Update CI script

Wip doc

CMakeLists.txt

@@ -4,6 +4,8 @@ set(CMAKE_C_STANDARD 11)
 project(sist2 C)
 list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_LIST_DIR}/CMakeModules")
 
+option(SIST_DEBUG "Build a debug executable" on)
+
 add_executable(
         sist2
         src/main.c
@@ -26,6 +28,7 @@ add_executable(
         src/parsing/arc.c src/parsing/arc.h
         src/parsing/doc.c src/parsing/doc.h
         src/log.c src/log.h
+        src/parsing/cbr.h src/parsing/cbr.c
 
         # argparse
         argparse/argparse.h argparse/argparse.c
@@ -80,14 +83,40 @@ target_link_directories(
         ${UUID_LIBRARY_DIRS}
 )
 
-target_compile_options(sist2
+target_compile_options(
+        sist2
         PRIVATE
-        -Ofast
-#        -march=native
         -fPIC
-        -fno-stack-protector
-        -fomit-frame-pointer
-        )
+)
+
+if (SIST_DEBUG)
+    target_compile_options(
+            sist2
+            PRIVATE
+            -g
+            -fstack-protector
+            -fno-omit-frame-pointer
+            -fsanitize=address
+    )
+    target_link_options(
+            sist2
+            PRIVATE
+            -fsanitize=address
+    )
+    set_target_properties(
+            sist2
+            PROPERTIES
+            OUTPUT_NAME sist2_debug
+    )
+else ()
+    target_compile_options(
+            sist2
+            PRIVATE
+            -Ofast
+            -fno-stack-protector
+            -fomit-frame-pointer
+    )
+endif ()
 
 TARGET_LINK_LIBRARIES(
         sist2
@@ -114,16 +143,14 @@ TARGET_LINK_LIBRARIES(
 
         m
         bz2
-        ${PROJECT_SOURCE_DIR}/lib/libmagic.a
+#        ${PROJECT_SOURCE_DIR}/lib/libmagic.a
+        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/libtesseract.a
         ${PROJECT_SOURCE_DIR}/lib/liblept.a
@@ -136,6 +163,8 @@ TARGET_LINK_LIBRARIES(
         ${PROJECT_SOURCE_DIR}/lib/libcrypto.a
         ${PROJECT_SOURCE_DIR}/lib/libssl.a
         dl
+
+        pcre
 )
 
 add_custom_target(

Docker/Dockerfile

@@ -3,7 +3,7 @@ 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
+ curl libtiff5 libpng16-16 libpcre3
 
 RUN mkdir -p /usr/share/tessdata && \
     cd /usr/share/tessdata/ && \

README.md

@@ -8,9 +8,12 @@ sist2 (Simple incremental search tool)
 
 *Warning: sist2 is in early development*
 
+![sist2.png](sist2.png)
+
 ## Features
 
 * Fast, low memory usage, multi-threaded
+* Mobile-friendly Web interface
 * Portable (all its features are packaged in a single executable)
 * Extracts text from common file types \*
 * Generates thumbnails \*
@@ -26,80 +29,53 @@ sist2 (Simple incremental search tool)
 
 ## Getting Started
 
-1. Have an [Elasticsearch](https://www.elastic.co/downloads/elasticsearch) instance running
-1. 
+1. Have an Elasticsearch (>= 6.X.X) instance running
+    1. Download [from official website](https://www.elastic.co/downloads/elasticsearch)
+    1. *(or)* Run using docker:
+        ```bash
+       docker run -d --name es1 --net sist2_net -p 9200:9200 \
+            -e "discovery.type=single-node" elasticsearch:7.5.2
+        ```
+    1. *(or)* Run using docker-compose:
+        ```yaml
+          elasticsearch:
+            image: docker.elastic.co/elasticsearch/elasticsearch:7.5.2
+            environment:
+              - discovery.type=single-node
+              - "ES_JAVA_OPTS=-Xms1G -Xmx2G"
+        ```
+1. Download sist2 executable
     1. Download the [latest sist2 release](https://github.com/simon987/sist2/releases) *
     1. *(or)* Download a [development snapshot](https://files.simon987.net/artifacts/Sist2/Build/) *(Not recommended!)*
     1. *(or)* `docker pull simon987/sist2:latest`
+
+1. See [Usage guide](USAGE.md)
    
 
 \* *Windows users*: **sist2** runs under [WSL](https://en.wikipedia.org/wiki/Windows_Subsystem_for_Linux)    
-\* *Mac users*: See [#1](https://github.com/simon987/sist2/issues/1)
 
 
 ## Example usage
 
+See [Usage guide](USAGE.md) for more details
 
-![demo](demo.gif)
-
-See help page `sist2 --help` for more details.
-
-**Scan a directory**
-```bash
-sist2 scan ~/Documents -o ./orig_idx/
-sist2 scan --threads 4 --content-size 16384 /mnt/Pictures
-sist2 scan --incremental ./orig_idx/ -o ./updated_idx/ ~/Documents
-```
-
-**Push index to Elasticsearch or file**
-```bash
-sist2 index --force-reset ./my_idx
-sist2 index --print ./my_idx > raw_documents.ndjson
-```
-
-**Start web interface**
-```bash
-sist2 web --bind 0.0.0.0 --port 4321 ./my_idx1 ./my_idx2 ./my_idx3
-```
-
-### Use sist2 with docker
-
-**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
-```
-
-**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
-```
+1. Scan a directory: `sist2 scan ~/Documents -o ./docs_idx`
+1. Push index to Elasticsearch: `sist2 index ./docs_idx`
+1. Start web interface: `sist2 web ./docs_idx`
 
 
 ## Format support
 
 File type | Library | Content | Thumbnail | Metadata
 :---|:---|:---|:---|:---
-pdf,xps,cbz,fb2,epub | MuPDF | text+ocr | yes, `png` | title |
+pdf,xps,cbz,cbr,fb2,epub | MuPDF | text+ocr | yes, `png` | title |
 `audio/*` | ffmpeg | - | yes, `jpeg` | ID3 tags |
 `video/*` | ffmpeg | - | yes, `jpeg` | title, comment, artist |
-`image/*` | ffmpeg | - | yes, `jpeg` | `EXIF:Artist`, `EXIF:ImageDescription` |
+`image/*` | ffmpeg | - | yes, `jpeg` | [Common EXIF tags](https://github.com/simon987/sist2/blob/efdde2734eca9b14a54f84568863b7ffd59bdba3/src/parsing/media.c#L190) |
 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 |
+docx, xlsx, pptx | *(none)* | yes | no | no |
 
 \* *See [Archive files](#archive-files)*
  
@@ -120,11 +96,11 @@ To check if a media file can be parsed without *seek*, execute `cat file.mp4 | f
  
 ### OCR
 
-You can enable OCR support for pdf,xps,cbz,fb2,epub file types with the
+You can enable OCR support for pdf,xps,cbz,cbr,fb2,epub file types with the
 `--ocr <lang>` option. Download the language data files with your
 package manager (`apt install tesseract-ocr-eng`) or directly [from Github](https://github.com/tesseract-ocr/tesseract/wiki/Data-Files).
 
-The `simon987/sist2` github image comes with common languages 
+The `simon987/sist2` image comes with common languages 
 (hin, jpn, eng, fra, rus, spa) pre-installed.
 
 Examples
@@ -145,8 +121,9 @@ binaries.
     ```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
+        libcurl4-openssl-dev libbz2-dev yasm libharfbuzz-dev ragel \
+        libarchive-dev libtiff5 libpng16-16 libpango1.0-dev \
+        libxml2-dev libopenjp2-7-dev libleptonica-dev
    ```
 
 2. Build

USAGE.md

@@ -0,0 +1,275 @@
+# Usage
+
+*More examples (specifically with docker/compose) are in progress*
+
+* [scan](#scan)
+    * [options](#scan-options)
+    * [examples](#scan-examples)
+    * [index format](#index-format)
+* [index](#index)
+    * [options](#index-options)
+    * [examples](#index-examples)
+* [web](#web)
+    * [options](#web-options)
+    * [examples](#web-examples)
+    * [rewrite_url](#rewrite_url)
+    * [link to specific indices](#link-to-specific-indices)
+
+```
+Usage: sist2 scan [OPTION]... PATH
+   or: sist2 index [OPTION]... INDEX
+   or: sist2 web [OPTION]... INDEX...
+Lightning-fast file system indexer and search tool.
+
+    -h, --help            show this help message and exit
+    -v, --version         Show version and exit
+    --verbose             Turn on logging
+    --very-verbose        Turn on debug messages
+
+Scan options
+    -t, --threads=<int>   Number of threads. DEFAULT=1
+    -q, --quality=<flt>   Thumbnail quality, on a scale of 1.0 to 31.0, 1.0 being the best. DEFAULT=5
+    --size=<int>          Thumbnail size, in pixels. Use negative value to disable. DEFAULT=500
+    --content-size=<int>  Number of bytes to be extracted from text documents. Use negative value to disable. DEFAULT=32768
+    --incremental=<str>   Reuse an existing index and only scan modified files.
+    -o, --output=<str>    Output directory. DEFAULT=index.sist2/
+    --rewrite-url=<str>   Serve files from this url instead of from disk.
+    --name=<str>          Index display name. DEFAULT: (name of the directory)
+    --depth=<int>         Scan up to DEPTH subdirectories deep. Use 0 to only scan files in PATH. DEFAULT: -1
+    --archive=<str>       Archive file mode (skip|list|shallow|recurse). skip: Don't parse, list: only get file names as text, shallow: Don't parse archives inside archives. DEFAULT: recurse
+    --ocr=<str>           Tesseract language (use tesseract --list-langs to see which are installed on your machine)
+    -e, --exclude=<str>   Files that match this regex will not be scanned
+    --fast                Only index file names & mime type
+
+Index options
+    --es-url=<str>        Elasticsearch url with port. DEFAULT=http://localhost:9200
+    -p, --print           Just print JSON documents to stdout.
+    --script-file=<str>   Path to user script.
+    --batch-size=<int>    Index batch size. DEFAULT: 100
+    -f, --force-reset     Reset Elasticsearch mappings and settings. (You must use this option the first time you use the index command)
+
+Web options
+    --es-url=<str>        Elasticsearch url. DEFAULT=http://localhost:9200
+    --bind=<str>          Listen on this address. DEFAULT=localhost
+    --port=<str>          Listen on this port. DEFAULT=4090
+    --auth=<str>          Basic auth in user:password format
+Made by simon987 <me@simon987.net>. Released under GPL-3.0
+
+```
+
+## Scan
+
+### Scan options
+
+* `-t, --threads` 
+      Number of threads for file parsing. **Do not set a number higher than `$(nproc)`!**.
+* `-q, --quality` 
+    Thumbnail quality, on a scale of 1.0 to 31.0, 1.0 being the best. *Does not affect PDF thumbnails quality*
+* `--size` 
+    Thumbnail size in pixels.
+* `--content-size` 
+    Number of bytes of text to be extracted from the content of files (plain text and PDFs).
+    Repeated whitespace and special characters do not count toward this limit.
+* `--incremental`
+    Specify an existing index. Information about files in this index that were not modified (based on *mtime* attribute)
+    will be copied to the new index and will not be parsed again.
+* `-o, --output` Output directory. 
+* `--rewrite-url` Set the `rewrite_url` option for the web module (See [rewrite_url](#rewrite_url)) 
+* `--name` Set the `name` option for the web module
+* `--depth` Maximum scan dept. Set to 0 only scan files directly in the root directory, set to -1 for infinite depth
+* `--archive` Archive file mode.
+    * skip: Don't parse
+    * list: Only get file names as text
+    * shallow: Don't parse archives inside archives.
+    * recurse: Scan archives recursively (default)
+* `--ocr` See [OCR](README.md#OCR)
+* `-e, --exclude` Regex pattern to exclude files. A file is excluded if the pattern matches any 
+    part of the full absolute path.
+    
+    Examples: 
+    * `-e ".*\.ttf"`: Ignore ttf files
+    * `-e ".*\.(ttf|rar)"`: Ignore ttf and rar files
+    * `-e "^/mnt/backups/"`: Ignore all files in the `/mnt/backups/` directory
+    * `-e "^/mnt/Data[12]/"`: Ignore all files in the `/mnt/Data1/` and `/mnt/Data2/` directory
+    * `-e "(^/usr/)|(^/var/)|(^/media/DRIVE-A/tmp/)|(^/media/DRIVE-B/Trash/)"` Exclude the
+     `/usr`, `/var`, `/media/DRIVE-A/tmp`, `/media/DRIVE-B/Trash` directories
+* `--fast` Only index file names and mime type
+
+### Scan examples
+
+Simple scan
+```bash
+sist2 scan ~/Documents
+
+sist2 scan \
+    --threads 4 --content-size 16000000 --quality 1.0 --archive shallow \
+    --name "My Documents" --rewrite-url "http://nas.domain.local/My Documents/" \
+    ~/Documents -o ./documents.idx/
+```
+
+Incremental scan
+```
+sist2 scan --incremental ./orig_idx/ -o ./updated_idx/ ~/Documents
+```
+
+### Index format
+
+A typical `binary` type index structure looks like this:
+```
+documents.idx/
+├── descriptor.json
+├── _index_139965416830720
+├── _index_139965425223424
+├── _index_139965433616128
+├── _index_139965442008832
+└── thumbs
+    ├── data.mdb
+    └── lock.mdb
+```
+
+The `_index_*` files contain the raw binary index data and are not meant to be
+read by other applications. The format is generally compatible across different 
+sist2 versions.
+
+The `thumbs/` folder is a [LMDB](https://en.wikipedia.org/wiki/Lightning_Memory-Mapped_Database)
+database containing the thumbnails.
+
+The `descriptor.json` file contains general information about the index. The 
+following fields are safe to modify manually: `root`, `name`, [rewrite_url](#rewrite_url) and `timestamp`.
+
+
+*Advanced usage*
+
+Instead of using the `scan` module, you can also import an index generated
+by a third party application. The 'external' index must have the following format:
+
+```
+my_index/
+├── descriptor.json
+├── _index_0
+└── thumbs
+    ├── data.mdb
+    └── lock.mdb
+```
+
+*descriptor.json*:
+```json
+{
+    "uuid": "<valid UUID4>",
+    "version": "_external_v1",
+    "root": "(optional)",
+    "name": "<name>",
+    "rewrite_url": "(optional)",
+    "type": "json",
+    "timestamp": 1578971024
+}
+```
+
+*_index_0*: NDJSON format (One json object per line)
+
+```json
+{
+  "_id": "unique uuid for the file",
+  "index": "index uuid4 (same one as descriptor.json!)",
+  "mime": "application/x-cbz",
+  "size": 14341204,
+  "mtime": 1578882996,
+  "extension": "cbz",
+  "name": "my_book",
+  "path": "path/to/books",
+  "content": "text contents of the book",
+  "title": "Title of the book",
+  "tag": ["genre.fiction", "author.someguy", "etc..."],
+  "_keyword": [
+    {"k": "ISBN", "v": "ABCD34789231"}
+  ],
+  "_text": [
+    {"k": "other", "v": "This will be indexed as text"}
+  ]
+}
+```
+
+You can find the full list of supported fields [here](src/io/serialize.c#L90)
+
+The `_keyword.*` items will be indexed and searchable as **keyword** fields (only full matches allowed).
+The `_text.*` items will be indexed and searchable as **text** fields (fuzzy searching allowed)
+
+
+*thumbs/*:
+
+LMDB key-value store. Keys are **binary** 128-bit UUID4s (`_id` field)
+and values are raw image bytes.
+
+Importing an external `binary` type index is technically possible but
+it is currently unsupported and has no guaranties of back/forward compatibility.
+
+
+## Index
+### Index options
+ * `--es-url` 
+ Elasticsearch url and port. If you are using docker, make sure that both containers are on the
+ same network.
+ * `-p, --print` 
+    Print index in JSON format to stdout.
+ * `--script-file` 
+    Path to user script. See [Scripting](scripting/README.md).
+ * `--batch-size=<int>` 
+    Index batch size. Indexing is generally faster with larger batches, but payloads that
+    are too large will fail and additional overhead for retrying with smaller sizes may slow
+    down the process.
+ * `-f, --force-reset` 
+    Reset Elasticsearch mappings and settings.
+    **(You must use this option the first time you use the index command)**.
+    
+### Index examples
+
+**Push to elasticsearch**
+```bash
+sist2 index --force-reset --batch-size 1000 --es-url http://localhost:9200 ./my_index/
+sist2 index ./my_index/
+```
+
+**Save index in JSON format**
+```bash
+sist2 index --print ./my_index/ > my_index.ndjson
+```
+
+**Inspect contents of an index**
+```bash
+sist2 index --print ./my_index/ | jq | less
+```
+
+## Web
+
+### Web options
+ * `--es-url=<str>` Elasticsearch url.
+ * `--bind=<str>` Listen on this address.
+ * `--port=<str>` Listen on this port.
+ * `--auth=<str>` Basic auth in user:password format
+ 
+### Web examples
+
+**Single index**
+```bash
+sist2 web --auth admin:hunter2 --bind 0.0.0.0 --port 8888 my_index
+```
+
+**Multiple indices**
+```bash
+# Indices will be displayed in this order in the web interface
+sist2 web index1 index2 index3 index4
+```
+
+### rewrite_url
+
+When the `rewrite_url` field is not empty, the web module ignores the `root`
+field and will return a HTTP redirect to `<rewrite_url><path>/<name><extension>`
+instead of serving the file from disk. 
+Both the `root` and `rewrite_url` fields are safe to manually modify from the 
+`descriptor.json` file.
+
+### Link to specific indices
+
+To link to specific indices, you can add a list of comma-separated index name to 
+the URL: `?i=<name>,<name>`. By default, indices with `"(nsfw)"` in their name are
+not displayed.

