Fix build problems...

maybe a typo in cli.c

.gitignore

@@ -15,3 +15,4 @@ bundle*.css
 bundle.js
 *.a
 vgcore.*
+build/

.gitmodules

@@ -31,15 +31,9 @@
 [submodule "lib/mupdf"]
 	path = lib/mupdf
 	url = git://git.ghostscript.com/mupdf.git
-[submodule "lib/zstd"]
-	path = lib/zstd
-	url = https://github.com/facebook/zstd
-[submodule "lib/lz4"]
-	path = lib/lz4
-	url = https://github.com/lz4/lz4
-[submodule "lib/libarchive"]
-	path = lib/libarchive
-	url = https://github.com/libarchive/libarchive
-[submodule "lib/libxml2"]
-	path = lib/libxml2
-	url = https://github.com/GNOME/libxml2
+[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

.teamcity/settings.kts

@@ -0,0 +1,69 @@
+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

@@ -1,95 +1,57 @@
 cmake_minimum_required(VERSION 3.7)
 set(CMAKE_C_STANDARD 11)
 
-option(WITH_SIST2 "Build main executable" ON)
-option(WITH_SIST2_SCAN "Build scan executable" ON)
-
 project(sist2 C)
 list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_LIST_DIR}/CMakeModules")
 
-if (WITH_SIST2)
-    add_executable(
-            sist2
-            src/main.c
-            src/sist.h
-            src/io/walk.h src/io/walk.c
-            src/parsing/media.h src/parsing/media.c
-            src/parsing/pdf.h src/parsing/pdf.c
-            src/io/store.h src/io/store.c
-            src/tpool.h src/tpool.c
-            src/parsing/parse.h src/parsing/parse.c
-            src/io/serialize.h src/io/serialize.c
-            src/parsing/mime.h src/parsing/mime.c src/parsing/mime_generated.c
-            src/parsing/text.h src/parsing/text.c
-            src/index/web.c src/index/web.h
-            src/web/serve.c src/web/serve.h
-            src/web/auth_basic.h src/web/auth_basic.c
-            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
+add_executable(
+        sist2
+        src/main.c
+        src/sist.h
+        src/io/walk.h src/io/walk.c
+        src/parsing/media.h src/parsing/media.c
+        src/parsing/pdf.h src/parsing/pdf.c
+        src/io/store.h src/io/store.c
+        src/tpool.h src/tpool.c
+        src/parsing/parse.h src/parsing/parse.c
+        src/io/serialize.h src/io/serialize.c
+        src/parsing/mime.h src/parsing/mime.c src/parsing/mime_generated.c
+        src/parsing/text.h src/parsing/text.c
+        src/index/web.c src/index/web.h
+        src/web/serve.c src/web/serve.h
+        src/web/auth_basic.h src/web/auth_basic.c
+        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/log.c src/log.h
 
-            # argparse
-            argparse/argparse.h argparse/argparse.c
+        # argparse
+        argparse/argparse.h argparse/argparse.c
 
-            # cJSON
-            cJSON/cJSON.h cJSON/cJSON.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
+        # 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
 
-            # utf8.h
-            utf8.h/utf8.h
-            src/parsing/arc.c src/parsing/arc.h src/parsing/doc.c src/parsing/doc.h)
-endif ()
-
-if (WITH_SIST2_SCAN)
-    add_executable(
-            sist2_scan
-            src/main.c
-            src/sist.h
-            src/io/walk.h src/io/walk.c
-            src/parsing/media.h src/parsing/media.c
-            src/parsing/pdf.h src/parsing/pdf.c
-            src/io/store.h src/io/store.c
-            src/tpool.h src/tpool.c
-            src/parsing/parse.h src/parsing/parse.c
-            src/io/serialize.h src/io/serialize.c
-            src/parsing/mime.h src/parsing/mime.c src/parsing/mime_generated.c
-            src/parsing/text.h src/parsing/text.c
-            src/util.c src/util.h
-            src/ctx.h src/types.h src/parsing/font.c src/parsing/font.h
-
-            # 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
-
-            # utf8.h
-            utf8.h/utf8.h
-            src/parsing/arc.c src/parsing/arc.h src/parsing/doc.c src/parsing/doc.h)
-endif ()
+        # utf8.h
+        utf8.h/utf8.h
+)
 
 find_package(PkgConfig REQUIRED)
 set(ENV{PKG_CONFIG_PATH} "$ENV{PKG_CONFIG_PATH}:/usr/local/lib/pkgconfig/")
 
-find_package(LibMagic REQUIRED)
-find_package(FFmpeg REQUIRED)
-find_package(OpenSSL REQUIRED)
+#find_package(OpenSSL REQUIRED)
 find_package(Freetype REQUIRED)
 
 pkg_check_modules(GLIB REQUIRED glib-2.0)
 pkg_check_modules(GOBJECT REQUIRED gobject-2.0)
 pkg_check_modules(UUID REQUIRED uuid)
 
-add_definitions(${LIBMAGIC_CFLAGS_OTHER})
 add_definitions(${UUID_CFLAGS_OTHER})
 add_definitions(${GLIB_CFLAGS_OTHER})
 add_definitions(${GOBJECT_CFLAGS_OTHER})
@@ -99,166 +61,80 @@ list(REMOVE_ITEM GLIB_LIBRARIES pcre)
 list(REMOVE_ITEM GOBJECT_LIBRARIES pcre)
 list(REMOVE_ITEM UUID_LIBRARIES pcre)
 
-if (WITH_SIST2)
-    target_include_directories(
-            sist2 PUBLIC
-            ${LIBMAGIC_INCLUDE_DIRS}
-            ${GOBJECT_INCLUDE_DIRS}
-            ${OPENSSL_INCLUDE_DIR}
-            ${FFMPEG_INCLUDE_DIRS}
-            ${GLIB_INCLUDE_DIRS}
-            ${FREETYPE_INCLUDE_DIRS}
-            ${UUID_INCLUDE_DIRS}
-            ${PROJECT_SOURCE_DIR}/
-            ${PROJECT_SOURCE_DIR}/lmdb/libraries/liblmdb/
-            ${PROJECT_SOURCE_DIR}/lib/onion/src/
-            ${PROJECT_SOURCE_DIR}/lib/mupdf/include/
-            ${PROJECT_SOURCE_DIR}/include/
-            /usr/include/libxml2/
-    )
-    target_link_directories(
-            sist2 PUBLIC
-            ${UUID_LIBRARY_DIRS}
-            ${FFMPEG_LIBRARY_DIRS}
-    )
+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}
+)
 
+target_compile_options(sist2
+        PRIVATE
+        -Ofast
+        # -march=native
+        -fno-stack-protector
+        -fomit-frame-pointer
+        )
 
-    target_compile_options(sist2
-            PRIVATE
-            -Ofast
-#                    -march=native
-            -fno-stack-protector
-            -fomit-frame-pointer
-            )
+TARGET_LINK_LIBRARIES(
+        sist2
 
-    TARGET_LINK_LIBRARIES(
-            sist2
+        ${GLIB_LIBRARIES}
+        ${GOBJECT_LIBRARIES}
+        ${UUID_LIBRARIES}
 
-            ${GLIB_LIBRARIES}
-            ${GOBJECT_LIBRARIES}
-            ${UUID_LIBRARIES}
+        # ffmpeg
+        ${PROJECT_SOURCE_DIR}/lib/libavcodec.a
+        ${PROJECT_SOURCE_DIR}/lib/libavformat.a
+        ${PROJECT_SOURCE_DIR}/lib/libavutil.a
+        ${PROJECT_SOURCE_DIR}/lib/libswscale.a
+        ${PROJECT_SOURCE_DIR}/lib/libswresample.a
 
-            # ffmpeg
-            ${PROJECT_SOURCE_DIR}/lib/libavcodec.a
-            ${PROJECT_SOURCE_DIR}/lib/libavformat.a
-            ${PROJECT_SOURCE_DIR}/lib/libavutil.a
-            ${PROJECT_SOURCE_DIR}/lib/libswscale.a
-            ${PROJECT_SOURCE_DIR}/lib/libswresample.a
-            #        ${FFMPEG_LIBRARIES}
-            #        swscale
+        # mupdf
+        ${PROJECT_SOURCE_DIR}/lib/libmupdf.a
+        ${PROJECT_SOURCE_DIR}/lib/libmupdf-third.a
 
-            # mupdf
-            ${PROJECT_SOURCE_DIR}/lib/libmupdf.a
-            ${PROJECT_SOURCE_DIR}/lib/libmupdf-third.a
+        # onion
+        ${PROJECT_SOURCE_DIR}/lib/libonion_static.a
 
-            # onion
-            ${PROJECT_SOURCE_DIR}/lib/libonion_static.a
+        pthread
+        curl
+        m
+        bz2
+        ${PROJECT_SOURCE_DIR}/lib/libmagic.a
+        ${PROJECT_SOURCE_DIR}/lib/libharfbuzz.a
+        ${PROJECT_SOURCE_DIR}/lib/libopenjp2.a
+        freetype
+        archive
 
