49 @@
+{
+  "name": "sist2-admin-vue",
+  "version": "0.1.0",
+  "private": true,
+  "scripts": {
+    "serve": "vue-cli-service serve",
+    "build": "vue-cli-service build",
+    "watch": "vue-cli-service build --watch"
+  },
+  "dependencies": {
+    "axios": "^1.6.0",
+    "bootstrap-vue": "^2.21.2",
+    "core-js": "^3.6.5",
+    "moment": "^2.29.3",
+    "socket.io-client": "^4.5.1",
+    "vue": "^2.6.14",
+    "vue-i18n": "^8.24.4",
+    "vue-router": "^3.5.4",
+    "vuex": "^3.4.0"
+  },
+  "devDependencies": {
+    "@vue/cli-plugin-babel": "~5.0.8",
+    "@vue/cli-plugin-router": "~5.0.8",
+    "@vue/cli-plugin-vuex": "~5.0.8",
+    "@vue/cli-service": "~5.0.8",
+    "babel-eslint": "^10.1.0",
+    "bootstrap": "^4.5.2",
+    "vue-template-compiler": "^2.6.11"
+  },
+  "eslintConfig": {
+    "root": true,
+    "env": {
+      "node": true
+    },
+    "extends": [
+      "plugin:vue/essential",
+      "eslint:recommended"
+    ],
+    "parserOptions": {
+      "parser": "babel-eslint"
+    },
+    "rules": {}
+  },
+  "browserslist": [
+    "> 1%",
+    "last 2 versions",
+    "not dead"
+  ]
+}