ci/build.sh

@@ -2,6 +2,11 @@
 
 ./scripts/get_static_libs.sh
 
-cmake .
+rm -rf CMakeFiles CmakeCache.txt
+cmake -DSIST_DEBUG=off .
 make
 strip sist2
+
+rm -rf CMakeFiles CmakeCache.txt
+cmake -DSIST_DEBUG=on .
+make

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_ */

mime.csv

@@ -2,10 +2,14 @@ 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
@@ -17,7 +21,6 @@ application/inf, inf
 application/java-archive, jar
 application/java, class
 application/javascript,
-application/x-archive, a
 application/json, json
 application/marc, mrc
 application/mbedlet, mbd
@@ -27,7 +30,9 @@ application/msword, doc|dot|w6w|wiz|word
 application/netmc, mcp
 application/octet-stream, bin|dump|gpg
 application/oda, oda
+application/ogg, ogv
 application/pdf, pdf
+application/pgp-keys,
 application/pgp-signature, pgp
 application/pkcs7-signature, p7s
 application/pkix-cert, cer|crt
@@ -43,6 +48,10 @@ 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 +63,75 @@ application/vnd.ms-project, mpp
 application/vnd.oasis.opendocument.base, odb
 application/vnd.oasis.opendocument.formula, odf
 application/vnd.oasis.opendocument.graphics, odg
+application/vnd.oasis.opendocument.presentation, odp
+application/vnd.oasis.opendocument.spreadsheet, ods
 application/vnd.oasis.opendocument.text, odt
+application/vnd.openxmlformats-officedocument.presentationml.presentation, pptx
+application/vnd.openxmlformats-officedocument.spreadsheetml.sheet, xlsx
+application/vnd.openxmlformats-officedocument.wordprocessingml.document, docx
+application/vnd.symbian.install,
+application/vnd.tcpdump.pcap, pcap
 application/vnd.wap.wmlc, wmlc
 application/vnd.wap.wmlscriptc, wmlsc
 application/vnd.xara, web
 application/vocaltec-media-desc, vmd
 application/vocaltec-media-file, vmf
+application/warc, warc
+application/winhelp, hlp
 application/wordperfect6.0, w60
 application/wordperfect6.1, w61
 application/wordperfect, wp|wp5|wp6|wpd
 application/x-123, wk1
+application/x-7z-compressed, 7z
 application/x-aim, aim
+application/x-apple-diskimage,
+application/x-arc,
+application/x-archive, a
+application/x-atari-7800-rom, a78
 application/x-authorware-bin, aab
 application/x-authorware-map, aam
 application/x-authorware-seg, aas
+application/x-avira-qua,
 application/x-bcpio, bcpio
 application/x-bittorrent, torrent
 application/x-bsh, bsh
 application/x-bytecode.python, pyc
 application/x-bzip2, boz|bz2
 application/x-bzip, bz
+application/x-cbr, cbr
+application/x-cbz, cbz
 application/x-cdlink, vcd
 application/x-chat, cha|chat
+application/x-chrome-extension,
 application/x-cocoa, cco
 application/x-conference, nsc
+application/x-coredump,
 application/x-cpio, cpio
 application/x-dbf, dbf
 application/x-dbt,
+application/x-debian-package, deb
 application/x-deepv, deepv
 application/x-director, dcr|dir|dxr
+application/x-dmp, dmp
+application/x-dosdriver,
 application/x-dosexec, dll
 application/x-dvi, dvi
 application/x-elc, elc
+application/x-empty,
 application/x-envoy, env|evy
 application/x-esrehber, es
 application/x-excel, xla|xld|xlk|xlt|xlv
 application/x-executable, exe
+application/x-font-gdos,
+application/x-font-pf2, pf2
+application/x-font-pfm, pfm
 application/x-font-sfn,
 application/x-font-ttf, ttf|ttc
+application/x-fptapplication/x-dbt,
 application/x-freelance, pre
+application/x-gamecube-rom,
+application/x-gdbm,
+application/x-gettext-translation,
 application/x-git,
 application/x-gsp, gsp
 application/x-gss, gss
@@ -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-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/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
@@ -163,16 +228,22 @@ application/x-vnd.audioexplosion.mzz, mzz
 application/x-vnd.ls-xpix, xpix
 application/x-vrml, vrml
 application/x-wais-source, src|wsrc
+application/x-wine-extension-ini,
 application/x-wintalk, wtk
 application/x-world, svr
 application/x-wri, wri
 application/x-x509-ca-cert, der
 application/x-xz, xz
+application/x-zip,
+application/x-zstd, zst
 application/zip, zip
+application/zlib, z
+!audio/basic, au
 audio/it, it
 audio/make, funk|my|pfunk
 audio/midi, kar
 audio/mid, rmi
+audio/mp4, m4b
 audio/mpeg, m2a|mpa
 audio/ogg, ogg
 audio/s3m, s3m
@@ -180,7 +251,10 @@ 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 +326,30 @@ 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/PGP,
 text/plain, com|cmd|conf|def|g|idc|list|lst|mar|sdml|text|txt|md|groovy|license|properties|desktop|ini|rst|cmake|ipynb|readme|less|lo|go|yml|d|cs|hpp|srt|nfo|sfv|m3u|csv|eml
 text/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 +361,7 @@ 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 +376,31 @@ 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-po, po
 text/x-python, py
 text/x-ruby, rb
+text/x-sass, sass
+text/x-scss, scss
 text/x-server-parsed-html, ssi
 text/x-setext, etx
 text/x-sgml, sgm|sgml
 text/x-shellscript, sh
 text/x-speech, talk
+text/x-tcl,
 text/x-tex, tex
 text/x-uil, uil
 text/x-uuencode, uue
 text/x-vcalendar, vcs
+text/x-vcard, vcf
 video/animaflex, afl
 video/avi, avi
 video/avs-video, avs
+video/MP2T,
 video/mp4, mp4
 video/mpeg, m1v|m2v|mpe|mpeg|mpg
 video/quicktime, moov|mov|qt
@@ -318,101 +415,15 @@ 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

schema/mappings.json

@@ -1,13 +1,17 @@
 {
   "properties": {
+    "_tie": {
+      "type": "keyword",
+      "doc_values": true
+    },
+    "_depth": {
+      "type": "integer"
+    },
     "path": {
       "type": "text",
       "analyzer": "path_analyzer",
-      "copy_to": "suggest-path"
-    },
-    "suggest-path": {
-      "type": "completion",
-      "analyzer": "case_insensitive_kw_analyzer"
+      "fielddata": true,
+      "index_prefixes": {}
     },
     "mime": {
       "type": "keyword"
@@ -105,6 +109,30 @@
     },
     "tag": {
       "type": "keyword"
+    },
+    "exif_make": {
+      "type": "text"
+    },
+    "exif_model": {
+      "type": "text"
+    },
+    "exif:software": {
+      "type": "text"
+    },
+    "exif_exposure_time": {
+      "type": "keyword"
+    },
+    "exif_fnumber": {
+      "type": "keyword"
+    },
+    "exif_iso_speed_ratings": {
+      "type": "keyword"
+    },
+    "exif_focal_length": {
+      "type": "keyword"
+    },
+    "exif_user_comment": {
+      "type": "text"
     }
   }
 }

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();"
+      }
+    }
+  ]
+}