-            pthread
-            curl
-            m
-            bz2
-            magic
-            ${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/libxml2.a
-            xml2
-            ${PROJECT_SOURCE_DIR}/lib/libopc/libmce.a
-            ${PROJECT_SOURCE_DIR}/lib/libopc/libopc.a
-            ${PROJECT_SOURCE_DIR}/lib/libopc/libplib.a
-    )
-
-endif ()
-
-if (WITH_SIST2_SCAN)
-
-    set_target_properties(
-            sist2_scan
-            PROPERTIES COMPILE_DEFINITIONS SIST_SCAN_ONLY
-    )
-    set_target_properties(
-            sist2_scan
-            PROPERTIES
-            COMPILE_DEFINITIONS SIST_SCAN_ONLY
-            LINK_FLAGS -static
-    )
-    target_include_directories(
-            sist2_scan PUBLIC
-            ${LIBMAGIC_INCLUDE_DIRS}
-            ${GOBJECT_INCLUDE_DIRS}
-            ${OPENSSL_INCLUDE_DIR}
-            ${FFMPEG_INCLUDE_DIRS}
-            ${GLIB_INCLUDE_DIRS}
-            ${UUID_INCLUDE_DIRS}
-            ${FREETYPE_INCLUDE_DIRS}
-            ${PROJECT_SOURCE_DIR}/
-            ${PROJECT_SOURCE_DIR}/lmdb/libraries/liblmdb/
-            ${PROJECT_SOURCE_DIR}/lib/onion/src/
-            ${PROJECT_SOURCE_DIR}/lib/mupdf/include/
-            ${PROJECT_SOURCE_DIR}/include/
-            /usr/include/libxml2/
-    )
-    target_link_directories(
-            sist2_scan PUBLIC
-            ${UUID_LIBRARY_DIRS}
-            ${FFMPEG_LIBRARY_DIRS}
-    )
-    target_compile_options(sist2_scan
-            PRIVATE
-            -Ofast
-            #        -march=native
-            -fno-stack-protector
-            -fomit-frame-pointer
-            )
-    TARGET_LINK_LIBRARIES(
-            sist2_scan
-
-            ${GLIB_LIBRARIES}
-            ${GOBJECT_LIBRARIES}
-            ${UUID_LIBRARIES}
-
-            # ffmpeg
-            ${PROJECT_SOURCE_DIR}/lib/libavcodec.a
-            ${PROJECT_SOURCE_DIR}/lib/libavformat.a
-            ${PROJECT_SOURCE_DIR}/lib/libavutil.a
-            ${PROJECT_SOURCE_DIR}/lib/libswscale.a
-            ${PROJECT_SOURCE_DIR}/lib/libswresample.a
-
-            # mupdf
-            ${PROJECT_SOURCE_DIR}/lib/libmupdf.a
-            ${PROJECT_SOURCE_DIR}/lib/libmupdf-third.a
-
-            ${PROJECT_SOURCE_DIR}/lib/libbz2.a
-            ${PROJECT_SOURCE_DIR}/lib/libmagic.a
-
-            pthread
-            m
-            ${PROJECT_SOURCE_DIR}/lib/libharfbuzz.a
-            ${PROJECT_SOURCE_DIR}/lib/libopenjp2.a
-            freetype
-
-            ${PROJECT_SOURCE_DIR}/lib/libarchive.a
-            ${PROJECT_SOURCE_DIR}/lib/liblz4.a
-            ${PROJECT_SOURCE_DIR}/lib/liblzma.a
-            ${PROJECT_SOURCE_DIR}/lib/libzstd.a
-
-            ${PROJECT_SOURCE_DIR}/lib/libxml2.a
-            ${PROJECT_SOURCE_DIR}/lib/libopc/libmce.a
-            ${PROJECT_SOURCE_DIR}/lib/libopc/libopc.a
-            ${PROJECT_SOURCE_DIR}/lib/libopc/libplib.a
-    )
-endif ()
+        ${PROJECT_SOURCE_DIR}/lib/libtesseract.a
+        ${PROJECT_SOURCE_DIR}/lib/liblept.a
+        png
+        tiff
+        stdc++
+)
 
 add_custom_target(
         before_sist2
         COMMAND ${CMAKE_CURRENT_SOURCE_DIR}/scripts/before_build.sh
 )
 
-IF (WITH_SIST2)
-    add_dependencies(sist2 before_sist2)
-else ()
-    add_dependencies(sist2_scan before_sist2)
-endif ()
+add_dependencies(sist2 before_sist2)

Docker/Dockerfile

@@ -2,8 +2,18 @@ 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
+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"]
+ENTRYPOINT ["/root/sist2"]

Docker/build.sh

@@ -1,5 +1,6 @@
 rm ./sist2
 cp ../sist2 .
+strip sist2
 
 version=$(./sist2 --version)
 

README.md

@@ -1,5 +1,6 @@
 ![GitHub](https://img.shields.io/github/license/simon987/sist2.svg)
 [![CodeFactor](https://www.codefactor.io/repository/github/simon987/sist2/badge?s=05daa325188aac4eae32c786f3d9cf4e0593f822)](https://www.codefactor.io/repository/github/simon987/sist2)
+[![Development snapshots](https://ci.simon987.net/app/rest/builds/buildType(Sist2_Build)/statusIcon)](https://files.simon987.net/artifacts/Sist2/Build/)
 
 # sist2
 
@@ -11,21 +12,24 @@ sist2 (Simple incremental search tool)
 
 * Fast, low memory usage, multi-threaded
 * Portable (all its features are packaged in a single executable)
-* Extracts text from common file types\*
-* Generates thumbnails\*
+* Extracts text from common file types \*
+* Generates thumbnails \*
 * Incremental scanning
 * Automatic tagging from file attributes via [user scripts](scripting/README.md)
 * Recursive scan inside archive files \*\*
+* OCR support with tesseract \*\*\*
 
 
 \* See [format support](#format-support)    
-\** See [Archive files](#archive-files)
+\*\* See [Archive files](#archive-files)    
+\*\*\* See [OCR](#ocr)    
 
 ## 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`
    
 
@@ -85,7 +89,7 @@ docker stop sist2
 
 File type | Library | Content | Thumbnail | Metadata
 :---|:---|:---|:---|:---
-pdf,xps,cbz,fb2,epub | MuPDF | yes | yes, `png` | title |
+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` |
@@ -110,6 +114,21 @@ scan is also supported.
 
 To check if a media file can be parsed without *seek*, execute `cat file.mp4 | ffprobe -`
  
+ 
+### OCR
+
+You can enable OCR support for pdf,xps,cbz,fb2,epub file types with the
+`--ocr <lang>` option. Download the language data files with your
+package manager (`apt install tesseract-ocr-eng`) or directly [from Github](https://github.com/tesseract-ocr/tesseract/wiki/Data-Files).
+
+The `simon987/sist2` github image comes with common languages 
+(hin, jpn, eng, fra, rus, spa) pre-installed.
+
+Examples
+```bash
+sist2 scan --ocr jpn ~/Books/Manga/
+sist2 scan --ocr eng ~/Books/Textbooks/
+```
 
 
 ## Build from source
@@ -121,15 +140,10 @@ binaries.
 
     *(Debian)*
     ```bash
-    apt install git cmake pkg-config libglib2.0-dev\
-        libssl-dev uuid-dev libavformat-dev libswscale-dev \
-        python3 libmagic-dev libfreetype6-dev libcurl-dev \
-        libbz2-dev yasm libharfbuzz-dev ragel libarchive-dev
-   ```
-    *(FreeBSD)*
-    ```bash
-   pkg install cmake gcc yasm gmake bash ffmpeg e2fsprogs-uuid\
-        autotools ragel libarchive
+    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
    ```
 
 2. Build

ci/build.sh

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+
+./scripts/get_static_libs.sh
+
+cmake .
+make
+strip sist2
+strip sist2_scan

mime.csv

@@ -252,7 +252,7 @@ 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
+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/richtext, rt|rtf|rtx
 text/rtf,
 text/scriplet, wsc

scripts/get_static_libs.sh

@@ -1,8 +1,11 @@
 #!/usr/bin/env bash
+
+THREADS=$(nproc)
+
 cd lib
 
 cd mupdf
-USE_SYSTEM_HARFBUZZ=yes USE_SYSTEM_OPENJPEG=yes HAVE_X11=no HAVE_GLUT=no make -j 4
+make USE_SYSTEM_HARFBUZZ=yes USE_SYSTEM_OPENJPEG=yes HAVE_X11=no HAVE_GLUT=no -j $THREADS
 cd ..
 
 mv mupdf/build/release/libmupdf.a .
@@ -12,7 +15,7 @@ mv mupdf/build/release/libmupdf-third.a .
 cd openjpeg
 #cmake . -DCMAKE_BUILD_TYPE=Release -DCMAKE_C_FLAGS="-O3 -march=native -DNDEBUG"
 cmake . -DCMAKE_BUILD_TYPE=Release -DCMAKE_C_FLAGS="-O3"
-make -j 4
+make -j $THREADS
 cd ..
 mv openjpeg/bin/libopenjp2.a .
 
@@ -20,7 +23,7 @@ mv openjpeg/bin/libopenjp2.a .
 cd harfbuzz
 ./autogen.sh
 ./configure --disable-shared --enable-static
-make -j 4
+make -j $THREADS
 cd ..
 mv harfbuzz/src/.libs/libharfbuzz.a .
 
@@ -31,7 +34,7 @@ cd ffmpeg
  --disable-manpages --disable-postproc --disable-avfilter \
  --disable-alsa --disable-lzma --disable-xlib --disable-debug\
  --disable-vdpau --disable-vaapi --disable-sdl2 --disable-network
-make -j 4
+make -j $THREADS
 cd ..
 
 mv ffmpeg/libavcodec/libavcodec.a .
@@ -48,14 +51,14 @@ cmake -DONION_USE_SSL=false -DONION_USE_PAM=false -DONION_USE_PNG=false -DONION_
 -DONION_USE_JPEG=false -DONION_USE_XML2=false -DONION_USE_SYSTEMD=false -DONION_USE_SQLITE3=false \
 -DONION_USE_REDIS=false -DONION_USE_GC=false -DONION_USE_TESTS=false -DONION_EXAMPLES=false \
 -DONION_USE_BINDINGS_CPP=false ..
-make -j 4
+make -j $THREADS
 cd ../..
 
 mv onion/build/src/onion/libonion_static.a .
 
 #bzip2
 cd bzip2-1.0.6
-make -j 4
+make -j $THREADS
 cd ..
 mv bzip2-1.0.6/libbz2.a .
 
@@ -63,47 +66,25 @@ mv bzip2-1.0.6/libbz2.a .
 cd libmagic
 ./autogen.sh
 ./configure --enable-static --disable-shared
-make -j 4
+make -j $THREADS
 cd ..
 mv libmagic/src/.libs/libmagic.a .
 