scripting/README.md

@@ -54,6 +54,11 @@ 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:
@@ -115,3 +120,33 @@ if (ctx._source.path != "") {
     tags.add("studio." + names[names.length-1]);
 }
 ```
+
+Parse `EXIF:F Number` tag
+```Java
+if (ctx._source?.exif_fnumber != null) {
+    String[] values = ctx._source.exif_fnumber.splitOnToken(' ');
+    String aperture = String.valueOf(Float.parseFloat(values[0]) / Float.parseFloat(values[1]));
+    if (aperture == "NaN") {
+        aperture = "0,0";
+    }
+    tags.add("Aperture.f/" + aperture.replace(".", ","));
+}
+```
+
+Display year and months from `EXIF:DateTime` tag
+```Java
+if (ctx._source?.exif_datetime != null) {
+    SimpleDateFormat parser = new SimpleDateFormat("yyyy:MM:dd HH:mm:ss");
+    Date date = parser.parse(ctx._source.exif_datetime);
+
+    SimpleDateFormat yp = new SimpleDateFormat("yyyy");
+    SimpleDateFormat mp = new SimpleDateFormat("MMMMMMMMM");
+
+    String year = yp.format(date);
+    String month = mp.format(date);
+
+    tags.add("Month." + month);
+    tags.add("Year." + year);
+}
+
+```

scripts/get_static_libs.sh

@@ -13,7 +13,7 @@ mv mupdf/build/release/libmupdf-third.a .
 
 # openjp2
 cd openjpeg
-cmake . -DCMAKE_BUILD_TYPE=Release -DCMAKE_C_FLAGS="-O3 -march=native -DNDEBUG -fPIC"
+cmake . -DCMAKE_BUILD_TYPE=Release -DCMAKE_C_FLAGS="-O3 -DNDEBUG -fPIC"
 make -j $THREADS
 cd ..
 mv openjpeg/bin/libopenjp2.a .
@@ -75,7 +75,7 @@ cd tesseract
 mkdir build
 cd build
 cmake -DSTATIC=on -DBUILD_TRAINING_TOOLS=off -DBUILD_TESTS=off -DCMAKE_BUILD_TYPE=Release \
-  -DCMAKE_CXX_FLAGS="-fPIC"  ..
+  -DCMAKE_CXX_FLAGS="-fPIC" -DAUTO_OPTIMIZE=off ..
 make -j $THREADS
 cd ../..
 mv tesseract/build/libtesseract.a .

scripts/index_static.py

@@ -1,6 +1,9 @@
+import json
+
 files = [
     "schema/mappings.json",
     "schema/settings.json",
+    "schema/pipeline.json",
 ]
 
 
@@ -9,6 +12,6 @@ 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()
     print("char %s[%d] = {%s};" % (clean(file), len(data), ",".join(str(int(b)) for b in data)))

src/cli.c

@@ -1,8 +1,6 @@
 #include "cli.h"
 #include "ctx.h"
 
-#include <tesseract/capi.h>
-
 #define DEFAULT_OUTPUT "index.sist2/"
 #define DEFAULT_CONTENT_SIZE 32768
 #define DEFAULT_QUALITY 5
@@ -71,8 +69,8 @@ int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
     if (args->incremental != NULL) {
         abs_path = abspath(args->incremental);
         if (abs_path == NULL) {
-            fprintf(stderr, "File not found: %s\n", args->incremental);
-            return 1;
+            sist_log("main.c", SIST_WARNING, "Could not open original index! Disabled incremental scan feature.");
+            args->incremental = NULL;
         }
     }
 
@@ -162,6 +160,26 @@ int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
         args->tesseract_path = path;
     }
 
+    if (args->exclude_regex != NULL) {
+        const char *error;
+        int error_offset;
+
+        pcre *re = pcre_compile(args->exclude_regex, 0, &error, &error_offset, 0);
+        if (error != NULL) {
+            LOG_FATALF("cli.c", "pcre_compile returned error: %s (offset:%d)", error, error_offset)
+        }
+
+        pcre_extra *re_extra = pcre_study(re, 0, &error);
+        if (error != NULL) {
+            LOG_FATALF("cli.c", "pcre_study returned error: %s", error)
+        }
+
+        ScanCtx.exclude = re;
+        ScanCtx.exclude_extra = re_extra;
+    } else {
+        ScanCtx.exclude = NULL;
+    }
+
     LOG_DEBUGF("cli.c", "arg quality=%f", args->quality)
     LOG_DEBUGF("cli.c", "arg size=%d", args->size)
     LOG_DEBUGF("cli.c", "arg content_size=%d", args->content_size)
@@ -175,6 +193,8 @@ int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
     LOG_DEBUGF("cli.c", "arg archive=%s", args->archive)
     LOG_DEBUGF("cli.c", "arg tesseract_lang=%s", args->tesseract_lang)
     LOG_DEBUGF("cli.c", "arg tesseract_path=%s", args->tesseract_path)
+    LOG_DEBUGF("cli.c", "arg exclude=%s", args->exclude_regex)
+    LOG_DEBUGF("cli.c", "arg fast=%d", args->fast)
 
     return 0;
 }
@@ -218,7 +238,7 @@ int index_args_validate(index_args_t *args, int argc, const char **argv) {
 
         args->script = malloc(info.st_size + 1);
         res = read(fd, args->script, info.st_size);
-        if (res == -1) {
+        if (res < 0) {
             fprintf(stderr, "Error reading script file '%s': %s\n", args->script_path, strerror(errno));
             return 1;
         }

src/cli.h

@@ -18,10 +18,14 @@ typedef struct scan_args {
     archive_mode_t archive_mode;
     char *tesseract_lang;
     const char *tesseract_path;
+    char *exclude_regex;
+    int fast;
 } scan_args_t;
 
 scan_args_t *scan_args_create();
+
 void scan_args_destroy(scan_args_t *args);
+
 int scan_args_validate(scan_args_t *args, int argc, const char **argv);
 
 typedef struct index_args {
@@ -45,12 +49,15 @@ typedef struct web_args {
 } web_args_t;
 
 index_args_t *index_args_create();
+
 void index_args_destroy(index_args_t *args);
 
 web_args_t *web_args_create();
+
 void web_args_destroy(web_args_t *args);
 
 int index_args_validate(index_args_t *args, int argc, const char **argv);
+
 int web_args_validate(web_args_t *args, int argc, const char **argv);
 
 #endif

src/ctx.h

@@ -28,7 +28,10 @@ struct {
 
     pthread_mutex_t mupdf_mu;
     char * tesseract_lang;
-    char * tesseract_path;
+    const char * tesseract_path;
+    pcre *exclude;
+    pcre_extra *exclude_extra;
+    int fast;
 } ScanCtx;
 
 struct {

src/index/elastic.c

@@ -1,12 +1,6 @@
 #include "elastic.h"
 #include "src/ctx.h"
 
-#include <stdlib.h>
-#include "web.h"
-#include <stdio.h>
-#include <string.h>
-#include <cJSON/cJSON.h>
-
 #include "static_generated.c"
 
 
@@ -20,6 +14,8 @@ typedef struct es_indexer {
 
 static es_indexer_t *Indexer;
 
+void delete_queue(int max);
+
 void print_json(cJSON *document, const char uuid_str[UUID_STR_LEN]) {
 
     cJSON *line = cJSON_CreateObject();
@@ -64,7 +60,7 @@ void execute_update_script(const char *script, const char index_id[UUID_STR_LEN]
     cJSON *term_obj = cJSON_AddObjectToObject(query, "term");
     cJSON_AddStringToObject(term_obj, "index", index_id);
 
-    char * str = cJSON_Print(body);
+    char *str = cJSON_Print(body);
 
     char bulk_url[4096];
     snprintf(bulk_url, 4096, "%s/sist2/_update_by_query?pretty", Indexer->es_url);
@@ -87,24 +83,18 @@ void execute_update_script(const char *script, const char index_id[UUID_STR_LEN]
     cJSON_Delete(resp);
 }
 
-void elastic_flush() {
-
-    if (Indexer == NULL) {
-        Indexer = create_indexer(IndexCtx.es_url);
-    }
-
+void *create_bulk_buffer(int max, int *count, size_t *buf_len) {
     es_bulk_line_t *line = Indexer->line_head;
-
-    int count = 0;
+    *count = 0;
 
     size_t buf_size = 0;
     size_t buf_cur = 0;
     char *buf = malloc(1);
 
-    while (line != NULL) {
+    while (line != NULL && *count < max) {
         char action_str[512];
         snprintf(action_str, 512,
-                "{\"index\":{\"_id\":\"%s\", \"_type\":\"_doc\", \"_index\":\"sist2\"}}\n", line->uuid_str);
+                 "{\"index\":{\"_id\":\"%s\", \"_type\":\"_doc\", \"_index\":\"sist2\"}}\n", line->uuid_str);
         size_t action_str_len = strlen(action_str);
 
         size_t line_len = strlen(line->line);
@@ -116,46 +106,105 @@ void elastic_flush() {
         memcpy(buf + buf_cur, line->line, line_len);
         buf_cur += line_len;
 
-        es_bulk_line_t *tmp = line;
         line = line->next;
-        free(tmp);
-        count++;
+        (*count)++;
     }
     buf = realloc(buf, buf_size + 1);
-    *(buf+buf_cur) = '\0';
+    *(buf + buf_cur) = '\0';
 
-    Indexer->line_head = NULL;
-    Indexer->line_tail = NULL;
-    Indexer->queued = 0;
+    *buf_len = buf_cur;
+    return buf;
+}
+
+void *print_errors(response_t *r) {
+    cJSON *ret_json = cJSON_Parse(r->body);
+    if (cJSON_GetObjectItem(ret_json, "errors")->valueint != 0) {
+        cJSON *err;
+        cJSON_ArrayForEach(err, cJSON_GetObjectItem(ret_json, "items")) {
+            if (cJSON_GetObjectItem(cJSON_GetObjectItem(err, "index"), "status")->valueint != 201) {
+                char *str = cJSON_Print(err);
+                LOG_ERRORF("elastic.c", "%s\n", str);
+                cJSON_free(str);
+            }
+        }
+    }
+    cJSON_Delete(ret_json);
+}
+
+void _elastic_flush(int max) {
+    size_t buf_len;
+    int count;
+    void *buf = create_bulk_buffer(max, &count, &buf_len);
 
     char bulk_url[4096];
-    snprintf(bulk_url, 4096, "%s/sist2/_bulk", Indexer->es_url);
+    snprintf(bulk_url, 4096, "%s/sist2/_bulk?pipeline=tie", Indexer->es_url);
     response_t *r = web_post(bulk_url, buf, "Content-Type: application/x-ndjson");
 
     if (r->status_code == 0) {
         LOG_FATALF("elastic.c", "Could not connect to %s, make sure that elasticsearch is running!\n", IndexCtx.es_url)
     }
 
-    LOG_INFOF("elastic.c", "Indexed %d documents (%zukB) <%d>", count, buf_cur / 1024, r->status_code);
+    if (r->status_code == 413) {
 
-    cJSON *ret_json = cJSON_Parse(r->body);
-    if (cJSON_GetObjectItem(ret_json, "errors")->valueint != 0) {
-        cJSON *err;
-        cJSON_ArrayForEach(err, cJSON_GetObjectItem(ret_json, "items")) {
-            if (cJSON_GetObjectItem(cJSON_GetObjectItem(err, "index"), "status")->valueint != 201) {
-                char* str = cJSON_Print(err);
-                LOG_ERRORF("elastic.c", "%s\n", str);
-                cJSON_free(str);
+        if (max <= 1) {
+            LOG_ERRORF("elastic.c", "Single document too large, giving up: {%s}", Indexer->line_head->uuid_str)
+            free_response(r);
+            free(buf);
+            delete_queue(1);
+            if (Indexer->queued != 0) {
+                elastic_flush();
             }
+            return;
+        }
+
+        LOG_WARNINGF("elastic.c", "Payload too large, retrying (%d documents)", count);
+
+        free_response(r);
+        free(buf);
+        _elastic_flush(max / 2);
+        return;
+
+    } else if (r->status_code != 200) {
+        print_errors(r);
+        delete_queue(Indexer->queued);
+
+    } else {
+
+        print_errors(r);
+        LOG_INFOF("elastic.c", "Indexed %d documents (%zukB) <%d>", count, buf_len / 1024, r->status_code);
+        delete_queue(max);
+
+        if (Indexer->queued != 0) {
+            elastic_flush();
         }
     }
 
-    cJSON_Delete(ret_json);
-
     free_response(r);
     free(buf);
 }
 
+void delete_queue(int max) {
+    for (int i = 0; i < max; i++) {
+        es_bulk_line_t *tmp = Indexer->line_head;
+        Indexer->line_head = tmp->next;
+        if (Indexer->line_head == NULL) {
+            Indexer->line_tail = NULL;
+        } else {
+            free(tmp);
+        }
+        Indexer->queued -= 1;
+    }
+}
+
+void elastic_flush() {
+
+    if (Indexer == NULL) {
+        Indexer = create_indexer(IndexCtx.es_url);
+    }
+
+    _elastic_flush(Indexer->queued);
+}
+
 void elastic_index_line(es_bulk_line_t *line) {
 
     if (Indexer == NULL) {
@@ -192,7 +241,7 @@ es_indexer_t *create_indexer(const char *url) {
     return indexer;
 }
 
-void destroy_indexer(char * script, char index_id[UUID_STR_LEN]) {
+void destroy_indexer(char *script, char index_id[UUID_STR_LEN]) {
 
     char url[4096];
 
@@ -245,6 +294,11 @@ void elastic_init(int force_reset) {
         LOG_INFOF("elastic.c", "Close index <%d>", r->status_code);
         free_response(r);
 
+        snprintf(url, 4096, "%s/_ingest/pipeline/tie", IndexCtx.es_url);
+        r = web_put(url, pipeline_json, "Content-Type: application/json");
+        LOG_INFOF("elastic.c", "Create pipeline <%d>", r->status_code);
+        free_response(r);
+
         snprintf(url, 4096, "%s/sist2/_settings", IndexCtx.es_url);
         r = web_put(url, settings_json, "Content-Type: application/json");
         LOG_INFOF("elastic.c", "Update settings <%d>", r->status_code);
@@ -278,7 +332,7 @@ cJSON *elastic_get_document(const char *uuid_str) {
 char *elastic_get_status() {
     char url[4096];
     snprintf(url, 4096,
-            "%s/_cluster/state/metadata/sist2?filter_path=metadata.indices.*.state", WebCtx.es_url);
+             "%s/_cluster/state/metadata/sist2?filter_path=metadata.indices.*.state", WebCtx.es_url);
 
     response_t *r = web_get(url);
     cJSON *json = NULL;

src/io/serialize.c

@@ -39,8 +39,8 @@ void write_index_descriptor(char *path, index_descriptor_t *desc) {
     cJSON_AddNumberToObject(json, "timestamp", (double) desc->timestamp);
 
     int fd = open(path, O_CREAT | O_WRONLY, S_IRUSR | S_IWUSR);
-    if (fd == -1) {
-        perror(path);
+    if (fd < 0) {
+        LOG_FATALF("serialize.c", "Could not write index descriptor: %s", strerror(errno));
     }
     char *str = cJSON_Print(json);
     write(fd, str, strlen(str));
@@ -57,7 +57,7 @@ index_descriptor_t read_index_descriptor(char *path) {
     int fd = open(path, O_RDONLY);
 
     if (fd == -1) {
-        LOG_FATAL("serialize.c", "Invalid/corrupt index (Could not find descriptor)\n")
+        LOG_FATALF("serialize.c", "Invalid/corrupt index (Could not find descriptor): %s: %s\n", path ,strerror(errno))
     }
 
     char *buf = malloc(info.st_size + 1);
@@ -134,6 +134,8 @@ char *get_meta_key_text(enum metakey meta_key) {
             return "exif_iso_speed_ratings";
         case MetaExifModel:
             return "exif_model";
+        case MetaExifDateTime:
+            return "exif_datetime";
         default:
             return NULL;
     }
@@ -183,7 +185,7 @@ void write_document(document_t *doc) {
 
     int res = write(index_fd, buf.buf, buf.cur);
     if (res == -1) {
-        perror("write");
+        LOG_FATALF("serialize.c", "Could not write document: %s", strerror(errno))
     }
     ScanCtx.stat_index_size += buf.cur;
     dyn_buffer_destroy(&buf);