-# libarchive
-cd libarchive/build
+# tesseract
+cd tesseract
+mkdir build
+cd build
+cmake -DSTATIC=on -DBUILD_TRAINING_TOOLS=off ..
+make -j $THREADS
+cd ../..
+mv tesseract/build/libtesseract.a .
+
+# leptonica
+cd leptonica
 ./autogen.sh
+./configure --without-zlib --without-jpeg --without-giflib \
+  --without-giflib --without-libwebp --without-libwebpmux --without-libopenjpeg \
+  --enable-static --disable-shared
+make -j $THREADS
 cd ..
-./configure --without-nettle --without-expat --without-xml2 --without-openssl
-make -j 4
-cd ..
-mv libarchive/.libs/libarchive.a .
-
-# lz4
-cd lz4
-make -j 4
-cd ..
-mv lz4/lib/liblz4.a .
-
-# lzma
-wget https://newcontinuum.dl.sourceforge.net/project/lzmautils/xz-5.2.3.tar.gz
-tar -xzf xz-5.2.3.tar.gz
-rm xz-5.2.3.tar.gz
-cd xz-5.2.3
-./autogen.sh
-./configure
-make -j 4
-cd ..
-mv xz-5.2.3/src/liblzma/.libs/liblzma.a .
-
-# zstd
-cd zstd
-make -j 4
-cd ..
-mv zstd/lib/libzstd.a .
-
-# xml2
-cd libxml2
-./autogen.sh --without-zlib --without-lzma
-make
-cd ..
-mv libxml2/.libs/libxml2.a .
-
-cd ..
+mv leptonica/src/.libs/liblept.a .

src/cli.c

@@ -1,4 +1,7 @@
 #include "cli.h"
+#include "ctx.h"
+
+#include <tesseract/capi.h>
 
 #define DEFAULT_OUTPUT "index.sist2/"
 #define DEFAULT_CONTENT_SIZE 32768
@@ -34,8 +37,6 @@ void scan_args_destroy(scan_args_t *args) {
     free(args);
 }
 
-#ifndef SIST_SCAN_ONLY
-
 void index_args_destroy(index_args_t *args) {
     //todo
     free(args);
@@ -46,8 +47,6 @@ void web_args_destroy(web_args_t *args) {
     free(args);
 }
 
-#endif
-
 int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
     if (argc < 2) {
         fprintf(stderr, "Required positional argument: PATH.\n");
@@ -134,11 +133,34 @@ int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
         fprintf(stderr, "Archive mode must be one of (skip, list, shallow, recurse), got '%s'", args->archive);
         return 1;
     }
+
+    if (args->tesseract_lang != NULL) {
+        TessBaseAPI *api = TessBaseAPICreate();
+        ret = TessBaseAPIInit3(api, TESS_DATAPATH, args->tesseract_lang);
+        if (ret != 0) {
+            fprintf(stderr, "Could not initialize tesseract with lang '%s'\n", args->tesseract_lang);
+            return 1;
+        }
+        TessBaseAPIEnd(api);
+        TessBaseAPIDelete(api);
+    }
+
+    LOG_DEBUGF("cli.c", "arg quality=%f", args->quality)
+    LOG_DEBUGF("cli.c", "arg size=%d", args->size)
+    LOG_DEBUGF("cli.c", "arg content_size=%d", args->content_size)
+    LOG_DEBUGF("cli.c", "arg threads=%d", args->threads)
+    LOG_DEBUGF("cli.c", "arg incremental=%s", args->incremental)
+    LOG_DEBUGF("cli.c", "arg output=%s", args->output)
+    LOG_DEBUGF("cli.c", "arg rewrite_url=%s", args->rewrite_url)
+    LOG_DEBUGF("cli.c", "arg name=%s", args->name)
+    LOG_DEBUGF("cli.c", "arg depth=%d", args->depth)
+    LOG_DEBUGF("cli.c", "arg path=%s", args->path)
+    LOG_DEBUGF("cli.c", "arg archive=%s", args->archive)
+    LOG_DEBUGF("cli.c", "arg ocr=%s", args->tesseract_lang)
+
     return 0;
 }
 
-#ifndef SIST_SCAN_ONLY
-
 int index_args_validate(index_args_t *args, int argc, const char **argv) {
 
     if (argc < 2) {
@@ -189,6 +211,14 @@ int index_args_validate(index_args_t *args, int argc, const char **argv) {
         args->batch_size = DEFAULT_BATCH_SIZE;
     }
 
+    LOG_DEBUGF("cli.c", "arg es_url=%s", args->es_url)
+    LOG_DEBUGF("cli.c", "arg index_path=%s", args->index_path)
+    LOG_DEBUGF("cli.c", "arg script_path=%s", args->script_path)
+    LOG_DEBUGF("cli.c", "arg script=%s", args->script)
+    LOG_DEBUGF("cli.c", "arg print=%d", args->print)
+    LOG_DEBUGF("cli.c", "arg batch_size=%d", args->batch_size)
+    LOG_DEBUGF("cli.c", "arg force_reset=%d", args->force_reset)
+
     return 0;
 }
 
@@ -223,10 +253,21 @@ int web_args_validate(web_args_t *args, int argc, const char **argv) {
     for (int i = 0; i < args->index_count; i++) {
         char *abs_path = abspath(args->indices[i]);
         if (abs_path == NULL) {
-            fprintf(stderr, "File not found: %s\n", abs_path);
+            fprintf(stderr, "File not found: %s\n", args->indices[i]);
             return 1;
         }
     }
+
+    LOG_DEBUGF("cli.c", "arg es_url=%s", args->es_url)
+    LOG_DEBUGF("cli.c", "arg bind=%s", args->bind)
+    LOG_DEBUGF("cli.c", "arg port=%s", args->port)
+    LOG_DEBUGF("cli.c", "arg credentials=%s", args->credentials)
+    LOG_DEBUGF("cli.c", "arg b64credentials=%s", args->b64credentials)
+    LOG_DEBUGF("cli.c", "arg index_count=%d", args->index_count)
+    for (int i = 0; i < args->index_count; i++) {
+        LOG_DEBUGF("cli.c", "arg indices[%d]=%s", i, args->indices[i])
+    }
+
     return 0;
 }
 
@@ -240,5 +281,3 @@ web_args_t *web_args_create() {
     return args;
 }
 
-#endif
-

src/cli.h

@@ -16,13 +16,13 @@ typedef struct scan_args {
     char *path;
     char *archive;
     archive_mode_t archive_mode;
+    char *tesseract_lang;
 } scan_args_t;
 
 scan_args_t *scan_args_create();
 void scan_args_destroy(scan_args_t *args);
 int scan_args_validate(scan_args_t *args, int argc, const char **argv);
 
-#ifndef SIST_SCAN_ONLY
 typedef struct index_args {
     char *es_url;
     const char *index_path;
@@ -51,6 +51,5 @@ void web_args_destroy(web_args_t *args);
 
 int index_args_validate(index_args_t *args, int argc, const char **argv);
 int web_args_validate(web_args_t *args, int argc, const char **argv);
-#endif
 
 #endif

src/ctx.h

@@ -17,6 +17,8 @@ struct {
     float tn_qscale;
     int depth;
     archive_mode_t archive_mode;
+    int verbose;
+    int very_verbose;
 
     size_t stat_tn_size;
     size_t stat_index_size;
@@ -25,10 +27,15 @@ struct {
     GHashTable *copy_table;
 
     pthread_mutex_t mupdf_mu;
+    char * tesseract_lang;
 } ScanCtx;
 
+struct {
+    int verbose;
+    int very_verbose;
+    int no_color;
+} LogCtx;
 
-#ifndef SIST_SCAN_ONLY
 struct {
     char *es_url;
     int batch_size;
@@ -40,7 +47,6 @@ struct {
     char *b64credentials;
     struct index_t indices[16];
 } WebCtx;
-#endif
 
 
 #endif

src/io/serialize.c

@@ -262,8 +262,7 @@ void read_index(const char *path, const char index_id[UUID_STR_LEN], index_func
                     break;
                 }
                 default:
-                    fprintf(stderr, "Invalid meta key (corrupt index): %x\n", key);
-                    break;
+                    LOG_FATALF("serialize.c", "Invalid meta key (corrupt index): %x", key)
             }
 
             key = getc(file);

src/io/store.c

@@ -9,9 +9,9 @@ store_t *store_create(char *path) {
     mdb_env_create(&store->env);
 
     int open_ret = mdb_env_open(store->env,
-                 path,
-                 MDB_WRITEMAP | MDB_MAPASYNC,
-                 S_IRUSR | S_IWUSR
+                                path,
+                                MDB_WRITEMAP | MDB_MAPASYNC,
+                                S_IRUSR | S_IWUSR
     );
 
     if (open_ret != 0) {
@@ -42,6 +42,12 @@ void store_destroy(store_t *store) {
 
 void store_write(store_t *store, char *key, size_t key_len, char *buf, size_t buf_len) {
 
+    if (LogCtx.very_verbose) {
+        char uuid_str[UUID_STR_LEN];
+        uuid_unparse((unsigned char *) key, uuid_str);
+        LOG_DEBUGF("store.c", "Store write {%s} %lu bytes", uuid_str, buf_len)
+    }
+
     MDB_val mdb_key;
     mdb_key.mv_data = key;
     mdb_key.mv_size = key_len;
@@ -68,6 +74,8 @@ void store_write(store_t *store, char *key, size_t key_len, char *buf, size_t bu
         mdb_env_set_mapsize(store->env, store->size);
         mdb_txn_begin(store->env, NULL, 0, &txn);
         put_ret = mdb_put(txn, store->dbi, &mdb_key, &mdb_value, 0);
+
+        LOG_INFOF("store.c", "Updated mdb mapsize to %lu bytes", store->size)
     }
 
     mdb_txn_commit(txn);

src/log.c

@@ -0,0 +1,99 @@
+#include "log.h"
+
+const char *log_colors[] = {
+        "\033[34m", "\033[01;34m", "\033[0m",
+        "\033[01;33m", "\033[31m", "\033[01;31m"
+};
+
+const char *log_levels[] = {
+        "DEBUG", "INFO", "WARNING", "ERROR", "FATAL"
+};
+
+void sist_logf(char *filepath, int level, char *format, ...) {
+
+    static int is_tty = -1;
+    if (is_tty == -1) {
+        is_tty = isatty(STDERR_FILENO);
+    }
+
+    char log_str[LOG_MAX_LENGTH];
+
+    unsigned long long pid = (unsigned long long) pthread_self();
+
+    char datetime[32];
+    time_t t;
+    struct tm result;
+    t = time(NULL);
+    localtime_r(&t, &result);
+    strftime(datetime, sizeof(datetime), "%Y-%m-%d %H:%M:%S", &result);
+
+    int log_len;
+    if (is_tty) {
+        log_len = snprintf(
+                log_str, sizeof(log_str),
+                "\033[%dm[%04X]%s [%s] [%s %s] ",
+                31 + ((unsigned int) (pid)) % 7, pid, log_colors[level],
+                datetime, log_levels[level], filepath
+        );
+    } else {
+        log_len = snprintf(
+                log_str, sizeof(log_str),
+                "[%04X] [%s] [%s %s] ",
+                pid, datetime, log_levels[level], filepath
+        );
+    }
+
+    va_list ap;
+    va_start(ap, format);
+    size_t maxsize = sizeof(log_str) - log_len;
+    log_len += vsnprintf(log_str + log_len, maxsize, format, ap);
+    va_end(ap);
+
+    if (is_tty) {
+        log_len += sprintf(log_str + log_len, "\033[0m\n");
+    } else {
+        *(log_str + log_len) = '\n';
+        log_len += 1;
+    }
+
+    write(STDOUT_FILENO, log_str, log_len);
+}
+
+void sist_log(char *filepath, int level, char *str) {
+
+    static int is_tty = -1;
+    if (is_tty == -1) {
+        is_tty = isatty(STDERR_FILENO);
+    }
+
+    char log_str[LOG_MAX_LENGTH];
+
+    unsigned long long pid = (unsigned long long) pthread_self();
+
+    char datetime[32];
+    time_t t;
+    struct tm result;
+    t = time(NULL);
+    localtime_r(&t, &result);
+    strftime(datetime, sizeof(datetime), "%Y-%m-%d %H:%M:%S", &result);
+
+    int log_len;
+    if (is_tty) {
+        log_len = snprintf(
+                log_str, sizeof(log_str),
+                "\033[%dm[%04X]%s [%s] [%s %s] %s \033[0m\n",
+                31 + ((unsigned int) (pid)) % 7, pid, log_colors[level],
+                datetime, log_levels[level], filepath,
+                str
+        );
+    } else {
+        log_len = snprintf(
+                log_str, sizeof(log_str),
+                "[%04X] [%s] [%s %s] %s \n",
+                pid, datetime, log_levels[level], filepath,
+                str
+        );
+    }
+
+    write(STDERR_FILENO, log_str, log_len);
+}

src/log.h

@@ -0,0 +1,45 @@
+#ifndef SIST2_LOG_H
+#define SIST2_LOG_H
+
+#define LOG_MAX_LENGTH 8192
+
+#define SIST_DEBUG 0
+#define SIST_INFO 1
+#define SIST_WARNING 2
+#define SIST_ERROR 3
+#define SIST_FATAL 4
+
+#define LOG_DEBUGF(filepath, fmt, ...) \
+    if (LogCtx.very_verbose) {sist_logf(filepath, SIST_DEBUG, fmt, __VA_ARGS__);}
+#define LOG_DEBUG(filepath, str) \
+    if (LogCtx.very_verbose) {sist_log(filepath, SIST_DEBUG, str);}
+
+#define LOG_INFOF(filepath, fmt, ...) \
+    if (LogCtx.verbose) {sist_logf(filepath, SIST_INFO, fmt, __VA_ARGS__);}
+#define LOG_INFO(filepath, str) \
+    if (LogCtx.verbose) {sist_log(filepath, SIST_INFO, str);}
+
+#define LOG_WARNINGF(filepath, fmt, ...) \
+    if (LogCtx.verbose) {sist_logf(filepath, SIST_WARNING, fmt, __VA_ARGS__);}
+#define LOG_WARNING(filepath, str) \
+    if (LogCtx.verbose) {sist_log(filepath, SIST_WARNING, str);}
+
+#define LOG_ERRORF(filepath, fmt, ...) \
+    if (LogCtx.verbose) {sist_logf(filepath, SIST_ERROR, fmt, __VA_ARGS__);}
+#define LOG_ERROR(filepath, str) \
+    if (LogCtx.verbose) {sist_log(filepath, SIST_ERROR, str);}
+
+#define LOG_FATALF(filepath, fmt, ...) \
+    sist_logf(filepath, SIST_FATAL, fmt, __VA_ARGS__);\
+    exit(-1);
+#define LOG_FATAL(filepath, str) \
+    sist_log(filepath, SIST_FATAL, str);\
+    exit(-1);
+
+#include "src/sist.h"
+
+void sist_logf(char *filepath, int level, char *format, ...);
+
+void sist_log(char *filepath, int level, char *str);
+
+#endif

src/main.c

@@ -1,16 +1,12 @@
 #include "sist.h"
 #include "ctx.h"
 
-#ifndef SIST_SCAN_ONLY
 #define DESCRIPTION "Lightning-fast file system indexer and search tool."
-#else
-#define DESCRIPTION "Lightning-fast file system indexer and search tool. (SCAN ONLY)"
-#endif
 
 #define EPILOG "Made by simon987 <me@simon987.net>. Released under GPL-3.0"
 
 
-static const char *const Version = "1.1.11";
+static const char *const Version = "1.2.0";
 static const char *const usage[] = {
         "sist2 scan [OPTION]... PATH",
         "sist2 index [OPTION]... INDEX",
@@ -19,9 +15,7 @@ static const char *const usage[] = {
 };
 
 void global_init() {
-#ifndef SIST_SCAN_ONLY
     curl_global_init(CURL_GLOBAL_NOTHING);
-#endif
     av_log_set_level(AV_LOG_QUIET);
     opcInitLibrary();
 }
@@ -40,24 +34,7 @@ void init_dir(const char *dirpath) {
 }
 
 void scan_print_header() {
-    printf("sist2 V%s\n", Version);
-    printf("---------------------\n");
-    printf("threads\t\t\t%d\n", ScanCtx.threads);
-    printf("tn_qscale\t\t%.1f/31.0\n", ScanCtx.tn_qscale);
-
-    if (ScanCtx.tn_size > 0) {
-        printf("tn_size\t\t\t%dpx\n", ScanCtx.tn_size);
-    } else {
-        printf("tn_size\t\t\tdisabled\n");
-    }
-
-    if (ScanCtx.content_size > 0) {
-        printf("content_size\t\t%d B\n", ScanCtx.content_size);
-    } else {
-        printf("content_size\t\t\tdisabled\n");
-    }
-
-    printf("output\t\t\t%s\n", ScanCtx.index.path);
+    LOG_INFOF("main.c", "sist2 v%s", Version)
 }
 
 void sist2_scan(scan_args_t *args) {
@@ -72,6 +49,7 @@ void sist2_scan(scan_args_t *args) {
     strncpy(ScanCtx.index.desc.name, args->name, sizeof(ScanCtx.index.desc.name));
     strncpy(ScanCtx.index.desc.root, args->path, sizeof(ScanCtx.index.desc.root));
     ScanCtx.index.desc.root_len = (short) strlen(ScanCtx.index.desc.root);
+    ScanCtx.tesseract_lang = args->tesseract_lang;
 
     init_dir(ScanCtx.index.path);
 
@@ -139,8 +117,6 @@ void sist2_scan(scan_args_t *args) {
     store_destroy(ScanCtx.index.store);
 }
 
-#ifndef SIST_SCAN_ONLY
-
 void sist2_index(index_args_t *args) {
 
     IndexCtx.es_url = args->es_url;
@@ -215,18 +191,14 @@ void sist2_web(web_args_t *args) {
     serve(args->bind, args->port);
 }
 
-#endif
-
 
 int main(int argc, const char *argv[]) {
 
     global_init();
 
     scan_args_t *scan_args = scan_args_create();
-#ifndef SIST_SCAN_ONLY
     index_args_t *index_args = index_args_create();
     web_args_t *web_args = web_args_create();
-#endif
 
     int arg_version = 0;
 
@@ -236,6 +208,8 @@ int main(int argc, const char *argv[]) {
             OPT_HELP(),
 
             OPT_BOOLEAN('v', "version", &arg_version, "Show version and exit"),
+            OPT_BOOLEAN(0, "verbose", &LogCtx.verbose, "Turn on logging"),
+            OPT_BOOLEAN(0, "very-verbose", &LogCtx.very_verbose, "Turn on debug messages"),
 
             OPT_GROUP("Scan options"),
             OPT_INTEGER('t', "threads", &scan_args->threads, "Number of threads. DEFAULT=1"),
@@ -255,8 +229,9 @@ int main(int argc, const char *argv[]) {
             OPT_STRING(0, "archive", &scan_args->archive, "Archive file mode (skip|list|shallow|recurse). "
                                                           "skip: Don't parse, list: only get file names as text, "
                                                           "shallow: Don't parse archives inside archives. DEFAULT: recurse"),
+            OPT_STRING(0, "ocr", &scan_args->tesseract_lang, "Tesseract language (use tesseract --list-langs to see "
+                                                             "which are installed on your machine)"),
 
-#ifndef SIST_SCAN_ONLY
             OPT_GROUP("Index options"),
             OPT_STRING(0, "es-url", &common_es_url, "Elasticsearch url with port. DEFAULT=http://localhost:9200"),
             OPT_BOOLEAN('p', "print", &index_args->print, "Just print JSON documents to stdout."),
@@ -270,7 +245,6 @@ int main(int argc, const char *argv[]) {
             OPT_STRING(0, "bind", &web_args->bind, "Listen on this address. DEFAULT=localhost"),
             OPT_STRING(0, "port", &web_args->port, "Listen on this port. DEFAULT=4090"),
             OPT_STRING(0, "auth", &web_args->credentials, "Basic auth in user:password format"),
-#endif
 
             OPT_END(),
     };
@@ -285,10 +259,12 @@ int main(int argc, const char *argv[]) {
         exit(0);
     }
 
-#ifndef SIST_SCAN_ONLY
+    if (LogCtx.very_verbose != 0) {
+        LogCtx.verbose = 1;
+    }
+
     web_args->es_url = common_es_url;
     index_args->es_url = common_es_url;
-#endif
 
     if (argc == 0) {
         argparse_usage(&argparse);
@@ -303,7 +279,6 @@ int main(int argc, const char *argv[]) {
 
     }
 
-#ifndef SIST_SCAN_ONLY
     else if (strcmp(argv[0], "index") == 0) {
 
         int err = index_args_validate(index_args, argc, argv);
@@ -321,7 +296,6 @@ int main(int argc, const char *argv[]) {
         sist2_web(web_args);
 
     }
-#endif
     else {
         fprintf(stderr, "Invalid command: '%s'\n", argv[0]);
         argparse_usage(&argparse);
@@ -331,10 +305,8 @@ int main(int argc, const char *argv[]) {
 
     scan_args_destroy(scan_args);
 
-#ifndef SIST_SCAN_ONLY
     index_args_destroy(index_args);
     web_args_destroy(web_args);
-#endif
 
     return 0;
 }

src/parsing/arc.c

@@ -67,18 +67,24 @@ void parse_archive(vfile_t *f, document_t *doc) {
     struct archive *a;
     struct archive_entry *entry;
 