@@ -191,6 +193,8 @@ void write_document(document_t *doc) {
 
 void thread_cleanup() {
     close(index_fd);
+    cleanup_parse();
+    cleanup_font();
 }
 
 
@@ -212,7 +216,12 @@ void read_index_bin(const char *path, const char *index_id, index_func func) {
         char uuid_str[UUID_STR_LEN];
         uuid_unparse(line.uuid, uuid_str);
 
-        cJSON_AddStringToObject(document, "mime", mime_get_mime_text(line.mime));
+        const char* mime_text = mime_get_mime_text(line.mime);
+        if (mime_text == NULL) {
+            cJSON_AddNullToObject(document, "mime");
+        } else {
+            cJSON_AddStringToObject(document, "mime", mime_get_mime_text(line.mime));
+        }
         cJSON_AddNumberToObject(document, "size", (double) line.size);
         cJSON_AddNumberToObject(document, "mtime", line.mtime);
 
@@ -278,6 +287,7 @@ void read_index_bin(const char *path, const char *index_id, index_func func) {
                 case MetaExifFocalLength:
                 case MetaExifUserComment:
                 case MetaExifIsoSpeedRatings:
+                case MetaExifDateTime:
                 case MetaExifModel:
                 case MetaTitle: {
                     buf.cur = 0;
@@ -326,7 +336,7 @@ void read_index_json(const char *path, UNUSED(const char *index_id), index_func
         char *line = NULL;
         size_t len;
         size_t read = getline(&line, &len, file);
-        if (read == -1) {
+        if (read < 0) {
             if (line) {
                 free(line);
             }

src/io/store.c

@@ -15,8 +15,7 @@ store_t *store_create(char *path) {
     );
 
     if (open_ret != 0) {
-        fprintf(stderr, "Error while opening store: %s (%s)\n", mdb_strerror(open_ret), path);
-        exit(1);
+        LOG_FATALF("store.c", "Error while opening store: %s (%s)\n", mdb_strerror(open_ret), path)
     }
 
     store->size = (size_t) 1024 * 1024 * 5;
@@ -82,7 +81,7 @@ void store_write(store_t *store, char *key, size_t key_len, char *buf, size_t bu
     pthread_rwlock_unlock(&store->lock);
 
     if (put_ret != 0) {
-        printf("%s\n", mdb_strerror(put_ret));
+        LOG_ERROR("store.c", mdb_strerror(put_ret))
     }
 }
 

src/io/walk.c

@@ -28,8 +28,18 @@ parse_job_t *create_fs_parse_job(const char *filepath, const struct stat *info,
     return job;
 }
 
+int sub_strings[30];
+#define EXCLUDED(str) (pcre_exec(ScanCtx.exclude, ScanCtx.exclude_extra, filepath, strlen(filepath), 0, 0, sub_strings, sizeof(sub_strings)) >= 0)
+
 int handle_entry(const char *filepath, const struct stat *info, int typeflag, struct FTW *ftw) {
-    if (ftw->level <= ScanCtx.depth && typeflag == FTW_F && S_ISREG(info->st_mode)) {
+
+    if (typeflag == FTW_F && S_ISREG(info->st_mode) && ftw->level <= ScanCtx.depth) {
+
+        if (ScanCtx.exclude != NULL && EXCLUDED(filepath)) {
+            LOG_DEBUGF("walk.c", "Excluded: %s", filepath)
+            return 0;
+        }
+
         parse_job_t *job = create_fs_parse_job(filepath, info, ftw->base);
         tpool_add_work(ScanCtx.pool, parse, job);
     }

src/main.c

@@ -6,7 +6,7 @@
 #define EPILOG "Made by simon987 <me@simon987.net>. Released under GPL-3.0"
 
 
-static const char *const Version = "1.2.5";
+static const char *const Version = "1.3.2";
 static const char *const usage[] = {
         "sist2 scan [OPTION]... PATH",
         "sist2 index [OPTION]... INDEX",
@@ -17,7 +17,6 @@ static const char *const usage[] = {
 void global_init() {
     curl_global_init(CURL_GLOBAL_NOTHING);
     av_log_set_level(AV_LOG_QUIET);
-    opcInitLibrary();
 }
 
 void init_dir(const char *dirpath) {
@@ -49,15 +48,19 @@ void sist2_scan(scan_args_t *args) {
     strncpy(ScanCtx.index.path, args->output, sizeof(ScanCtx.index.path));
     strncpy(ScanCtx.index.desc.name, args->name, sizeof(ScanCtx.index.desc.name));
     strncpy(ScanCtx.index.desc.root, args->path, sizeof(ScanCtx.index.desc.root));
+    strncpy(ScanCtx.index.desc.rewrite_url, args->rewrite_url, sizeof(ScanCtx.index.desc.rewrite_url));
     ScanCtx.index.desc.root_len = (short) strlen(ScanCtx.index.desc.root);
     ScanCtx.tesseract_lang = args->tesseract_lang;
     ScanCtx.tesseract_path = args->tesseract_path;
+    ScanCtx.fast = args->fast;
 
     init_dir(ScanCtx.index.path);
 
     ScanCtx.mime_table = mime_get_mime_table();
     ScanCtx.ext_table = mime_get_ext_table();
 
+    cbr_init();
+
     char store_path[PATH_MAX];
     snprintf(store_path, PATH_MAX, "%sthumbs", ScanCtx.index.path);
     mkdir(store_path, S_IWUSR | S_IRUSR | S_IXUSR);
@@ -71,9 +74,18 @@ void sist2_scan(scan_args_t *args) {
 
         DIR *dir = opendir(args->incremental);
         if (dir == NULL) {
-            perror("opendir");
-            return;
+            LOG_FATALF("main.c", "Could not open original index for incremental scan: %s", strerror(errno))
         }
+
+        char descriptor_path[PATH_MAX];
+        snprintf(descriptor_path, PATH_MAX, "%s/descriptor.json", args->incremental);
+        index_descriptor_t original_desc = read_index_descriptor(descriptor_path);
+
+        if (strcmp(original_desc.version, Version) != 0) {
+            LOG_FATALF("main.c", "Version mismatch! Index is %s but executable is %s/%s", original_desc.version,
+                       Version, INDEX_VERSION_EXTERNAL)
+        }
+
         struct dirent *de;
         while ((de = readdir(dir)) != NULL) {
             if (strncmp(de->d_name, "_index_", sizeof("_index_") - 1) == 0) {
@@ -84,7 +96,7 @@ void sist2_scan(scan_args_t *args) {
         }
         closedir(dir);
 
-        printf("Loaded %d items in to mtime table.", g_hash_table_size(ScanCtx.original_table));
+        LOG_INFOF("main.c", "Loaded %d items in to mtime table.", g_hash_table_size(ScanCtx.original_table))
     }
 
     ScanCtx.pool = tpool_create(args->threads, thread_cleanup);
@@ -136,15 +148,13 @@ void sist2_index(index_args_t *args) {
     LOG_DEBUGF("main.c", "descriptor version %s (%s)", desc.version, desc.type)
 
     if (strcmp(desc.version, Version) != 0 && strcmp(desc.version, INDEX_VERSION_EXTERNAL) != 0) {
-        fprintf(stderr, "Version mismatch! Index is %s but executable is %s/%s\n",
-                desc.version, Version, INDEX_VERSION_EXTERNAL);
-        return;
+        LOG_FATALF("main.c", "Version mismatch! Index is %s but executable is %s/%s", desc.version, Version,
+                   INDEX_VERSION_EXTERNAL)
     }
 
     DIR *dir = opendir(args->index_path);
     if (dir == NULL) {
-        perror("opendir");
-        return;
+        LOG_FATALF("main.c", "Could not open index %s: %s", args->index_path, strerror(errno))
     }
 
     index_func f;
@@ -237,6 +247,8 @@ int main(int argc, const char *argv[]) {
                                                           "shallow: Don't parse archives inside archives. DEFAULT: recurse"),
             OPT_STRING(0, "ocr", &scan_args->tesseract_lang, "Tesseract language (use tesseract --list-langs to see "
                                                              "which are installed on your machine)"),
+            OPT_STRING('e', "exclude", &scan_args->exclude_regex, "Files that match this regex will not be scanned"),
+            OPT_BOOLEAN(0, "fast", &scan_args->fast, "Only index file names & mime type"),
 
             OPT_GROUP("Index options"),
             OPT_STRING(0, "es-url", &common_es_url, "Elasticsearch url with port. DEFAULT=http://localhost:9200"),
@@ -262,7 +274,7 @@ int main(int argc, const char *argv[]) {
 
     if (arg_version) {
         printf(Version);
-        exit(0);
+        goto end;
     }
 
     if (LogCtx.very_verbose != 0) {
@@ -274,22 +286,20 @@ int main(int argc, const char *argv[]) {
 
     if (argc == 0) {
         argparse_usage(&argparse);
-        return 1;
+        goto end;
     } else if (strcmp(argv[0], "scan") == 0) {
 
         int err = scan_args_validate(scan_args, argc, argv);
         if (err != 0) {
-            return err;
+            goto end;
         }
         sist2_scan(scan_args);
 
-    }
-
-    else if (strcmp(argv[0], "index") == 0) {
+    } else if (strcmp(argv[0], "index") == 0) {
 
         int err = index_args_validate(index_args, argc, argv);
         if (err != 0) {
-            return err;
+            goto end;
         }
         sist2_index(index_args);
 
@@ -297,20 +307,19 @@ int main(int argc, const char *argv[]) {
 
         int err = web_args_validate(web_args, argc, argv);
         if (err != 0) {
-            return err;
+            goto end;
         }
         sist2_web(web_args);
 
-    }
-    else {
+    } else {
         fprintf(stderr, "Invalid command: '%s'\n", argv[0]);
         argparse_usage(&argparse);
-        return 1;
+        goto end;
     }
     printf("\n");
 
+    end:
     scan_args_destroy(scan_args);
-
     index_args_destroy(index_args);
     web_args_destroy(web_args);
 

src/parsing/arc.c

@@ -1,8 +1,6 @@
 #include "arc.h"
 #include "src/ctx.h"
 
-#define ARC_BUF_SIZE 8192
-
 int should_parse_filtered_file(const char *filepath, int ext) {
     char tmp[PATH_MAX * 2];
 

src/parsing/arc.h

@@ -2,6 +2,7 @@
 #define SIST2_ARC_H
 
 #include "src/sist.h"
+#define ARC_BUF_SIZE 8192
 
 int should_parse_filtered_file(const char *filepath, int ext);
 

src/parsing/cbr.c

@@ -0,0 +1,52 @@
+#include "cbr.h"
+#include "src/ctx.h"
+
+unsigned int cbr_mime;
+unsigned int cbz_mime;
+
+void cbr_init() {
+    cbr_mime = mime_get_mime_by_string(ScanCtx.mime_table, "application/x-cbr");
+    cbz_mime = mime_get_mime_by_string(ScanCtx.mime_table, "application/x-cbz");
+}
+
+int is_cbr(unsigned int mime) {
+    return mime == cbr_mime;
+}
+
+void parse_cbr(void *buf, size_t buf_len, document_t *doc) {
+    char *out_buf = malloc(buf_len * 2);
+    size_t out_buf_used = 0;
+
+    struct archive *rar_in = archive_read_new();
+    archive_read_support_filter_none(rar_in);
+    archive_read_support_format_rar(rar_in);
+
+    archive_read_open_memory(rar_in, buf, buf_len);
+
+    struct archive *zip_out = archive_write_new();
+    archive_write_set_format_zip(zip_out);
+    archive_write_open_memory(zip_out, out_buf, buf_len * 2, &out_buf_used);
+
+    struct archive_entry *entry;
+    while (archive_read_next_header(rar_in, &entry) == ARCHIVE_OK) {
+        archive_write_header(zip_out, entry);
+
+        char arc_buf[ARC_BUF_SIZE];
+        int len = archive_read_data(rar_in, arc_buf, ARC_BUF_SIZE);
+        while (len > 0) {
+            archive_write_data(zip_out, arc_buf, len);
+            len = archive_read_data(rar_in, arc_buf, ARC_BUF_SIZE);
+        }
+    }
+
+    archive_write_close(zip_out);
+    archive_write_free(zip_out);
+
+    archive_read_close(rar_in);
+    archive_read_free(rar_in);
+
+    doc->mime = cbz_mime;
+    parse_pdf(out_buf, out_buf_used, doc);
+    doc->mime = cbr_mime;
+    free(out_buf);
+}

src/parsing/cbr.h

@@ -0,0 +1,12 @@
+#ifndef SIST2_CBR_H
+#define SIST2_CBR_H
+
+#include "src/sist.h"
+
+void cbr_init();
+
+int is_cbr(unsigned int mime);
+
+void parse_cbr(void *buf, size_t buf_len, document_t *doc);
+
+#endif

src/parsing/doc.c

@@ -1,49 +1,31 @@
 #include "doc.h"
 #include "src/ctx.h"
 
-void dump_text(mceTextReader_t *reader, dyn_buffer_t *buf) {
 
-    mce_skip_attributes(reader);
-
-    mce_start_children(reader) {
-        mce_start_element(reader, NULL, _X("t")) {
-            mce_skip_attributes(reader);
-            mce_start_children(reader) {
-                mce_start_text(reader) {
-                    char *str = (char *) xmlTextReaderConstValue(reader->reader);
-                    dyn_buffer_append_string(buf, str);
-                    dyn_buffer_write_char(buf, ' ');
-                } mce_end_text(reader);
-            } mce_end_children(reader);
-        } mce_end_element(reader);
-
-        mce_start_element(reader, NULL, NULL) {
-            dump_text(reader, buf);
-        } mce_end_element(reader);
-
-    } mce_end_children(reader)
-}
+#define STR_STARTS_WITH(x, y) (strncmp(y, x, sizeof(y) - 1) == 0)
 
 __always_inline
-int should_read_part(opcPart part) {
+static int should_read_part(const char *part) {
 
-    char *part_name = (char *) part;
+    LOG_DEBUGF("doc.c", "Got part : %s", part)
 
     if (part == NULL) {
         return FALSE;
     }
 
     if (    // Word
-            strcmp(part_name, "word/document.xml") == 0
-            || strncmp(part_name, "word/footer", sizeof("word/footer") - 1) == 0
-            || strncmp(part_name, "word/header", sizeof("word/header") - 1) == 0
+            STR_STARTS_WITH(part, "word/document.xml")
+            || STR_STARTS_WITH(part, "word/footnotes.xml")
+            || STR_STARTS_WITH(part, "word/endnotes.xml")
+            || STR_STARTS_WITH(part, "word/footer")
+            || STR_STARTS_WITH(part, "word/header")
             // PowerPoint
-            || strncmp(part_name, "ppt/slides/slide", sizeof("ppt/slides/slide") - 1) == 0
-            || strncmp(part_name, "ppt/notesSlides/notesSlide", sizeof("ppt/notesSlides/notesSlide") - 1) == 0
+            || STR_STARTS_WITH(part, "ppt/slides/slide")
+            || STR_STARTS_WITH(part, "ppt/notesSlides/slide")
             // Excel
-            || strncmp(part_name, "xl/worksheets/sheet", sizeof("xl/worksheets/sheet") - 1) == 0
-            || strcmp(part_name, "xl/sharedStrings.xml") == 0
-            || strcmp(part_name, "xl/workbook.xml") == 0
+            || STR_STARTS_WITH(part, "xl/worksheets/sheet")
+            || STR_STARTS_WITH(part, "xl/sharedStrings.xml")
+            || STR_STARTS_WITH(part, "xl/workbook.xml")
             ) {
         return TRUE;
     }
@@ -51,31 +33,64 @@ int should_read_part(opcPart part) {
     return FALSE;
 }
 
+int extract_text(xmlDoc *xml, xmlNode *node, text_buffer_t *buf) {
+    //TODO: Check which nodes are likely to have a 't' child, and ignore nodes that aren't