-    a = archive_read_new();
-
-    archive_read_support_filter_all(a);
-    archive_read_support_format_all(a);
 
     arc_data_f data;
     data.f = f;
 
     int ret = 0;
     if (data.f->is_fs_file) {
+
+        a = archive_read_new();
+        archive_read_support_filter_all(a);
+        archive_read_support_format_all(a);
+
         ret = archive_read_open_filename(a, doc->filepath, ARC_BUF_SIZE);
     } else if (ScanCtx.archive_mode == ARC_MODE_RECURSE) {
+
+        a = archive_read_new();
+        archive_read_support_filter_all(a);
+        archive_read_support_format_all(a);
+
         ret = archive_read_open(
                 a, &data,
                 vfile_open_callback,
@@ -86,12 +92,11 @@ void parse_archive(vfile_t *f, document_t *doc) {
                 vfile_close_callback
         );
     } else {
-        archive_read_free(a);
         return;
     }
 
     if (ret != ARCHIVE_OK) {
-        fprintf(stderr, "OPEN[%d]:%s %s\n", ret, archive_error_string(a), doc->filepath);
+        LOG_ERRORF(doc->filepath, "(arc.c) [%d] %s", ret, archive_error_string(a))
         archive_read_free(a);
         return;
     }

src/parsing/doc.c

@@ -1,6 +1,7 @@
 #include "doc.h"
+#include "src/ctx.h"
 
-static void dumpText(mceTextReader_t *reader, dyn_buffer_t *buf) {
+void dump_text(mceTextReader_t *reader, dyn_buffer_t *buf) {
 
     mce_skip_attributes(reader);
 
@@ -17,7 +18,7 @@ static void dumpText(mceTextReader_t *reader, dyn_buffer_t *buf) {
         } mce_end_element(reader);
 
         mce_start_element(reader, NULL, NULL) {
-            dumpText(reader, buf);
+            dump_text(reader, buf);
         } mce_end_element(reader);
 
     } mce_end_children(reader)
@@ -50,30 +51,35 @@ int should_read_part(opcPart part) {
     return FALSE;
 }
 
-void read_part(opcContainer *c, dyn_buffer_t *buf, opcPart part) {
+__always_inline
+void read_part(opcContainer *c, dyn_buffer_t *buf, opcPart part, document_t *doc) {
 
     mceTextReader_t reader;
     int ret = opcXmlReaderOpen(c, &reader, part, NULL, "UTF-8", 0);
 
     if (ret != OPC_ERROR_NONE) {
-        //todo verbose
+        LOG_ERRORF(doc->filepath, "(doc.c) opcXmlReaderOpen() returned error code %d", ret);
         return;
     }
 
     mce_start_document(&reader) {
         mce_start_element(&reader, NULL, NULL) {
-            dumpText(&reader, buf);
+                dump_text(&reader, buf);
         } mce_end_element(&reader);
-    }mce_end_document(&reader);
+    } mce_end_document(&reader);
 
     mceTextReaderCleanup(&reader);
 }
 
 void parse_doc(void *mem, size_t mem_len, document_t *doc) {
 
+    if (mem == NULL) {
+        return;
+    }
+
     opcContainer *c = opcContainerOpenMem(mem, mem_len, OPC_OPEN_READ_ONLY, NULL);
     if (c == NULL) {
-        //todo verbose
+        LOG_ERROR(doc->filepath, "(doc.c) Couldn't open document with opcContainerOpenMem()");
         return;
     }
 
@@ -82,17 +88,20 @@ void parse_doc(void *mem, size_t mem_len, document_t *doc) {
     opcPart part = opcPartGetFirst(c);
     do {
         if (should_read_part(part)) {
-            read_part(c, &buf, part);
+            read_part(c, &buf, part, doc);
         }
     } while ((part = opcPartGetNext(c, part)));
 
     opcContainerClose(c, OPC_CLOSE_NOW);
-    dyn_buffer_write_char(&buf, '\0');
 
-    meta_line_t *meta = malloc(sizeof(meta_line_t) + buf.cur);
-    meta->key = MetaContent;
-    strcpy(meta->strval, buf.buf);
-    APPEND_META(doc, meta)
+    if (buf.cur > 0) {
+        dyn_buffer_write_char(&buf, '\0');
+
+        meta_line_t *meta = malloc(sizeof(meta_line_t) + buf.cur);
+        meta->key = MetaContent;
+        strcpy(meta->strval, buf.buf);
+        APPEND_META(doc, meta)
+    }
 
     dyn_buffer_destroy(&buf);
 }

src/parsing/font.c

@@ -147,6 +147,7 @@ void parse_font(const char *buf, size_t buf_len, document_t *doc) {
     FT_Face face;
     FT_Error err = FT_New_Memory_Face(ft_lib, (unsigned char *) buf, buf_len, 0, &face);
     if (err != 0) {
+        LOG_ERRORF(doc->filepath, "(font.c) FT_New_Memory_Face() returned error code [%d] %s", err, ft_error_string(err));
         return;
     }
 
@@ -176,6 +177,7 @@ void parse_font(const char *buf, size_t buf_len, document_t *doc) {
 
     err = FT_Set_Pixel_Sizes(face, 0, pixel);
     if (err != 0) {
+        LOG_WARNINGF(doc->filepath, "(font.c) FT_Set_Pixel_Sizes() returned error code [%d] %s", err, ft_error_string(err))
         return;
     }
 
@@ -194,6 +196,7 @@ void parse_font(const char *buf, size_t buf_len, document_t *doc) {
             c = c >= 'a' && c <= 'z' ? c - 32 : c + 32;
             err = FT_Load_Char(face, c, FT_LOAD_NO_HINTING | FT_LOAD_RENDER);
             if (err != 0) {
+                LOG_WARNINGF(doc->filepath, "(font.c) FT_Load_Char() returned error code [%d] %s", err, ft_error_string(err));
                 continue;
             }
         }

src/parsing/media.c

@@ -77,7 +77,8 @@ AVFrame *scale_frame(const AVCodecContext *decoder, const AVFrame *frame, int si
     return scaled_frame;
 }
 
-AVFrame *read_frame(AVFormatContext *pFormatCtx, AVCodecContext *decoder, int stream_idx) {
+__always_inline
+AVFrame *read_frame(AVFormatContext *pFormatCtx, AVCodecContext *decoder, int stream_idx, document_t *doc) {
     AVFrame *frame = av_frame_alloc();
 
     AVPacket avPacket;
@@ -90,9 +91,12 @@ AVFrame *read_frame(AVFormatContext *pFormatCtx, AVCodecContext *decoder, int st
             int read_frame_ret = av_read_frame(pFormatCtx, &avPacket);
 
             if (read_frame_ret != 0) {
-//                if (read_frame_ret != AVERROR_EOF) {
-//                    fprintf(stderr, "Error reading frame: %d\n", read_frame_ret);
-//                }
+                if (read_frame_ret != AVERROR_EOF) {
+                    LOG_WARNINGF(doc->filepath,
+                                 "(media.c) avcodec_read_frame() returned error code [%d] %s",
+                                 read_frame_ret, av_err2str(read_frame_ret)
+                    )
+                }
                 av_frame_free(&frame);
                 av_packet_unref(&avPacket);
                 return NULL;
@@ -109,7 +113,10 @@ AVFrame *read_frame(AVFormatContext *pFormatCtx, AVCodecContext *decoder, int st
         // Feed it to decoder
         int decode_ret = avcodec_send_packet(decoder, &avPacket);
         if (decode_ret != 0) {
-            printf("Error decoding frame: %s\n", av_err2str(decode_ret));
+            LOG_WARNINGF(doc->filepath,
+                         "(media.c) avcodec_send_packet() returned error code [%d] %s",
+                         decode_ret, av_err2str(decode_ret)
+            )
         }
         av_packet_unref(&avPacket);
         receive_ret = avcodec_receive_frame(decoder, frame);
@@ -120,6 +127,7 @@ AVFrame *read_frame(AVFormatContext *pFormatCtx, AVCodecContext *decoder, int st
 #define APPEND_TAG_META(doc, tag_, keyname) \
     text_buffer_t tex = text_buffer_create(-1); \
     text_buffer_append_string0(&tex, tag_->value); \
+    text_buffer_terminate_string(&tex); \
     meta_line_t *meta_tag = malloc(sizeof(meta_line_t) + tex.dyn_buffer.cur); \
     meta_tag->key = keyname; \
     strcpy(meta_tag->strval, tex.dyn_buffer.buf); \
@@ -152,7 +160,8 @@ void append_audio_meta(AVFormatContext *pFormatCtx, document_t *doc) {
 }
 
 __always_inline
-void append_video_meta(AVFormatContext *pFormatCtx, AVFrame *frame, document_t *doc, int include_audio_tags, int is_video) {
+void
+append_video_meta(AVFormatContext *pFormatCtx, AVFrame *frame, document_t *doc, int include_audio_tags, int is_video) {
 
     if (is_video) {
         meta_line_t *meta_duration = malloc(sizeof(meta_line_t));
@@ -259,7 +268,7 @@ void parse_media(AVFormatContext *pFormatCtx, document_t *doc) {
             }
         }
 
-        AVFrame *frame = read_frame(pFormatCtx, decoder, video_stream);
+        AVFrame *frame = read_frame(pFormatCtx, decoder, video_stream, doc);
         if (frame == NULL) {
             avcodec_free_context(&decoder);
             avformat_close_input(&pFormatCtx);
@@ -308,12 +317,14 @@ void parse_media_filename(const char *filepath, document_t *doc) {
 
     AVFormatContext *pFormatCtx = avformat_alloc_context();
     if (pFormatCtx == NULL) {
-        fprintf(stderr, "Could not allocate AVFormatContext! %s \n", filepath);
+        LOG_ERROR(doc->filepath, "(media.c) Could not allocate context with avformat_alloc_context()")
         return;
     }
     int res = avformat_open_input(&pFormatCtx, filepath, NULL, NULL);
     if (res < 0) {
-        fprintf(stderr, "media error: %s %s\n", filepath, av_err2str(res));
+        LOG_ERRORF(doc->filepath, "(media.c) avformat_open_input() returned [%d] %s", res, av_err2str(res))
+        avformat_close_input(&pFormatCtx);
+        avformat_free_context(pFormatCtx);
         return;
     }
 
@@ -336,7 +347,7 @@ void parse_media_vfile(struct vfile *f, document_t *doc) {
 
     AVFormatContext *pFormatCtx = avformat_alloc_context();
     if (pFormatCtx == NULL) {
-        fprintf(stderr, "Could not allocate AVFormatContext! %s \n", f->filepath);
+        LOG_ERROR(doc->filepath, "(media.c) Could not allocate context with avformat_alloc_context()")
         return;
     }
 
@@ -349,13 +360,22 @@ void parse_media_vfile(struct vfile *f, document_t *doc) {
     int res = avformat_open_input(&pFormatCtx, "", NULL, NULL);
     if (res == -5) {
         // Tried to parse media that requires seek
+        av_free(io_ctx->buffer);
+        avio_context_free(&io_ctx);
+        avformat_close_input(&pFormatCtx);
+        avformat_free_context(pFormatCtx);
         return;
-    } else if(res < 0) {
-        fprintf(stderr, "media error: %s %s\n", f->filepath, av_err2str(res));
+    } else if (res < 0) {
+        LOG_ERRORF(doc->filepath, "(media.c) avformat_open_input() returned [%d] %s", res, av_err2str(res))
+        av_free(io_ctx->buffer);
+        avio_context_free(&io_ctx);
+        avformat_close_input(&pFormatCtx);
+        avformat_free_context(pFormatCtx);
         return;
     }
 
     parse_media(pFormatCtx, doc);
-    av_free(io_ctx);
+    av_free(io_ctx->buffer);
+    avio_context_free(&io_ctx);
 }
 

src/parsing/mime_generated.c

@@ -1193,6 +1193,8 @@ g_hash_table_insert(ext_table, "srt", (gpointer)text_plain);
 g_hash_table_insert(ext_table, "nfo", (gpointer)text_plain);
 g_hash_table_insert(ext_table, "sfv", (gpointer)text_plain);
 g_hash_table_insert(ext_table, "m3u", (gpointer)text_plain);
+g_hash_table_insert(ext_table, "csv", (gpointer)text_plain);
+g_hash_table_insert(ext_table, "eml", (gpointer)text_plain);
 g_hash_table_insert(ext_table, "rt", (gpointer)text_richtext);
 g_hash_table_insert(ext_table, "rtf", (gpointer)text_richtext);
 g_hash_table_insert(ext_table, "rtx", (gpointer)text_richtext);

src/parsing/parse.c

@@ -1,4 +1,3 @@
-#include <src/ctx.h>
 #include "src/sist.h"
 #include "src/ctx.h"
 
@@ -9,8 +8,7 @@ int fs_read(struct vfile *f, void *buf, size_t size) {
     if (f->fd == -1) {
         f->fd = open(f->filepath, O_RDONLY);
         if (f->fd == -1) {
-            perror("open");
-            printf("%s\n", f->filepath);
+            LOG_ERRORF(f->filepath, "open(): [%d] %s", errno, strerror(errno))
             return -1;
         }
     }
@@ -39,7 +37,7 @@ void *read_all(parse_job_t *job, const char *buf, int bytes_read) {
 
         int ret = job->vfile.read(&job->vfile, full_buf + bytes_read, job->info.st_size - bytes_read);
         if (ret == -1) {
-            perror("read");
+            LOG_ERRORF(job->filepath, "read(): [%d] %s", errno, strerror(errno))
             return NULL;
         }
     }
@@ -75,6 +73,12 @@ void parse(void *arg) {
     uuid_generate(doc.uuid);
     char *buf[PARSE_BUF_SIZE];
 
+    if (LogCtx.very_verbose) {
+        char uuid_str[UUID_STR_LEN];
+        uuid_unparse(doc.uuid, uuid_str);
+        LOG_DEBUGF(job->filepath, "Starting parse job {%s}", uuid_str)
+    }
+
     if (job->info.st_size == 0) {
         doc.mime = MIME_EMPTY;
     } else if (*(job->filepath + job->ext) != '\0' && (job->ext - job->base != 1)) {
@@ -87,6 +91,7 @@ void parse(void *arg) {
         // Get mime type with libmagic
         bytes_read = job->vfile.read(&job->vfile, buf, PARSE_BUF_SIZE);
         if (bytes_read == -1) {
+            LOG_WARNINGF(job->filepath, "read() Error: %s", strerror(errno))
             CLOSE_FILE(job->vfile)
             return;
         }
@@ -95,7 +100,7 @@ void parse(void *arg) {
         if (magic_mime_str != NULL) {
             doc.mime = mime_get_mime_by_string(ScanCtx.mime_table, magic_mime_str);
             if (doc.mime == 0) {
-                fprintf(stderr, "Couldn't find mime %s, %s\n", magic_mime_str, job->filepath + job->base);
+                LOG_WARNINGF(job->filepath, "Couldn't find mime %s", magic_mime_str);
             }
         }
     }

src/parsing/pdf.c

@@ -1,6 +1,10 @@
 #include "pdf.h"
 #include "src/ctx.h"
 
+#define MIN_OCR_SIZE 128
+__thread text_buffer_t thread_buffer;
+
+
 fz_page *render_cover(fz_context *ctx, document_t *doc, fz_document *fzdoc) {
 
     int err = 0;
@@ -14,6 +18,7 @@ fz_page *render_cover(fz_context *ctx, document_t *doc, fz_document *fzdoc) {
 
     if (err != 0) {
         fz_drop_page(ctx, cover);
+        LOG_WARNINGF(doc->filepath, "fz_load_page() returned error code [%d] %s", err, ctx->error.message)
         return NULL;
     }
 
@@ -52,6 +57,7 @@ fz_page *render_cover(fz_context *ctx, document_t *doc, fz_document *fzdoc) {
         err = ctx->error.errcode;
 
     if (err != 0) {
+        LOG_WARNINGF(doc->filepath, "fz_run_page() returned error code [%d] %s", err, ctx->error.message)
         fz_drop_page(ctx, cover);
         fz_drop_pixmap(ctx, pixmap);
         return NULL;
@@ -76,6 +82,7 @@ fz_page *render_cover(fz_context *ctx, document_t *doc, fz_document *fzdoc) {
     fz_drop_pixmap(ctx, pixmap);
 
     if (err != 0) {
+        LOG_WARNINGF(doc->filepath, "fz_new_buffer_from_pixmap_as_png() returned error code [%d] %s", err, ctx->error.message)
         fz_drop_page(ctx, cover);
         return NULL;
     }
@@ -83,14 +90,22 @@ fz_page *render_cover(fz_context *ctx, document_t *doc, fz_document *fzdoc) {
     return cover;
 }
 
-void fz_noop_callback(__attribute__((unused)) void *user, __attribute__((unused)) const char *message) {}
+void fz_err_callback(void *user, UNUSED(const char *message)) {
+    if (LogCtx.verbose) {
+        document_t *doc = (document_t *) user;
+        LOG_WARNINGF(doc->filepath, "FZ: %s", message)
+    }
+}
 
-
-void init_ctx(fz_context *ctx) {
+__always_inline
+void init_ctx(fz_context *ctx, document_t *doc) {
     fz_disable_icc(ctx);
     fz_register_document_handlers(ctx);
-    ctx->warn.print = fz_noop_callback;
-    ctx->error.print = fz_noop_callback;
+
+    ctx->warn.print_user = doc;
+    ctx->warn.print = fz_err_callback;
+    ctx->error.print_user = doc;
+    ctx->error.print = fz_err_callback;
 }
 
 int read_stext_block(fz_stext_block *block, text_buffer_t *tex) {
@@ -112,6 +127,40 @@ int read_stext_block(fz_stext_block *block, text_buffer_t *tex) {
     return 0;
 }
 
+
+void fill_image(fz_context *ctx, UNUSED(fz_device *dev),
+        fz_image *img, UNUSED(fz_matrix ctm), UNUSED(float alpha),
+        UNUSED(fz_color_params color_params)) {
+
+    int l2factor = 0;
+
+    if (img->w > MIN_OCR_SIZE && img->h > MIN_OCR_SIZE) {
+
+        fz_pixmap *pix = img->get_pixmap(ctx, img, NULL, img->w, img->h, &l2factor);
+
+        if (pix->h > MIN_OCR_SIZE && img->h > MIN_OCR_SIZE && img->xres != 0) {
+            TessBaseAPI *api = TessBaseAPICreate();
+            TessBaseAPIInit3(api, TESS_DATAPATH, ScanCtx.tesseract_lang);
+
+            TessBaseAPISetImage(api, pix->samples, pix->w, pix->h, pix->n, pix->stride);
+            TessBaseAPISetSourceResolution(api, pix->xres);
+
+            char *text = TessBaseAPIGetUTF8Text(api);
+            size_t len = strlen(text);
+            text_buffer_append_string(&thread_buffer, text, len - 1);
+            LOG_DEBUGF(
+                    "pdf.c",
+                    "(OCR) %dx%d got %dB from tesseract (%s), buffer:%dB",
+                    pix->w, pix->h, len, ScanCtx.tesseract_lang, thread_buffer.dyn_buffer.cur
+            )
+
+            TessBaseAPIEnd(api);
+            TessBaseAPIDelete(api);
+            fz_drop_pixmap(ctx, pix);
+        }
+    }
+}
+
 void parse_pdf(void *buf, size_t buf_len, document_t *doc) {
 
     if (buf == NULL) {
@@ -125,7 +174,7 @@ void parse_pdf(void *buf, size_t buf_len, document_t *doc) {
     }
     fz_context *ctx = fz_new_context(NULL, NULL, FZ_STORE_UNLIMITED);
 
-    init_ctx(ctx);
+    init_ctx(ctx, doc);
 
     int err = 0;
 