+    xmlErrorPtr err = xmlGetLastError();
+    if (err != NULL) {
+        if (err->level == XML_ERR_FATAL) {
+            LOG_ERRORF("doc.c", "Got fatal XML error while parsing document: %s", err->message)
+            return -1;
+        } else {
+            LOG_ERRORF("doc.c", "Got recoverable XML error while parsing document: %s", err->message)
+        }
+    }
+
+    for (xmlNode *child = node; child; child = child->next) {
+        if (*child->name == 't' && *(child->name + 1) == '\0') {
+            xmlChar *text = xmlNodeListGetString(xml, child->xmlChildrenNode, 1);
+
+            if (text) {
+                text_buffer_append_string0(buf, (char *) text);
+                text_buffer_append_char(buf, ' ');
+                xmlFree(text);
+            }
+        }
+
+        extract_text(xml, child->children, buf);
+    }
+}
+
+int xml_io_read(void *context, char *buffer, int len) {
+    struct archive *a = context;
+    return archive_read_data(a, buffer, len);
+}
+
+int xml_io_close(UNUSED(void *context)) {
+    //noop
+    return 0;
+}
+
 __always_inline
-void read_part(opcContainer *c, dyn_buffer_t *buf, opcPart part, document_t *doc) {
+static int read_part(struct archive *a, text_buffer_t *buf, document_t *doc) {
 
-    mceTextReader_t reader;
-    int options;
-    if (LogCtx.very_verbose) {
-        options = XML_PARSE_NONET;
-    } else {
-        options = XML_PARSE_NOWARNING | XML_PARSE_NOERROR | XML_PARSE_NONET;
+    xmlDoc *xml = xmlReadIO(xml_io_read, xml_io_close, a, "/", NULL, XML_PARSE_RECOVER | XML_PARSE_NOWARNING | XML_PARSE_NOERROR | XML_PARSE_NONET);
+
+    if (xml == NULL) {
+        LOG_ERROR(doc->filepath, "Could not parse XML")
+        return -1;
     }
 
-    int ret = opcXmlReaderOpen(c, &reader, part, NULL, "UTF-8", options);
-
-    if (ret != OPC_ERROR_NONE) {
-        LOG_ERRORF(doc->filepath, "(doc.c) opcXmlReaderOpen() returned error code %d", ret);
-        return;
+    xmlNode *root = xmlDocGetRootElement(xml);
+    if (root == NULL) {
+        LOG_ERROR(doc->filepath, "Empty document")
+        xmlFreeDoc(xml);
+        return -1;
     }
 
-    mce_start_document(&reader) {
-        mce_start_element(&reader, NULL, NULL) {
-                dump_text(&reader, buf);
-        } mce_end_element(&reader);
-    } mce_end_document(&reader);
+    extract_text(xml, root, buf);
+    xmlFreeDoc(xml);
 
-    mceTextReaderCleanup(&reader);
+    return 0;
 }
 
 void parse_doc(void *mem, size_t mem_len, document_t *doc) {
@@ -84,31 +99,42 @@ void parse_doc(void *mem, size_t mem_len, document_t *doc) {
         return;
     }
 
-    opcContainer *c = opcContainerOpenMem(mem, mem_len, OPC_OPEN_READ_ONLY, NULL);
-    if (c == NULL) {
-        LOG_ERROR(doc->filepath, "(doc.c) Couldn't open document with opcContainerOpenMem()");
+    struct archive *a = archive_read_new();
+    archive_read_support_format_zip(a);
+
+    int ret = archive_read_open_memory(a, mem, mem_len);
+    if (ret != ARCHIVE_OK) {
+        LOG_ERRORF(doc->filepath, "Could not read archive: %s", archive_error_string(a))
+        archive_read_free(a);
         return;
     }
 
-    dyn_buffer_t buf = dyn_buffer_create();
+    text_buffer_t buf = text_buffer_create(ScanCtx.content_size);
 
-    opcPart part = opcPartGetFirst(c);
-    do {
-        if (should_read_part(part)) {
-            read_part(c, &buf, part, doc);
+    struct archive_entry *entry;
+    while (archive_read_next_header(a, &entry) == ARCHIVE_OK) {
+        if (S_ISREG(archive_entry_stat(entry)->st_mode)) {
+            const char *path = archive_entry_pathname(entry);
+
+            if (should_read_part(path)) {
+                ret = read_part(a, &buf, doc);
+                if (ret != 0) {
+                    break;
+                }
+            }
         }
-    } while ((part = opcPartGetNext(c, part)));
+    }
 
-    opcContainerClose(c, OPC_CLOSE_NOW);
+    if (buf.dyn_buffer.cur > 0) {
+        text_buffer_terminate_string(&buf);
 
-    if (buf.cur > 0) {
-        dyn_buffer_write_char(&buf, '\0');
-
-        meta_line_t *meta = malloc(sizeof(meta_line_t) + buf.cur);
+        meta_line_t *meta = malloc(sizeof(meta_line_t) + buf.dyn_buffer.cur);
         meta->key = MetaContent;
-        strcpy(meta->strval, buf.buf);
+        strcpy(meta->strval, buf.dyn_buffer.buf);
         APPEND_META(doc, meta)
     }
 
-    dyn_buffer_destroy(&buf);
+    archive_read_close(a);
+    archive_read_free(a);
+    text_buffer_destroy(&buf);
 }

src/parsing/font.c

@@ -140,6 +140,7 @@ void parse_font(const char *buf, size_t buf_len, document_t *doc) {
     if (ft_lib == NULL) {
         FT_Init_FreeType(&ft_lib);
     }
+
     if (buf == NULL) {
         return;
     }
@@ -169,6 +170,7 @@ void parse_font(const char *buf, size_t buf_len, document_t *doc) {
     APPEND_META(doc, meta_name)
 
     if (ScanCtx.tn_size <= 0) {
+        FT_Done_Face(face);
         return;
     }
 
@@ -178,6 +180,7 @@ 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))
+        FT_Done_Face(face);
         return;
     }
 
@@ -224,3 +227,7 @@ void parse_font(const char *buf, size_t buf_len, document_t *doc) {
 
     FT_Done_Face(face);
 }
+
+void cleanup_font() {
+    FT_Done_FreeType(ft_lib);
+}

src/parsing/font.h

@@ -5,5 +5,6 @@
 
 
 void parse_font(const char * buf, size_t buf_len, document_t *doc);
+void cleanup_font();
 
 #endif

src/parsing/media.c

@@ -5,7 +5,7 @@
 #define AVIO_BUF_SIZE 8192
 
 __always_inline
-AVCodecContext *alloc_jpeg_encoder(int dstW, int dstH, float qscale) {
+static AVCodecContext *alloc_jpeg_encoder(int dstW, int dstH, float qscale) {
 
     AVCodec *jpeg_codec = avcodec_find_encoder(AV_CODEC_ID_MJPEG);
     AVCodecContext *jpeg = avcodec_alloc_context3(jpeg_codec);
@@ -78,7 +78,7 @@ AVFrame *scale_frame(const AVCodecContext *decoder, const AVFrame *frame, int si
 }
 
 __always_inline
-AVFrame *read_frame(AVFormatContext *pFormatCtx, AVCodecContext *decoder, int stream_idx, document_t *doc) {
+static AVFrame *read_frame(AVFormatContext *pFormatCtx, AVCodecContext *decoder, int stream_idx, document_t *doc) {
     AVFrame *frame = av_frame_alloc();
 
     AVPacket avPacket;
@@ -113,10 +113,13 @@ 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) {
-            LOG_WARNINGF(doc->filepath,
+            LOG_ERRORF(doc->filepath,
                          "(media.c) avcodec_send_packet() returned error code [%d] %s",
                          decode_ret, av_err2str(decode_ret)
             )
+            av_frame_free(&frame);
+            av_packet_unref(&avPacket);
+            return NULL;
         }
         av_packet_unref(&avPacket);
         receive_ret = avcodec_receive_frame(decoder, frame);
@@ -135,11 +138,11 @@ AVFrame *read_frame(AVFormatContext *pFormatCtx, AVCodecContext *decoder, int st
     text_buffer_destroy(&tex);
 
 __always_inline
-void append_audio_meta(AVFormatContext *pFormatCtx, document_t *doc) {
+static void append_audio_meta(AVFormatContext *pFormatCtx, document_t *doc) {
 
     AVDictionaryEntry *tag = NULL;
     while ((tag = av_dict_get(pFormatCtx->metadata, "", tag, AV_DICT_IGNORE_SUFFIX))) {
-        char key[32];
+        char key[256];
         strncpy(key, tag->key, sizeof(key));
 
         char *ptr = key;
@@ -160,7 +163,7 @@ void append_audio_meta(AVFormatContext *pFormatCtx, document_t *doc) {
 }
 
 __always_inline
-void
+static void
 append_video_meta(AVFormatContext *pFormatCtx, AVFrame *frame, document_t *doc, int include_audio_tags, int is_video) {
 
     if (is_video) {
@@ -209,6 +212,8 @@ append_video_meta(AVFormatContext *pFormatCtx, AVFrame *frame, document_t *doc,
                 APPEND_TAG_META(doc, tag, MetaExifIsoSpeedRatings)
             } else if (strcmp(tag->key, "ExposureTime") == 0) {
                 APPEND_TAG_META(doc, tag, MetaExifExposureTime)
+            } else if (strcmp(tag->key, "DateTime") == 0) {
+                APPEND_TAG_META(doc, tag, MetaExifDateTime)
             }
         }
     }

src/parsing/mime.h

@@ -8,7 +8,7 @@
 #define MIME_EMPTY 1
 
 #define DONT_PARSE 0x80000000
-#define SHOULD_PARSE(mime_id) (mime_id & DONT_PARSE) != DONT_PARSE && mime_id != 0
+#define SHOULD_PARSE(mime_id) (ScanCtx.fast == 0 && (mime_id & DONT_PARSE) != DONT_PARSE && mime_id != 0)
 
 #define PDF_MASK 0x40000000
 #define IS_PDF(mime_id) (mime_id & PDF_MASK) == PDF_MASK

src/parsing/parse.c

@@ -36,8 +36,14 @@ void *read_all(parse_job_t *job, const char *buf, int bytes_read) {
         memcpy(full_buf, buf, bytes_read);
 
         int ret = job->vfile.read(&job->vfile, full_buf + bytes_read, job->info.st_size - bytes_read);
-        if (ret == -1) {
-            LOG_ERRORF(job->filepath, "read(): [%d] %s", errno, strerror(errno))
+        if (ret < 0) {
+            free(full_buf);
+
+            if (job->vfile.is_fs_file) {
+                LOG_ERRORF(job->filepath, "read(): [%d] %s", errno, strerror(errno))
+            } else {
+                LOG_ERRORF(job->filepath, "(virtual) read(): [%d] %s", ret, archive_error_string(job->vfile.arc))
+            }
             return NULL;
         }
     }
@@ -58,6 +64,7 @@ void parse(void *arg) {
 
     if (Magic == NULL) {
         Magic = magic_open(MAGIC_MIME_TYPE);
+        magic_load(Magic, NULL);
     }
 
     doc.filepath = job->filepath;
@@ -87,11 +94,17 @@ void parse(void *arg) {
 
     int bytes_read = 0;
 
-    if (doc.mime == 0) {
+    if (doc.mime == 0 && !ScanCtx.fast) {
         // 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))
+        if (bytes_read < 0) {
+
+            if (job->vfile.is_fs_file) {
+                LOG_ERRORF(job->filepath, "read(): [%d] %s", errno, strerror(errno))
+            } else {
+                LOG_ERRORF(job->filepath, "(virtual) read(): [%d] %s", bytes_read, archive_error_string(job->vfile.arc))
+            }
+
             CLOSE_FILE(job->vfile)
             return;
         }
@@ -99,10 +112,16 @@ void parse(void *arg) {
         const char *magic_mime_str = magic_buffer(Magic, buf, bytes_read);
         if (magic_mime_str != NULL) {
             doc.mime = mime_get_mime_by_string(ScanCtx.mime_table, magic_mime_str);
+
+            LOG_DEBUGF(job->filepath, "libmagic: %s", magic_mime_str);
+
             if (doc.mime == 0) {
                 LOG_WARNINGF(job->filepath, "Couldn't find mime %s", magic_mime_str);
             }
         }
+
+        magic_close(Magic);
+        Magic = NULL;
     }
 
     int mmime = MAJOR_MIME(doc.mime);
@@ -149,6 +168,13 @@ void parse(void *arg) {
         if (doc_buf != buf && doc_buf != NULL) {
             free(doc_buf);
         }
+    } else if (is_cbr(doc.mime)) {
+        void *cbr_buf = read_all(job, (char *) buf, bytes_read);
+        parse_cbr(cbr_buf, doc.size, &doc);
+
+        if (cbr_buf != buf && cbr_buf != NULL) {
+            free(cbr_buf);
+        }
     }
 
     //Parent meta
@@ -166,3 +192,9 @@ void parse(void *arg) {
 
     CLOSE_FILE(job->vfile)
 }
+
+void cleanup_parse() {
+    if (Magic != NULL) {
+        magic_close(Magic);
+    }
+}

src/parsing/parse.h

@@ -10,4 +10,6 @@ void fs_close(struct vfile *f);
 
 void parse(void *arg);
 
+void cleanup_parse();
+
 #endif

src/parsing/pdf.c

@@ -1,16 +1,18 @@
 #include "pdf.h"
 #include "src/ctx.h"
 
-#define MIN_OCR_SIZE 128
+#define MIN_OCR_SIZE 350
+#define MIN_OCR_LEN 10
 __thread text_buffer_t thread_buffer;
 
 
-fz_page *render_cover(fz_context *ctx, document_t *doc, fz_document *fzdoc) {
+int render_cover(fz_context *ctx, document_t *doc, fz_document *fzdoc) {
 
     int err = 0;
     fz_page *cover = NULL;
 
     fz_var(cover);
+    fz_var(err);
     fz_try(ctx)
         cover = fz_load_page(ctx, fzdoc, 0);
     fz_catch(ctx)
@@ -19,7 +21,7 @@ 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;
+        return FALSE;
     }
 
     fz_rect bounds = fz_bound_page(ctx, cover);
@@ -60,7 +62,7 @@ fz_page *render_cover(fz_context *ctx, document_t *doc, fz_document *fzdoc) {
         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;
+        return FALSE;
     }
 
     fz_buffer *fzbuf = NULL;
@@ -80,15 +82,15 @@ fz_page *render_cover(fz_context *ctx, document_t *doc, fz_document *fzdoc) {
 
     fz_drop_buffer(ctx, fzbuf);
     fz_drop_pixmap(ctx, pixmap);
+    fz_drop_page(ctx, cover);
 
     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;
+        return FALSE;
     }
 
-    return cover;
+    return TRUE;
 }
 
 void fz_err_callback(void *user, UNUSED(const char *message)) {
@@ -99,7 +101,7 @@ void fz_err_callback(void *user, UNUSED(const char *message)) {
 }
 
 __always_inline
-void init_ctx(fz_context *ctx, document_t *doc) {
+static void init_ctx(fz_context *ctx, document_t *doc) {
     fz_disable_icc(ctx);
     fz_register_document_handlers(ctx);
 
@@ -109,7 +111,8 @@ void init_ctx(fz_context *ctx, document_t *doc) {
     ctx->error.print = fz_err_callback;
 }
 
-int read_stext_block(fz_stext_block *block, text_buffer_t *tex) {
+__always_inline
+static int read_stext_block(fz_stext_block *block, text_buffer_t *tex) {
     if (block->type != FZ_STEXT_BLOCK_TEXT) {
         return 0;
     }
@@ -128,6 +131,7 @@ int read_stext_block(fz_stext_block *block, text_buffer_t *tex) {
     return 0;
 }
 
+#define IS_VALID_BPP(d) (d==1 || d==2 || d==4 || d==8 || d==16 || d==24 || d==32)
 
 void fill_image(fz_context *ctx, UNUSED(fz_device *dev),
                 fz_image *img, UNUSED(fz_matrix ctm), UNUSED(float alpha),
@@ -135,7 +139,7 @@ void fill_image(fz_context *ctx, UNUSED(fz_device *dev),
 
     int l2factor = 0;
 
-    if (img->w > MIN_OCR_SIZE && img->h > MIN_OCR_SIZE) {
+    if (img->w > MIN_OCR_SIZE && img->h > MIN_OCR_SIZE && IS_VALID_BPP(img->n)) {
 
         fz_pixmap *pix = img->get_pixmap(ctx, img, NULL, img->w, img->h, &l2factor);
 
@@ -148,12 +152,14 @@ void fill_image(fz_context *ctx, UNUSED(fz_device *dev),
 