@@ -171,6 +220,7 @@ void parse_pdf(void *buf, size_t buf_len, document_t *doc) {
         err = ctx->error.errcode;
 
     if (err) {
+        LOG_WARNINGF(doc->filepath, "fz_count_pages() returned error code [%d] %s", err, ctx->error.message)
         fz_drop_stream(ctx, stream);
         fz_drop_document(ctx, fzdoc);
         fz_drop_context(ctx);
@@ -197,7 +247,7 @@ void parse_pdf(void *buf, size_t buf_len, document_t *doc) {
 
     if (ScanCtx.content_size > 0) {
         fz_stext_options opts = {0};
-        text_buffer_t text_buf = text_buffer_create(ScanCtx.content_size);
+        thread_buffer = text_buffer_create(ScanCtx.content_size);
 
         for (int current_page = 0; current_page < page_count; current_page++) {
             fz_page *page = NULL;
@@ -210,7 +260,8 @@ void parse_pdf(void *buf, size_t buf_len, document_t *doc) {
                 fz_catch(ctx)
                     err = ctx->error.errcode;
                 if (err != 0) {
-                    text_buffer_destroy(&text_buf);
+                    LOG_WARNINGF(doc->filepath, "fz_load_page() returned error code [%d] %s", err, ctx->error.message)
+                    text_buffer_destroy(&thread_buffer);
                     fz_drop_page(ctx, page);
                     fz_drop_stream(ctx, stream);
                     fz_drop_document(ctx, fzdoc);
@@ -221,6 +272,15 @@ void parse_pdf(void *buf, size_t buf_len, document_t *doc) {
 
             fz_stext_page *stext = fz_new_stext_page(ctx, fz_bound_page(ctx, page));
             fz_device *dev = fz_new_stext_device(ctx, stext, &opts);
+            dev->stroke_path = NULL;
+            dev->stroke_text = NULL;
+            dev->clip_text = NULL;
+            dev->clip_stroke_path = NULL;
+            dev->clip_stroke_text = NULL;
+
+            if (ScanCtx.tesseract_lang != NULL) {
+                dev->fill_image = fill_image;
+            }
 
             fz_var(err);
             fz_try(ctx)
@@ -234,7 +294,8 @@ void parse_pdf(void *buf, size_t buf_len, document_t *doc) {
                 err = ctx->error.errcode;
 
             if (err != 0) {
-                text_buffer_destroy(&text_buf);
+                LOG_WARNINGF(doc->filepath, "fz_run_page() returned error code [%d] %s", err, ctx->error.message)
+                text_buffer_destroy(&thread_buffer);
                 fz_drop_page(ctx, page);
                 fz_drop_stext_page(ctx, stext);
                 fz_drop_stream(ctx, stream);
@@ -245,7 +306,7 @@ void parse_pdf(void *buf, size_t buf_len, document_t *doc) {
 
             fz_stext_block *block = stext->first_block;
             while (block != NULL) {
-                int ret = read_stext_block(block, &text_buf);
+                int ret = read_stext_block(block, &thread_buffer);
                 if (ret == TEXT_BUF_FULL) {
                     break;
                 }
@@ -254,22 +315,21 @@ void parse_pdf(void *buf, size_t buf_len, document_t *doc) {
             fz_drop_stext_page(ctx, stext);
             fz_drop_page(ctx, page);
 
-            if (text_buf.dyn_buffer.cur >= text_buf.dyn_buffer.size) {
+            if (thread_buffer.dyn_buffer.cur >= thread_buffer.dyn_buffer.size) {
                 break;
             }
         }
-        text_buffer_terminate_string(&text_buf);
+        text_buffer_terminate_string(&thread_buffer);
 
-        meta_line_t *meta_content = malloc(sizeof(meta_line_t) + text_buf.dyn_buffer.cur);
+        meta_line_t *meta_content = malloc(sizeof(meta_line_t) + thread_buffer.dyn_buffer.cur);
         meta_content->key = MetaContent;
-        memcpy(meta_content->strval, text_buf.dyn_buffer.buf, text_buf.dyn_buffer.cur);
+        memcpy(meta_content->strval, thread_buffer.dyn_buffer.buf, thread_buffer.dyn_buffer.cur);
         APPEND_META(doc, meta_content)
 
-        text_buffer_destroy(&text_buf);
+        text_buffer_destroy(&thread_buffer);
     }
 
     fz_drop_stream(ctx, stream);
     fz_drop_document(ctx, fzdoc);
     fz_drop_context(ctx);
 }
-

src/parsing/pdf.h

@@ -2,6 +2,7 @@
 #define SIST2_PDF_H
 
 #include "src/sist.h"
+#include <tesseract/capi.h>
 
 
 void parse_pdf(void *buf, size_t buf_len, document_t *doc);

src/parsing/text.c

@@ -25,6 +25,7 @@ void parse_text(int bytes_read, struct vfile *f, char *buf, document_t *doc) {
     }
     text_buffer_t tex = text_buffer_create(ScanCtx.content_size);
     text_buffer_append_string(&tex, intermediate_buf, intermediate_buf_len);
+    text_buffer_terminate_string(&tex);
 
     meta_line_t *meta = malloc(sizeof(meta_line_t) + tex.dyn_buffer.cur);
     meta->key = MetaContent;

src/sist.h

@@ -2,6 +2,8 @@
 #define SIST_H
 
 #define UUID_STR_LEN 37
+#define UNUSED(x) __attribute__((__unused__))  x
+#define TESS_DATAPATH "/usr/share/tessdata/"
 
 #include <glib-2.0/glib.h>
 #include <unistd.h>
@@ -12,11 +14,11 @@
 #include <ftw.h>
 #include <uuid.h>
 #include <magic.h>
-#include <libavformat/avformat.h>
-#include <libswscale/swscale.h>
-#include <libswresample/swresample.h>
-#include <libavcodec/avcodec.h>
-#include <libavutil/imgutils.h>
+#include "libavformat/avformat.h"
+#include "libswscale/swscale.h"
+#include "libswresample/swresample.h"
+#include "libavcodec/avcodec.h"
+#include "libavutil/imgutils.h"
 #include <ctype.h>
 #include <mupdf/fitz.h>
 #include <mupdf/pdf.h>
@@ -33,14 +35,12 @@
 #include <opc/opc.h>
 #include <libxml/xmlstring.h>
 
-#ifndef SIST_SCAN_ONLY
 #include <onion/onion.h>
 #include <onion/handler.h>
 #include <onion/block.h>
 #include <onion/shortcuts.h>
 #include <onion/codecs.h>
 #include <curl/curl.h>
-#endif
 
 #include "cJSON/cJSON.h"
 
@@ -59,14 +59,13 @@
 #include "parsing/arc.h"
 #include "parsing/doc.h"
 #include "cli.h"
+#include "log.h"
 #include "utf8.h/utf8.h"
 
-#ifndef SIST_SCAN_ONLY
 #include "src/index/elastic.h"
 #include "index/web.h"
 #include "web/serve.h"
 #include "web/auth_basic.h"
-#endif
 
 ;
 

src/tpool.c

@@ -136,6 +136,7 @@ static void *tpool_worker(void *arg) {
         pthread_mutex_unlock(&(pool->work_mutex));
     }
 
+    LOG_INFO("tpool.c", "Executing cleaup function")
     pool->cleanup_func();
 
     pthread_cond_signal(&(pool->working_cond));
@@ -144,6 +145,7 @@ static void *tpool_worker(void *arg) {
 }
 
 void tpool_wait(tpool_t *pool) {
+    LOG_INFO("tpool.c", "Waiting for worker threads to finish")
     pthread_mutex_lock(&(pool->work_mutex));
     while (1) {
         if (pool->done_cnt < pool->work_cnt) {
@@ -159,6 +161,8 @@ void tpool_wait(tpool_t *pool) {
     }
     progress_bar_print(1.0, ScanCtx.stat_tn_size, ScanCtx.stat_index_size);
     pthread_mutex_unlock(&(pool->work_mutex));
+
+    LOG_INFO("tpool.c", "Worker threads finished")
 }
 
 void tpool_destroy(tpool_t *pool) {
@@ -166,6 +170,8 @@ void tpool_destroy(tpool_t *pool) {
         return;
     }
 
+    LOG_INFO("tpool.c", "Destroying thread pool")
+
     pthread_mutex_lock(&(pool->work_mutex));
     tpool_work_t *work = pool->work_head;
     while (work != NULL) {
@@ -185,6 +191,8 @@ void tpool_destroy(tpool_t *pool) {
         }
     }
 
+    LOG_INFO("tpool.c", "Final cleanup")
+
     pthread_mutex_destroy(&(pool->work_mutex));
     pthread_cond_destroy(&(pool->has_work_cond));
     pthread_cond_destroy(&(pool->working_cond));
@@ -220,6 +228,8 @@ tpool_t *tpool_create(size_t thread_cnt, void cleanup_func()) {
 
 void tpool_start(tpool_t *pool) {
 
+    LOG_INFOF("tpool.c", "Starting thread pool with %d threads", pool->thread_cnt)
+
     for (size_t i = 0; i < pool->thread_cnt; i++) {
         pthread_create(&pool->threads[i], NULL, tpool_worker, pool);
     }

src/types.h

@@ -70,8 +70,6 @@ typedef struct document {
     short ext;
     meta_line_t *meta_head;
     meta_line_t *meta_tail;
-    struct document *child_head;
-    struct document *child_tail;
     char *filepath;
 } document_t;
 
@@ -79,8 +77,6 @@ typedef struct vfile vfile_t;
 
 typedef int (*read_func_t)(struct vfile *, void *buf, size_t size);
 
-typedef int (*seek_func_t)(struct vfile *, size_t size, int whence);
-
 typedef void (*close_func_t)(struct vfile *);
 
 typedef struct vfile {

src/util.c

@@ -149,7 +149,6 @@ int text_buffer_append_string(text_buffer_t *buf, char *str, size_t len) {
         (0xe0 == (0xf0 & str[0]) && len < 3) ||
         (0xc0 == (0xe0 & str[0]) && len == 1) ||
         *(str) == 0) {
-        text_buffer_terminate_string(buf);
         return 0;
     }
 
@@ -158,7 +157,6 @@ int text_buffer_append_string(text_buffer_t *buf, char *str, size_t len) {
             text_buffer_append_char(buf, c);
         }
     }
-    text_buffer_terminate_string(buf);
     return 0;
 }
 
@@ -169,7 +167,6 @@ int text_buffer_append_string0(text_buffer_t *buf, char *str) {
             text_buffer_append_char(buf, c);
         }
     }
-    text_buffer_terminate_string(buf);
 }
 
 int text_buffer_append_char(text_buffer_t *buf, int c) {

src/util.h

@@ -7,7 +7,7 @@
 #define INITIAL_BUF_SIZE 1024 * 16
 
 #define SHOULD_IGNORE_CHAR(c) !(SHOULD_KEEP_CHAR(c))
-#define SHOULD_KEEP_CHAR(c) (c >= (int)'!')
+#define SHOULD_KEEP_CHAR(c) ((c >= '0' && c <= '9') || (c >= 'A' && c <= 'z') || (c > 127))
 
 
 typedef struct dyn_buffer {

web/css/dark.css

@@ -2,6 +2,23 @@
     outline: 0;
 }
 
+.path-row {
+    display: -ms-flexbox;
+    display: flex;
+    -ms-flex-align: start;
+    align-items: flex-start;
+}
+
+.tag-container {
+    margin-left: 0.3rem;
+}
+
+.path-line {
+    color: #BBB;
+    text-overflow: ellipsis;
+    overflow: hidden;
+}
+
 a {
     color: #00BCD4;
 }
@@ -24,7 +41,11 @@ body {
 }
 