             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
-            )
+            if (len >= MIN_OCR_LEN) {
+                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);
@@ -162,7 +168,7 @@ void fill_image(fz_context *ctx, UNUSED(fz_device *dev),
     }
 }
 
-void parse_pdf(void *buf, size_t buf_len, document_t *doc) {
+void parse_pdf(const void *buf, size_t buf_len, document_t *doc) {
 
     if (buf == NULL) {
         return;
@@ -193,7 +199,7 @@ void parse_pdf(void *buf, size_t buf_len, document_t *doc) {
     fz_catch(ctx)
         err = ctx->error.errcode;
 
-    if (err) {
+    if (err != 0) {
         fz_drop_stream(ctx, stream);
         fz_drop_document(ctx, fzdoc);
         fz_drop_context(ctx);
@@ -228,18 +234,11 @@ void parse_pdf(void *buf, size_t buf_len, document_t *doc) {
         return;
     }
 
-    fz_page *cover = NULL;
     if (ScanCtx.tn_size > 0) {
-        cover = render_cover(ctx, doc, fzdoc);
-    } else {
-        fz_var(cover);
-        fz_try(ctx)
-            cover = fz_load_page(ctx, fzdoc, 0);
-        fz_catch(ctx)
-            cover = NULL;
+        err = render_cover(ctx, doc, fzdoc);
     }
 
-    if (cover == NULL) {
+    if (err == TRUE) {
         fz_drop_stream(ctx, stream);
         fz_drop_document(ctx, fzdoc);
         fz_drop_context(ctx);
@@ -252,23 +251,19 @@ void parse_pdf(void *buf, size_t buf_len, document_t *doc) {
 
         for (int current_page = 0; current_page < page_count; current_page++) {
             fz_page *page = NULL;
-            if (current_page == 0) {
-                page = cover;
-            } else {
-                fz_var(err);
-                fz_try(ctx)
-                            page = fz_load_page(ctx, fzdoc, current_page);
-                fz_catch(ctx)
-                    err = ctx->error.errcode;
-                if (err != 0) {
-                    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);
-                    fz_drop_context(ctx);
-                    return;
-                }
+            fz_var(err);
+            fz_try(ctx)
+                page = fz_load_page(ctx, fzdoc, current_page);
+            fz_catch(ctx)
+                err = ctx->error.errcode;
+            if (err != 0) {
+                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);
+                fz_drop_context(ctx);
+                return;
             }
 
             fz_stext_page *stext = fz_new_stext_page(ctx, fz_bound_page(ctx, page));
@@ -285,12 +280,12 @@ void parse_pdf(void *buf, size_t buf_len, document_t *doc) {
 
             fz_var(err);
             fz_try(ctx)
-                        fz_run_page(ctx, page, dev, fz_identity, NULL);
+                fz_run_page(ctx, page, dev, fz_identity, NULL);
             fz_always(ctx)
-                {
-                    fz_close_device(ctx, dev);
-                    fz_drop_device(ctx, dev);
-                }
+            {
+                fz_close_device(ctx, dev);
+                fz_drop_device(ctx, dev);
+            }
             fz_catch(ctx)
                 err = ctx->error.errcode;
 

src/parsing/pdf.h

@@ -4,6 +4,6 @@
 #include "src/sist.h"
 
 
-void parse_pdf(void *buf, size_t buf_len, document_t *doc);
+void parse_pdf(const void *buf, size_t buf_len, document_t *doc);
 
 #endif

src/sist.h

@@ -31,10 +31,11 @@
 #include "freetype/freetype.h"
 #include <archive.h>
 #include <archive_entry.h>
-#include <opc/opc.h>
 #include <libxml/xmlstring.h>
+#include <libxml/parser.h>
 #define BOOL int
 #include <tesseract/capi.h>
+#include <pcre.h>
 
 #include <onion/onion.h>
 #include <onion/handler.h>
@@ -47,6 +48,7 @@
 
 #include "types.h"
 #include "tpool.h"
+#include "utf8.h/utf8.h"
 #include "util.h"
 #include "io/store.h"
 #include "io/serialize.h"
@@ -59,9 +61,9 @@
 #include "parsing/font.h"
 #include "parsing/arc.h"
 #include "parsing/doc.h"
+#include "parsing/cbr.h"
 #include "cli.h"
 #include "log.h"
-#include "utf8.h/utf8.h"
 
 #include "src/index/elastic.h"
 #include "index/web.h"

src/types.h

@@ -39,6 +39,7 @@ enum metakey {
     MetaExifUserComment = 20 | META_STR_MASK,
     MetaExifModel = 21 | META_STR_MASK,
     MetaExifIsoSpeedRatings = 22 | META_STR_MASK,
+    MetaExifDateTime = 23 | META_STR_MASK,
     //Note to self: this will break after 31 entries
 };
 
@@ -48,7 +49,7 @@ enum metakey {
 
 typedef struct index_descriptor {
     char uuid[UUID_STR_LEN];
-    char version[6];
+    char version[64];
     long timestamp;
     char root[PATH_MAX];
     char rewrite_url[8196];
@@ -94,7 +95,6 @@ typedef int (*read_func_t)(struct vfile *, void *buf, size_t size);
 typedef void (*close_func_t)(struct vfile *);
 
 typedef struct vfile {
-
     union {
         int fd;
         struct archive *arc;

src/util.c

@@ -1,235 +1,6 @@
 #include "util.h"
 #include "src/ctx.h"
 
-dyn_buffer_t dyn_buffer_create() {
-    dyn_buffer_t buf;
-
-    buf.size = INITIAL_BUF_SIZE;
-    buf.cur = 0;
-    buf.buf = malloc(INITIAL_BUF_SIZE);
-
-    return buf;
-}
-
-void grow_buffer(dyn_buffer_t *buf, size_t size) {
-    if (buf->cur + size > buf->size) {
-        do {
-            buf->size *= 2;
-        } while (buf->cur + size > buf->size);
-
-        buf->buf = realloc(buf->buf, buf->size);
-    }
-}
-
-void grow_buffer_small(dyn_buffer_t *buf) {
-    if (buf->cur + sizeof(long) > buf->size) {
-        buf->size *= 2;
-        buf->buf = realloc(buf->buf, buf->size);
-    }
-}
-
-void dyn_buffer_write(dyn_buffer_t *buf, void *data, size_t size) {
-    grow_buffer(buf, size);
-
-    memcpy(buf->buf + buf->cur, data, size);
-    buf->cur += size;
-}
-
-void dyn_buffer_write_char(dyn_buffer_t *buf, char c) {
-    grow_buffer_small(buf);
-
-    *(buf->buf + buf->cur) = c;
-    buf->cur += sizeof(c);
-}
-
-void dyn_buffer_write_str(dyn_buffer_t *buf, char *str) {
-    dyn_buffer_write(buf, str, strlen(str));
-    dyn_buffer_write_char(buf, '\0');
-}
-
-void dyn_buffer_append_string(dyn_buffer_t *buf, char *str) {
-    dyn_buffer_write(buf, str, strlen(str));
-}
-
-void dyn_buffer_write_int(dyn_buffer_t *buf, int d) {
-    grow_buffer_small(buf);
-
-    *(int *) (buf->buf + buf->cur) = d;
-    buf->cur += sizeof(int);
-}
-
-void dyn_buffer_write_short(dyn_buffer_t *buf, short s) {
-    grow_buffer_small(buf);
-
-    *(short *) (buf->buf + buf->cur) = s;
-    buf->cur += sizeof(short);
-}
-
-void dyn_buffer_write_long(dyn_buffer_t *buf, unsigned long l) {
-    grow_buffer_small(buf);
-
-    *(unsigned long *) (buf->buf + buf->cur) = l;
-    buf->cur += sizeof(unsigned long);
-}
-
-void dyn_buffer_destroy(dyn_buffer_t *buf) {
-    free(buf->buf);
-}
-
-void text_buffer_destroy(text_buffer_t *buf) {
-    dyn_buffer_destroy(&buf->dyn_buffer);
-}
-
-text_buffer_t text_buffer_create(int max_size) {
-    text_buffer_t text_buf;
-
-    text_buf.dyn_buffer = dyn_buffer_create();
-    text_buf.max_size = max_size;
-    text_buf.last_char_was_whitespace = FALSE;
-
-    return text_buf;
-}
-
-void text_buffer_terminate_string(text_buffer_t *buf) {
-    if (*(buf->dyn_buffer.buf + buf->dyn_buffer.cur - 1) == ' ') {
-        *(buf->dyn_buffer.buf + buf->dyn_buffer.cur - 1) = '\0';
-    } else {
-        dyn_buffer_write_char(&buf->dyn_buffer, '\0');
-    }
-}
-
-__always_inline
-int utf8_validchr(const char *s) {
-    if (0x00 == (0x80 & *s)) {
-        return TRUE;
-    } else if (0xf0 == (0xf8 & *s)) {
-        if ((0x80 != (0xc0 & s[1])) || (0x80 != (0xc0 & s[2])) ||
-            (0x80 != (0xc0 & s[3]))) {
-            return FALSE;
-        }
-
-        if (0x80 == (0xc0 & s[4])) {
-            return FALSE;
-        }
-
-        if ((0 == (0x07 & s[0])) && (0 == (0x30 & s[1]))) {
-            return FALSE;
-        }
-    } else if (0xe0 == (0xf0 & *s)) {
-        if ((0x80 != (0xc0 & s[1])) || (0x80 != (0xc0 & s[2]))) {
-            return FALSE;
-        }
-
-        if (0x80 == (0xc0 & s[3])) {
-            return FALSE;
-        }
-
-        if ((0 == (0x0f & s[0])) && (0 == (0x20 & s[1]))) {
-            return FALSE;
-        }
-    } else if (0xc0 == (0xe0 & *s)) {
-        if (0x80 != (0xc0 & s[1])) {
-            return FALSE;
-        }
-
-        if (0x80 == (0xc0 & s[2])) {
-            return FALSE;
-        }
-
-        if (0 == (0x1e & s[0])) {
-            return FALSE;
-        }
-    } else {
-        return FALSE;
-    }
-
-    return TRUE;
-}
-
-int text_buffer_append_string(text_buffer_t *buf, char *str, size_t len) {
-
-    utf8_int32_t c;
-    if (str == NULL || len < 1 ||
-        (0xf0 == (0xf8 & str[0]) && len < 4) ||
-        (0xe0 == (0xf0 & str[0]) && len < 3) ||
-        (0xc0 == (0xe0 & str[0]) && len == 1) ||
-        *(str) == 0) {
-        return 0;
-    }
-
-    for (void *v = utf8codepoint(str, &c); c != '\0' && ((char *) v - str + 4) < len; v = utf8codepoint(v, &c)) {
-        if (utf8_validchr(v)) {
-            text_buffer_append_char(buf, c);
-        }
-    }
-    return 0;
-}
-
-int text_buffer_append_string0(text_buffer_t *buf, char *str) {
-    utf8_int32_t c;
-    for (void *v = utf8codepoint(str, &c); c != '\0'; v = utf8codepoint(v, &c)) {
-        if (utf8_validchr(v)) {
-            text_buffer_append_char(buf, c);
-        }
-    }
-}
-
-int text_buffer_append_char(text_buffer_t *buf, int c) {
-
-    if (SHOULD_IGNORE_CHAR(c) || c == ' ') {
-        if (!buf->last_char_was_whitespace && buf->dyn_buffer.cur != 0) {
-            dyn_buffer_write_char(&buf->dyn_buffer, ' ');
-            buf->last_char_was_whitespace = TRUE;
-
-            if (buf->max_size > 0 && buf->dyn_buffer.cur >= buf->max_size) {
-                return TEXT_BUF_FULL;
-            }
-        }
-    } else {
-        buf->last_char_was_whitespace = FALSE;
-        grow_buffer_small(&buf->dyn_buffer);
-
-        if (0 == ((utf8_int32_t) 0xffffff80 & c)) {
-            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = (char) c;
-        } else if (0 == ((utf8_int32_t) 0xfffff800 & c)) {
-            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = 0xc0 | (char) (c >> 6);
-            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = 0x80 | (char) (c & 0x3f);
-        } else if (0 == ((utf8_int32_t) 0xffff0000 & c)) {
-            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = 0xe0 | (char) (c >> 12);
-            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = 0x80 | (char) ((c >> 6) & 0x3f);
-            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = 0x80 | (char) (c & 0x3f);
-        } else {
-            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = 0xf0 | (char) (c >> 18);
-            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = 0x80 | (char) ((c >> 12) & 0x3f);
-            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = 0x80 | (char) ((c >> 6) & 0x3f);
-            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = 0x80 | (char) (c & 0x3f);
-        }
-
-        if (buf->max_size > 0 && buf->dyn_buffer.cur >= buf->max_size) {
-            return TEXT_BUF_FULL;
-        }
-    }
-
-    return 0;
-}
-
-void incremental_put(GHashTable *table, unsigned long inode_no, int mtime) {
-    g_hash_table_insert(table, (gpointer) inode_no, GINT_TO_POINTER(mtime));
-}
-
-int incremental_get(GHashTable *table, unsigned long inode_no) {
-    if (table != NULL) {
-        return GPOINTER_TO_INT(g_hash_table_lookup(table, (gpointer) inode_no));
-    } else {
-        return 0;
-    }
-}
-
-int incremental_mark_file_for_copy(GHashTable *table, unsigned long inode_no) {
-    g_hash_table_insert(table, GINT_TO_POINTER(inode_no), GINT_TO_POINTER(1));
-}
-
-
 #define PBSTR "========================================"
 #define PBWIDTH 40
 
@@ -259,8 +30,10 @@ char *abspath(const char *path) {
     if (abs == NULL) {
         return NULL;
     }
-    abs = realloc(abs, strlen(abs) + 2);
-    strcat(abs, "/");
+    if (strlen(abs) > 1) {
+        abs = realloc(abs, strlen(abs) + 2);
+        strcat(abs, "/");
+    }
 
     wordfree(&w);
     return abs;

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 >= '0' && c <= '9') || (c >= 'A' && c <= 'z') || (c > 127))
+#define SHOULD_KEEP_CHAR(c) ((c >= '\'' && c <= ';') || (c >= 'A' && c <= 'z') || (c > 127))
 
 
 typedef struct dyn_buffer {
@@ -32,47 +32,253 @@ dyn_buffer_t url_escape(char *str);
 
 void progress_bar_print(double percentage, size_t tn_size, size_t index_size);
 
-
 GHashTable *incremental_get_table();
 
-dyn_buffer_t dyn_buffer_create();
+__always_inline
+static int utf8_validchr2(const char *s) {
+    if (0x00 == (0x80 & *s)) {
+        return TRUE;
+    } else if (0xf0 == (0xf8 & *s)) {
+        if ((0x80 != (0xc0 & s[1])) || (0x80 != (0xc0 & s[2])) ||
+            (0x80 != (0xc0 & s[3]))) {
+            return FALSE;
+        }
 
-void grow_buffer(dyn_buffer_t *buf, size_t size);
+        if (0x80 == (0xc0 & s[4])) {
+            return FALSE;
+        }
 
-void grow_buffer_small(dyn_buffer_t *buf);
+        if ((0 == (0x07 & s[0])) && (0 == (0x30 & s[1]))) {
+            return FALSE;
+        }
+    } else if (0xe0 == (0xf0 & *s)) {
+        if ((0x80 != (0xc0 & s[1])) || (0x80 != (0xc0 & s[2]))) {
+            return FALSE;
+        }
 
-void dyn_buffer_write(dyn_buffer_t *buf, void *data, size_t size);
+        if (0x80 == (0xc0 & s[3])) {
+            return FALSE;
+        }
 
-void dyn_buffer_write_char(dyn_buffer_t *buf, char c);
+        if ((0 == (0x0f & s[0])) && (0 == (0x20 & s[1]))) {
+            return FALSE;
+        }
+    } else if (0xc0 == (0xe0 & *s)) {
+        if (0x80 != (0xc0 & s[1])) {
+            return FALSE;
+        }
 
-void dyn_buffer_write_str(dyn_buffer_t *buf, char *str);
+        if (0x80 == (0xc0 & s[2])) {
+            return FALSE;
+        }
 
-void dyn_buffer_append_string(dyn_buffer_t *buf, char *str);
+        if (0 == (0x1e & s[0])) {
+            return FALSE;
+        }
+    } else {