 .sub-document {
-    background: #37474F;
+    background: #37474F !important;
+}
+
+.list-group-item.sub-document {
+    border-top: 1px solid #646464 !important;
 }
 
 .sub-document .text-muted {
@@ -112,6 +133,7 @@ body {
 }
 
 .file-title {
+    width: 100%;
     font-size: 10pt;
     white-space: nowrap;
     text-overflow: ellipsis;

web/css/jquery.toast.min.css

@@ -0,0 +1 @@
+.jq-toast-wrap,.jq-toast-wrap *{margin:0;padding:0}.jq-toast-wrap{display:block;position:fixed;width:250px;pointer-events:none!important;letter-spacing:normal;z-index:9000!important}.jq-toast-wrap.bottom-left{bottom:20px;left:20px}.jq-toast-wrap.bottom-right{bottom:20px;right:40px}.jq-toast-wrap.top-left{top:20px;left:20px}.jq-toast-wrap.top-right{top:20px;right:40px}.jq-toast-single{display:block;width:100%;padding:10px;margin:0 0 5px;border-radius:4px;font-size:12px;font-family:arial,sans-serif;line-height:17px;position:relative;pointer-events:all!important;background-color:#444;color:#fff}.jq-toast-single h2{font-family:arial,sans-serif;font-size:14px;margin:0 0 7px;background:0 0;color:inherit;line-height:inherit;letter-spacing:normal}.jq-toast-single a{color:#eee;text-decoration:none;font-weight:700;border-bottom:1px solid #fff;padding-bottom:3px;font-size:12px}.jq-toast-single ul{margin:0 0 0 15px;background:0 0;padding:0}.jq-toast-single ul li{list-style-type:disc!important;line-height:17px;background:0 0;margin:0;padding:0;letter-spacing:normal}.close-jq-toast-single{position:absolute;top:3px;right:7px;font-size:14px;cursor:pointer}.jq-toast-loader{display:block;position:absolute;top:-2px;height:5px;width:0;left:0;border-radius:5px;background:red}.jq-toast-loaded{width:100%}.jq-has-icon{padding:10px 10px 10px 50px;background-repeat:no-repeat;background-position:10px}.jq-icon-info{background-image:url(data:image/png;base64,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);background-color:#31708f;color:#d9edf7;border-color:#bce8f1}.jq-icon-warning{background-image:url(data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABgAAAAYCAYAAADgdz34AAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsMAAA7DAcdvqGQAAAGYSURBVEhL5ZSvTsNQFMbXZGICMYGYmJhAQIJAICYQPAACiSDB8AiICQQJT4CqQEwgJvYASAQCiZiYmJhAIBATCARJy+9rTsldd8sKu1M0+dLb057v6/lbq/2rK0mS/TRNj9cWNAKPYIJII7gIxCcQ51cvqID+GIEX8ASG4B1bK5gIZFeQfoJdEXOfgX4QAQg7kH2A65yQ87lyxb27sggkAzAuFhbbg1K2kgCkB1bVwyIR9m2L7PRPIhDUIXgGtyKw575yz3lTNs6X4JXnjV+LKM/m3MydnTbtOKIjtz6VhCBq4vSm3ncdrD2lk0VgUXSVKjVDJXJzijW1RQdsU7F77He8u68koNZTz8Oz5yGa6J3H3lZ0xYgXBK2QymlWWA+RWnYhskLBv2vmE+hBMCtbA7KX5drWyRT/2JsqZ2IvfB9Y4bWDNMFbJRFmC9E74SoS0CqulwjkC0+5bpcV1CZ8NMej4pjy0U+doDQsGyo1hzVJttIjhQ7GnBtRFN1UarUlH8F3xict+HY07rEzoUGPlWcjRFRr4/gChZgc3ZL2d8oAAAAASUVORK5CYII=);background-color:#8a6d3b;color:#fcf8e3;border-color:#faebcc}.jq-icon-error{background-image:url(data:image/png;base64,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);background-color:#a94442;color:#f2dede;border-color:#ebccd1}.jq-icon-success{background-image:url(data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABgAAAAYCAYAAADgdz34AAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsMAAA7DAcdvqGQAAADsSURBVEhLY2AYBfQMgf///3P8+/evAIgvA/FsIF+BavYDDWMBGroaSMMBiE8VC7AZDrIFaMFnii3AZTjUgsUUWUDA8OdAH6iQbQEhw4HyGsPEcKBXBIC4ARhex4G4BsjmweU1soIFaGg/WtoFZRIZdEvIMhxkCCjXIVsATV6gFGACs4Rsw0EGgIIH3QJYJgHSARQZDrWAB+jawzgs+Q2UO49D7jnRSRGoEFRILcdmEMWGI0cm0JJ2QpYA1RDvcmzJEWhABhD/pqrL0S0CWuABKgnRki9lLseS7g2AlqwHWQSKH4oKLrILpRGhEQCw2LiRUIa4lwAAAABJRU5ErkJggg==);color:#dff0d8;background-color:#3c763d;border-color:#d6e9c6}

web/css/light.css

@@ -2,6 +2,23 @@
     outline: 0;
 }
 
+.path-row {
+    display: -ms-flexbox;
+    display: flex;
+    -ms-flex-align: start;
+    align-items: flex-start;
+}
+
+.tag-container {
+    margin-left: 0.3rem;
+}
+
+.path-line {
+    color: #444;
+    text-overflow: ellipsis;
+    overflow: hidden;
+}
+
 body {
     overflow-y: scroll;
 }
@@ -16,7 +33,7 @@ body {
 }
 
 .sub-document {
-    background: #AB47BC1F;
+    background: #AB47BC1F !important;
 }
 
 .navbar-brand {
@@ -82,6 +99,7 @@ body {
 }
 
 .file-title {
+    width: 100%;
     font-size: 10pt;
     white-space: nowrap;
     text-overflow: ellipsis;

web/js/dom.js

@@ -367,6 +367,10 @@ function createDocLine(hit) {
     const line = document.createElement("div");
     line.setAttribute("class", "list-group-item flex-column align-items-start");
 
+    if (hit["_source"].hasOwnProperty("parent")) {
+        line.classList.add("sub-document");
+        isSubDocument = true;
+    }
 
     const title = makeTitle(hit);
 
@@ -396,8 +400,16 @@ function createDocLine(hit) {
         titleDiv.appendChild(contentDiv);
     }
 
+    let pathLine = document.createElement("div");
+    pathLine.setAttribute("class", "path-row");
+
+    let path = document.createElement("div");
+    path.setAttribute("class", "path-line");
+    path.setAttribute("title", hit["_source"]["path"] + "/");
+    path.appendChild(document.createTextNode(hit["_source"]["path"] + "/"));
+
     let tagContainer = document.createElement("div");
-    tagContainer.setAttribute("class", "");
+    tagContainer.setAttribute("class", "tag-container");
 
     for (let i = 0; i < tags.length; i++) {
         tagContainer.appendChild(tags[i]);
@@ -409,7 +421,9 @@ function createDocLine(hit) {
     sizeTag.setAttribute("class", "text-muted");
     tagContainer.appendChild(sizeTag);
 
-    titleDiv.appendChild(tagContainer);
+    titleDiv.appendChild(pathLine);
+    pathLine.appendChild(path);
+    pathLine.appendChild(tagContainer);
 
     return line;
 }

web/js/search.js

@@ -19,6 +19,19 @@ if (localStorage.getItem("mode") === null) {
     mode = localStorage.getItem("mode")
 }
 
+function showEsError() {
+    $.toast({
+        heading: "Elasticsearch connection error",
+        text: "sist2 web module encountered an error while connecting " +
+            "to Elasticsearch. See server logs for more information.",
+        stack: false,
+        bgColor: "#a94442",
+        textColor: "#f2dede",
+        position: 'bottom-right',
+        hideAfter: false
+    });
+}
+
 jQuery["jsonPost"] = function (url, data) {
     return jQuery.ajax({
         url: url,
@@ -26,6 +39,7 @@ jQuery["jsonPost"] = function (url, data) {
         data: JSON.stringify(data),
         contentType: "application/json"
     }).fail(err => {
+        showEsError();
         console.log(err);
     });
 };
@@ -46,19 +60,28 @@ function toggleFuzzy() {
 }
 
 $.jsonPost("i").then(resp => {
+
+    const urlIndices = (new URLSearchParams(location.search)).get("i");
+
     resp["indices"].forEach(idx => {
         const opt = $("<option>")
             .attr("value", idx.id)
             .append(idx.name);
-        if (!idx.name.includes("(nsfw)")) {
-            opt.attr("selected", !idx.name.includes("(nsfw)"));
+
+        if (urlIndices) {
+            if (urlIndices.split(",").indexOf(idx.name) !== -1) {
+                opt.attr("selected", true);
+                selectedIndices.push(idx.id);
+            }
+        } else if (!idx.name.includes("(nsfw)")) {
+            opt.attr("selected", true);
             selectedIndices.push(idx.id);
         }
         $("#indices").append(opt);
     });
 });
 
-function handleTreeClick (tree) {
+function handleTreeClick(tree) {
     return (event, node, handler) => {
         event.preventTreeDefault();
 
@@ -127,7 +150,7 @@ $.jsonPost("es", {
 
 function leafTag(tag) {
     const tokens = tag.split(".");
-    return tokens[tokens.length-1]
+    return tokens[tokens.length - 1]
 }
 
 // Tags tree
@@ -145,8 +168,8 @@ $.jsonPost("es", {
     resp["aggregations"]["tags"]["buckets"]
         .sort((a, b) => a["key"].localeCompare(b["key"]))
         .forEach(bucket => {
-        addTag(tagMap, bucket["key"], bucket["key"], bucket["doc_count"])
-    });
+            addTag(tagMap, bucket["key"], bucket["key"], bucket["doc_count"])
+        });
 
     tagMap.push({"text": "All", "id": "any"});
     tagTree = new InspireTree({

web/search.html

@@ -11,7 +11,7 @@
 
 <nav class="navbar navbar-expand-lg">
     <a class="navbar-brand" href="/">sist2</a>
-    <span class="badge badge-pill version">v1.1.11</span>
+    <span class="badge badge-pill version">v1.2.0</span>
     <span class="tagline">Lightning-fast file system indexer and search tool </span>
     <a style="margin-left: auto" id="theme" class="btn" title="Toggle theme" href="/">Theme</a>
 </nav>