+        return FALSE;
+    }
 
-void dyn_buffer_write_int(dyn_buffer_t *buf, int d);
+    return TRUE;
+}
 
-void dyn_buffer_write_short(dyn_buffer_t *buf, short s);
 
-void dyn_buffer_write_long(dyn_buffer_t *buf, unsigned long l);
+__always_inline
+static dyn_buffer_t dyn_buffer_create() {
+    dyn_buffer_t buf;
 
-void dyn_buffer_destroy(dyn_buffer_t *buf);
+    buf.size = INITIAL_BUF_SIZE;
+    buf.cur = 0;
+    buf.buf = malloc(INITIAL_BUF_SIZE);
 
-void text_buffer_destroy(text_buffer_t *buf);
+    return buf;
+}
 
-text_buffer_t text_buffer_create(int max_size);
+__always_inline
+static void grow_buffer(dyn_buffer_t *buf, size_t size) {
+    if (buf->cur + size > buf->size) {
+        do {
+            buf->size *= 2;
+        } while (buf->cur + size > buf->size);
 
-void text_buffer_terminate_string(text_buffer_t *buf);
+        buf->buf = realloc(buf->buf, buf->size);
+    }
+}
 
-int text_buffer_append_string(text_buffer_t *buf, char *str, size_t len);
-int text_buffer_append_string0(text_buffer_t *buf, char *str);
+__always_inline
+static void grow_buffer_small(dyn_buffer_t *buf) {
+    if (buf->cur + sizeof(long) > buf->size) {
+        buf->size *= 2;
+        buf->buf = realloc(buf->buf, buf->size);
+    }
+}
 
-int text_buffer_append_char(text_buffer_t *buf, int c);
+__always_inline
+static void dyn_buffer_write(dyn_buffer_t *buf, void *data, size_t size) {
+    grow_buffer(buf, size);
 
-void incremental_put(GHashTable *table, unsigned long inode_no, int mtime);
+    memcpy(buf->buf + buf->cur, data, size);
+    buf->cur += size;
+}
 
-int incremental_get(GHashTable *table, unsigned long inode_no);
+__always_inline
+static void dyn_buffer_write_char(dyn_buffer_t *buf, char c) {
+    grow_buffer_small(buf);
+
+    *(buf->buf + buf->cur) = c;
+    buf->cur += sizeof(c);
+}
+
+__always_inline
+static void dyn_buffer_write_str(dyn_buffer_t *buf, char *str) {
+    dyn_buffer_write(buf, str, strlen(str));
+    dyn_buffer_write_char(buf, '\0');
+}
+
+__always_inline
+static void dyn_buffer_append_string(dyn_buffer_t *buf, char *str) {
+    dyn_buffer_write(buf, str, strlen(str));
+}
+
+__always_inline
+static void dyn_buffer_write_int(dyn_buffer_t *buf, int d) {
+    grow_buffer_small(buf);
+
+    *(int *) (buf->buf + buf->cur) = d;
+    buf->cur += sizeof(int);
+}
+
+__always_inline
+static void dyn_buffer_write_short(dyn_buffer_t *buf, short s) {
+    grow_buffer_small(buf);
+
+    *(short *) (buf->buf + buf->cur) = s;
+    buf->cur += sizeof(short);
+}
+
+__always_inline
+static void dyn_buffer_write_long(dyn_buffer_t *buf, unsigned long l) {
+    grow_buffer_small(buf);
+
+    *(unsigned long *) (buf->buf + buf->cur) = l;
+    buf->cur += sizeof(unsigned long);
+}
+
+__always_inline
+static void dyn_buffer_destroy(dyn_buffer_t *buf) {
+    free(buf->buf);
+}
+
+__always_inline
+static void text_buffer_destroy(text_buffer_t *buf) {
+    dyn_buffer_destroy(&buf->dyn_buffer);
+}
+
+__always_inline
+static text_buffer_t text_buffer_create(int max_size) {
+    text_buffer_t text_buf;
+
+    text_buf.dyn_buffer = dyn_buffer_create();
+    text_buf.max_size = max_size;
+    text_buf.last_char_was_whitespace = FALSE;
+
+    return text_buf;
+}
+
+__always_inline
+static int text_buffer_append_char(text_buffer_t *buf, int c) {
+
+    if (SHOULD_IGNORE_CHAR(c) || c == ' ') {
+        if (!buf->last_char_was_whitespace && buf->dyn_buffer.cur != 0) {
+            dyn_buffer_write_char(&buf->dyn_buffer, ' ');
+            buf->last_char_was_whitespace = TRUE;
+
+            if (buf->max_size > 0 && buf->dyn_buffer.cur >= buf->max_size) {
+                return TEXT_BUF_FULL;
+            }
+        }
+    } else {
+        buf->last_char_was_whitespace = FALSE;
+        grow_buffer_small(&buf->dyn_buffer);
+
+        if (0 == ((utf8_int32_t) 0xffffff80 & c)) {
+            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = (char) c;
+        } else if (0 == ((utf8_int32_t) 0xfffff800 & c)) {
+            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = 0xc0 | (char) (c >> 6);
+            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = 0x80 | (char) (c & 0x3f);
+        } else if (0 == ((utf8_int32_t) 0xffff0000 & c)) {
+            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = 0xe0 | (char) (c >> 12);
+            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = 0x80 | (char) ((c >> 6) & 0x3f);
+            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = 0x80 | (char) (c & 0x3f);
+        } else {
+            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = 0xf0 | (char) (c >> 18);
+            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = 0x80 | (char) ((c >> 12) & 0x3f);
+            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = 0x80 | (char) ((c >> 6) & 0x3f);
+            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = 0x80 | (char) (c & 0x3f);
+        }
+
+        if (buf->max_size > 0 && buf->dyn_buffer.cur >= buf->max_size) {
+            return TEXT_BUF_FULL;
+        }
+    }
+
+    return 0;
+}
+
+
+__always_inline
+static void text_buffer_terminate_string(text_buffer_t *buf) {
+    if (buf->dyn_buffer.cur > 0 && *(buf->dyn_buffer.buf + buf->dyn_buffer.cur - 1) == ' ') {
+        *(buf->dyn_buffer.buf + buf->dyn_buffer.cur - 1) = '\0';
+    } else {
+        dyn_buffer_write_char(&buf->dyn_buffer, '\0');
+    }
+}
+
+__always_inline
+static int text_buffer_append_string(text_buffer_t *buf, char *str, size_t len) {
+
+    utf8_int32_t c;
+    if (str == NULL || len < 1 ||
+        (0xf0 == (0xf8 & str[0]) && len < 4) ||
+        (0xe0 == (0xf0 & str[0]) && len < 3) ||
+        (0xc0 == (0xe0 & str[0]) && len == 1) ||
+        *(str) == 0) {
+        return 0;
+    }
+
+    for (void *v = utf8codepoint(str, &c); c != '\0' && ((char *) v - str + 4) < len; v = utf8codepoint(v, &c)) {
+        if (utf8_validchr2(v)) {
+            text_buffer_append_char(buf, c);
+        }
+    }
+    return 0;
+}
+
+__always_inline
+static int text_buffer_append_string0(text_buffer_t *buf, char *str) {
+    return text_buffer_append_string(buf, str, strlen(str));
+}
+
+__always_inline
+static void incremental_put(GHashTable *table, unsigned long inode_no, int mtime) {
+    g_hash_table_insert(table, (gpointer) inode_no, GINT_TO_POINTER(mtime));
+}
+
+__always_inline
+static int incremental_get(GHashTable *table, unsigned long inode_no) {
+    if (table != NULL) {
+        return GPOINTER_TO_INT(g_hash_table_lookup(table, (gpointer) inode_no));
+    } else {
+        return 0;
+    }
+}
+
+__always_inline
+static int incremental_mark_file_for_copy(GHashTable *table, unsigned long inode_no) {
+    g_hash_table_insert(table, GINT_TO_POINTER(inode_no), GINT_TO_POINTER(1));
+}
 
-int incremental_mark_file_for_copy(GHashTable *table, unsigned long inode_no);
 
 const char *find_file_in_paths(const char **paths, const char *filename);
 

src/web/serve.c

@@ -181,7 +181,12 @@ int chunked_response_file(const char *filename, const char *mime,
         }
     }
     onion_response_set_length(res, length);
-    onion_response_set_header(res, "Content-Type", mime);
+    if (mime != NULL) {
+        onion_response_set_header(res, "Content-Type", mime);
+    } else {
+        onion_response_set_header(res, "Content-Type", "application/octet-stream");
+    }
+
     onion_response_write_headers(res);
     if ((onion_request_get_flags(request) & OR_HEAD) == OR_HEAD) {
         length = 0;
@@ -221,14 +226,6 @@ int search(UNUSED(void *p), onion_request *req, onion_response *res) {
         return OCS_NOT_PROCESSED;
     }
 
-    char *scroll_param;
-    const char *scroll = onion_request_get_query(req, "scroll");
-    if (scroll != NULL) {
-        scroll_param = "?scroll=3m";
-    } else {
-        scroll_param = "";
-    }
-
     const struct onion_block_t *block = onion_request_get_data(req);
 
     if (block == NULL) {
@@ -236,7 +233,7 @@ int search(UNUSED(void *p), onion_request *req, onion_response *res) {
     }
 
     char url[4096];
-    snprintf(url, 4096, "%s/sist2/_search%s", WebCtx.es_url, scroll_param);
+    snprintf(url, 4096, "%s/sist2/_search", WebCtx.es_url);
     response_t *r = web_post(url, onion_block_data(block), "Content-Type: application/json");
 
     set_default_headers(res);
@@ -246,6 +243,7 @@ int search(UNUSED(void *p), onion_request *req, onion_response *res) {
     if (r->status_code == 200) {
         onion_response_write(res, r->body, r->size);
     } else {
+        sist_log("serve.c", SIST_WARNING, "ElasticSearch error during query");
         onion_response_set_code(res, HTTP_INTERNAL_ERROR);
     }
 
@@ -254,43 +252,6 @@ int search(UNUSED(void *p), onion_request *req, onion_response *res) {
     return OCS_PROCESSED;
 }
 
-int scroll(UNUSED(void *p), onion_request *req, onion_response *res) {
-
-    int flags = onion_request_get_flags(req);
-    if ((flags & OR_METHODS) != OR_GET) {
-        return OCS_NOT_PROCESSED;
-    }
-
-    char url[4096];
-    snprintf(url, 4096, "%s/_search/scroll", WebCtx.es_url);
-
-    const char *scroll_id = onion_request_get_query(req, "scroll_id");
-
-    cJSON *json = cJSON_CreateObject();
-    cJSON_AddStringToObject(json, "scroll_id", scroll_id);
-    cJSON_AddStringToObject(json, "scroll", "3m");
-
-    char *json_str = cJSON_PrintUnformatted(json);
-    response_t *r = web_post(url, json_str, "Content-Type: application/json");
-
-    cJSON_Delete(json);
-    cJSON_free(json_str);
-
-    if (r->status_code != 200) {
-        free_response(r);
-        return OCS_NOT_PROCESSED;
-    }
-
-    set_default_headers(res);
-    onion_response_set_header(res, "Content-Type", "application/json");
-    onion_response_set_header(res, "Content-Disposition", "application/json");
-    onion_response_set_length(res, r->size);
-    onion_response_write(res, r->body, r->size);
-    free_response(r);
-
-    return OCS_PROCESSED;
-}
-
 int serve_file_from_url(cJSON *json, index_t *idx, onion_request *req, onion_response *res) {
 
     const char *path = cJSON_GetObjectItem(json, "path")->valuestring;
@@ -466,7 +427,6 @@ void serve(const char *hostname, const char *port) {
     onion_url_add(urls, "img/sprite-skin-flat.png", img_sprite_skin_flag);
 
     onion_url_add(urls, "es", search);
-    onion_url_add(urls, "scroll", scroll);
     onion_url_add(urls, "status", status);
     onion_url_add(
             urls,

web/css/auto-complete.min.css

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

web/css/dark.css

@@ -102,6 +102,7 @@ body {
     border-bottom: none;
     border-left: none;
     border-right: none;
+    padding: .25rem 0.5rem;
 }
 
 .list-group-item:first-child {
@@ -199,7 +200,7 @@ body {
     max-width: 100%;
     max-height: 175px;
     margin: 0 auto 0;
-    padding: 3px 3px 0 3px;
+    padding: 3px 3px 0;
     width: auto;
     height: auto;
 }
@@ -208,7 +209,7 @@ body {
     display: block;
     max-width: 64px;
     max-height: 64px;
-    margin: 0 auto 0;
+    margin: 0 auto;
     width: auto;
     height: auto;
 }
@@ -243,11 +244,18 @@ body {
 }
 
 mark {
-    background: #fff217;
+    background: rgba(251, 191, 41, 0.25);
     border-radius: 0;
     padding: 1px 0;
+    color: inherit;
 }
 
+.content-div mark {
+    background: rgba(251, 191, 41, 0.40);
+    color: white;
+}
+
+
 .content-div {
     font-family: SFMono-Regular, Menlo, Monaco, Consolas, "Liberation Mono", "Courier New", monospace;
     font-size: 13px;
@@ -391,10 +399,6 @@ option {
     margin-top: 1em;
 }
 
-.list-group-item {
-    padding: .25rem 0.5rem;
-}
-
 .wrapper-sm {
     min-width: 64px;
 }
@@ -423,3 +427,33 @@ option {
     margin-top: -14px;
     font-size: 11px;
 }
+
+@media (min-width: 800px) {
+    .small-btn {
+        display: none;
+    }
+    .large-btn {
+        display: inherit;
+    }
+}
+
+@media (max-width: 801px) {
+    .small-btn {
+        display: inherit;
+    }
+    .large-btn {
+        display: none;
+    }
+}
+
+#searchBar {
+    border-right: none;
+}
+
+#pathTree .title {
+    cursor: pointer;
+}
+
+svg {
+    fill: white;
+}

web/css/light.css

@@ -184,6 +184,7 @@ mark {
     background: #fff217;
     border-radius: 0;
     padding: 1px 0;
+    color: inherit;
 }
 
 .content-div {
@@ -287,3 +288,29 @@ mark {
     margin-top: -14px;
     font-size: 11px;
 }
+
+@media (min-width: 800px) {
+    .small-btn {
+        display: none;
+    }
+    .large-btn {
+        display: inherit;
+    }
+}
+
+@media (max-width: 801px) {
+    .small-btn {
+        display: inherit;
+    }
+    .large-btn {
+        display: none;
+    }
+}
+
+#searchBar {
+    border-right: none;
+}
+
+#pathTree .title {
+    cursor: pointer;
+}

web/js/dom.js

@@ -75,6 +75,10 @@ function shouldPlayVideo(hit) {
     return videoc !== "hevc" && videoc !== "mpeg2video" && videoc !== "wmv3";
 }
 
+function shouldDisplayRawImage(hit) {
+    return hit["_source"]["mime"] && hit["_source"]["mime"].startsWith("image/") && hit["_source"]["videoc"] !== "tiff";
+}
+
 function makePlaceholder(w, h, small) {
     let calc;
     if (small) {
@@ -96,10 +100,14 @@ function makePlaceholder(w, h, small) {
     return el;
 }
 
+function ext(hit) {
+    return hit["_source"].hasOwnProperty("extension") && hit["_source"]["extension"] !== "" ? "." + hit["_source"]["extension"] : "";
+}
+
 function makeTitle(hit) {
     let title = document.createElement("div");
     title.setAttribute("class", "file-title");
-    let extension = hit["_source"].hasOwnProperty("extension") && hit["_source"]["extension"] !== "" ? "." + hit["_source"]["extension"] : "";
+    let extension = ext(hit);
 
     applyNameToTitle(hit, title, extension);
 
@@ -113,7 +121,7 @@ function getTags(hit, mimeCategory) {
     switch (mimeCategory) {
         case "video":
         case "image":
-            if (hit["_source"].hasOwnProperty("videoc")) {
+            if (hit["_source"].hasOwnProperty("videoc") && hit["_source"]["videoc"]) {
                 const formatTag = document.createElement("span");
                 formatTag.setAttribute("class", "badge badge-pill badge-video");
                 formatTag.appendChild(document.createTextNode(hit["_source"]["videoc"].replace(" ", "")));
@@ -121,7 +129,7 @@ function getTags(hit, mimeCategory) {
             }
             break;
         case "audio": {
-            if (hit["_source"].hasOwnProperty("audioc")) {
+            if (hit["_source"].hasOwnProperty("audioc") && hit["_source"]["audioc"]) {
                 let formatTag = document.createElement("span");
                 formatTag.setAttribute("class", "badge badge-pill badge-audio");
                 formatTag.appendChild(document.createTextNode(hit["_source"]["audioc"]));
@@ -156,7 +164,7 @@ function getTags(hit, mimeCategory) {
 function infoButtonCb(hit) {
     return () => {
         getDocumentInfo(hit["_id"]).then(doc => {
-            $("#modal-title").text(doc["name"] + (doc["extension"] ? "." + doc["extension"] : ""));
+            $("#modal-title").text(doc["name"] + ext(hit));
 
             const tbody = $("<tbody>");
             $("#modal-body").empty()
@@ -175,7 +183,7 @@ function infoButtonCb(hit) {
                 "bitrate", "artist", "album", "album_artist", "genre", "title", "font_name", "tag"
             ]);
             Object.keys(doc)
-                .filter(key => key.startsWith("_keyword.") || key.startsWith("_text.") || displayFields.has(key))
+                .filter(key => key.startsWith("_keyword.") || key.startsWith("_text.") || displayFields.has(key) || key.startsWith("exif_"))
                 .forEach(key => {
                     tbody.append($("<tr>")
                         .append($("<td>").text(key))
@@ -369,6 +377,7 @@ function makeThumbnail(mimeCategory, hit, imgWrapper, small) {
         || hit["_source"]["mime"] === "application/pdf"
         || hit["_source"]["mime"] === "application/epub+zip"
         || hit["_source"]["mime"] === "application/x-cbz"
+        || hit["_source"]["mime"] === "application/x-cbr"
         || hit["_source"].hasOwnProperty("font_name")
     ) {
         thumbnail = document.createElement("img");
@@ -379,6 +388,15 @@ function makeThumbnail(mimeCategory, hit, imgWrapper, small) {
         }
         thumbnail.setAttribute("src", `t/${hit["_source"]["index"]}/${hit["_id"]}`);
 
+        if (!hit["_source"]["parent"] && shouldDisplayRawImage(hit)) {
+            imgWrapper.setAttribute("id", "sp" + hit["_id"]);
+            imgWrapper.setAttribute("data-src", `t/${hit["_source"]["index"]}/${hit["_id"]}`);
+            imgWrapper.setAttribute("href", `f/${hit["_id"]}`);
+            imgWrapper.setAttribute("data-caption", hit["_source"]["path"] + "/" + hit["_source"]["name"] + ext(hit));
+            imgWrapper.setAttribute("data-group", "p" + Math.floor(docCount / SIZE));
+            imgWrapper.classList.add("sp");
+        }
+
         const placeholder = makePlaceholder(hit["_source"]["width"], hit["_source"]["height"], small);
         imgWrapper.appendChild(placeholder);
 
@@ -499,8 +517,7 @@ function makePreloader() {
 function makePageIndicator(searchResult) {
     let pageIndicator = document.createElement("div");
     pageIndicator.setAttribute("class", "page-indicator font-weight-light");
-    const totalHits = searchResult["hits"]["total"].hasOwnProperty("value")
-        ? searchResult["hits"]["total"]["value"] : searchResult["hits"]["total"];
+    const totalHits = searchResult["aggregations"]["total_count"]["value"];
     pageIndicator.appendChild(document.createTextNode(docCount + " / " + totalHits));
     return pageIndicator;
 }
@@ -529,26 +546,29 @@ function makeStatsCard(searchResult) {
     resultMode.appendChild(gridMode);
     resultMode.appendChild(listMode);
 
-    if (mode === "grid") {
+    if (CONF.options.display === "grid") {
         gridMode.classList.add("active")
     } else {
         listMode.classList.add("active")
     }
 
     gridMode.addEventListener("click", () => {
-        mode = "grid";
-        localStorage.setItem("mode", mode);
+        console.log("what");
+        console.log(CONF.options);
+        CONF.options.display = "grid";
+        console.log(CONF.options);
+        CONF.save();
+        console.log(CONF.options);
         searchDebounced();
     });
     listMode.addEventListener("click", () => {
-        mode = "list";
-        localStorage.setItem("mode", mode);
+        CONF.options.display = "list";
+        CONF.save();
         searchDebounced();
     });
 
     let stat = document.createElement("span");
-    const totalHits = searchResult["hits"]["total"].hasOwnProperty("value")
-        ? searchResult["hits"]["total"]["value"] : searchResult["hits"]["total"];
+    const totalHits = searchResult["aggregations"]["total_count"]["value"];
     stat.appendChild(document.createTextNode(totalHits + " results in " + searchResult["took"] + "ms"));
 
     statsCardBody.appendChild(stat);
@@ -568,7 +588,7 @@ function makeStatsCard(searchResult) {
 function makeResultContainer() {
     let resultContainer = document.createElement("div");
 
-    if (mode === "grid") {
+    if (CONF.options.display === "grid") {
         resultContainer.setAttribute("class", "card-columns");
     } else {
         resultContainer.setAttribute("class", "list-group");

web/js/search.js

@@ -6,19 +6,47 @@ let tagTree;
 
 let searchBar = document.getElementById("searchBar");
 let pathBar = document.getElementById("pathBar");
-let scroll_id = null;
+let lastDoc = null;
+let reachedEnd = false;
 let docCount = 0;
 let coolingDown = false;
 let searchBusy = true;
 let selectedIndices = [];
+let indexMap = {};
 
-let mode;
-if (localStorage.getItem("mode") === null) {
-    mode = "grid";
-} else {
-    mode = localStorage.getItem("mode")
+const CONF = new Settings();
+
+const _defaults = {
+    display: "grid",
+    fuzzy: true,
+    highlight: true
+};
+
+function Settings() {
+    this.options = {};
+
+    this._onUpdate = function () {
+        $("#fuzzyToggle").prop("checked", this.options.fuzzy);
+    }
+
+    this.load = function () {
+        const raw = window.localStorage.getItem("options");
+        if (raw === null) {
+            this.options = _defaults;
+        } else {
+            this.options = JSON.parse(raw);
+        }
+
+        this._onUpdate();
+    }
+
+    this.save = function () {
+        window.localStorage.setItem("options", JSON.stringify(this.options));
+        this._onUpdate();
+    }
 }
 
+
 function showEsError() {
     $.toast({
         heading: "Elasticsearch connection error",
@@ -53,6 +81,7 @@ window.onload = () => {
         }
         window.location.reload();
     })
+    CONF.load();
 };
 
 function toggleFuzzy() {
@@ -62,8 +91,8 @@ function toggleFuzzy() {
 $.jsonPost("i").then(resp => {
 
     const urlIndices = (new URLSearchParams(location.search)).get("i");
-
     resp["indices"].forEach(idx => {
+        indexMap[idx.id] = idx.name;
         const opt = $("<option>")
             .attr("value", idx.id)
             .append(idx.name);
@@ -79,6 +108,8 @@ $.jsonPost("i").then(resp => {
         }
         $("#indices").append(opt);
     });
+
+    createPathTree("#pathTree");
 });
 
 function getDocumentInfo(id) {
@@ -105,6 +136,7 @@ function handleTreeClick(tree) {
     }
 }
 
+//TODO: filter based on selected indexes, sort mime types
 $.jsonPost("es", {
     aggs: {
         mimeTypes: {
@@ -151,15 +183,10 @@ $.jsonPost("es", {
         target: '#mimeTree'
     });
     mimeTree.on("node.click", handleTreeClick(mimeTree));
-    mimeTree.select();
-    mimeTree.node("any").deselect();
+    mimeTree.deselect();
+    mimeTree.node("any").select();
 });
 
-function leafTag(tag) {
-    const tokens = tag.split(".");
-    return tokens[tokens.length - 1]
-}
-
 // Tags tree
 $.jsonPost("es", {
     aggs: {
@@ -221,35 +248,10 @@ function addTag(map, tag, id, count) {
     }
 }
 
-new autoComplete({
-    selector: '#pathBar',
-    minChars: 1,
-    delay: 400,
-    renderItem: function (item) {
-        return '<div class="autocomplete-suggestion" data-val="' + item + '">' + item + '</div>';
-    },
-    source: async function (term, suggest) {
-        term = term.toLowerCase();
-
-        const choices = await getPathChoices();
-
-        let matches = [];
-        for (let i = 0; i < choices.length; i++) {
-            if (~choices[i].toLowerCase().indexOf(term)) {
-                matches.push(choices[i]);
-            }
-        }
-        suggest(matches);
-    },
-    onSelect: function () {
-        searchDebounced();
-    }
-});
-
 function insertHits(resultContainer, hits) {
     for (let i = 0; i < hits.length; i++) {
 
-        if (mode === "grid") {
+        if (CONF.options.display === "grid") {
             resultContainer.appendChild(createDocCard(hits[i]));
         } else {
             resultContainer.appendChild(createDocLine(hits[i]));
@@ -259,41 +261,18 @@ function insertHits(resultContainer, hits) {
 }
 
 window.addEventListener("scroll", function () {
-    if (!coolingDown && !searchBusy) {
+    if (!searchBusy) {
         let threshold = 400;
 
         if ((window.innerHeight + window.scrollY) >= document.body.offsetHeight - threshold) {
-            coolingDown = true;
-            doScroll();
+            if (!reachedEnd) {
+                coolingDown = true;
+                search(lastDoc);
+            }
         }
     }
 });
 
-function doScroll() {
-    $.get("scroll", {scroll_id: scroll_id})
-        .then(searchResult => {
-            let searchResults = document.getElementById("searchResults");
-            let hits = searchResult["hits"]["hits"];
-
-            //Page indicator
-            let pageIndicator = makePageIndicator(searchResult);
-            searchResults.appendChild(pageIndicator);
-
-            //Result container
-            let resultContainer = makeResultContainer();
-            searchResults.appendChild(resultContainer);
-
-            insertHits(resultContainer, hits);
-
-            if (hits.length === SIZE) {
-                coolingDown = false;
-            }
-        })
-        .fail(() => {
-            window.location.reload();
-        })
-}
-
 function getSelectedNodes(tree) {
     let selectedNodes = [];
 
@@ -314,21 +293,25 @@ function getSelectedNodes(tree) {
     return selectedNodes
 }
 
-function search() {
+function search(after = null) {
+    lastDoc = null;
+
     if (searchBusy) {
         return;
     }
     searchBusy = true;
 
-    //Clear old search results
     let searchResults = document.getElementById("searchResults");
-    while (searchResults.firstChild) {
-        searchResults.removeChild(searchResults.firstChild);
+    //Clear old search results
+    let preload;
+    if (!after) {
+        while (searchResults.firstChild) {
+            searchResults.removeChild(searchResults.firstChild);
+        }
+        preload = makePreloader();
+        searchResults.appendChild(preload);
     }
 
-    const preload = makePreloader();
-    searchResults.appendChild(preload);
-
     let query = searchBar.value;
     let empty = query === "";
     let condition = empty ? "should" : "must";
@@ -362,27 +345,40 @@ function search() {
         filters.push([{terms: {"tag": tags}}]);
     }
 
-    $.jsonPost("es?scroll=1", {
+    let q = {
         "_source": {
-            excludes: ["content"]
+            excludes: ["content", "_tie"]
         },
         query: {
             bool: {
                 [condition]: {
-                    multi_match: {
+                    simple_query_string: {
                         query: query,
-                        type: "most_fields",
                         fields: fields,
-                        operator: "and"
+                        default_operator: "and"
                     }
                 },
                 filter: filters
             }
         },
-        sort: [
-            "_score"
+        "sort": [
+            {"_score": {"order": "desc"}},
+            {"_tie": {"order": "asc"}}
         ],
-        highlight: {
+        aggs:
+            {
+                total_size: {"sum": {"field": "size"}},
+                total_count: {"value_count": {"field": "size"}}
+            },
+        size: SIZE,
+    };
+
+    if (after) {
+        q.search_after = [after["_score"], after["_id"]];
+    }
+
+    if (CONF.options.highlight) {
+        q.highlight = {
             pre_tags: ["<mark>"],
             post_tags: ["</mark>"],
             fields: {
@@ -392,25 +388,36 @@ function search() {
                 "name.nGram": {},
                 font_name: {},
             }
-        },
-        aggs: {
-            total_size: {"sum": {"field": "size"}}
-        },
-        size: SIZE,
-    }).then(searchResult => {
-        scroll_id = searchResult["_scroll_id"];
+        };
+    }
 
-        preload.remove();
-        //Search stats
-        searchResults.appendChild(makeStatsCard(searchResult));
+    $.jsonPost("es", q).then(searchResult => {
+        let hits = searchResult["hits"]["hits"];
+        if (hits) {
+            lastDoc = hits[hits.length - 1];
+        }
+
+        if (!after) {
+            preload.remove();
+            searchResults.appendChild(makeStatsCard(searchResult));
+        } else {
+            let pageIndicator = makePageIndicator(searchResult);
+            searchResults.appendChild(pageIndicator);
+        }
 
         //Setup page
         let resultContainer = makeResultContainer();
         searchResults.appendChild(resultContainer);
 
-        docCount = 0;
-        insertHits(resultContainer, searchResult["hits"]["hits"]);
+        window.setTimeout(() => {
+            $(".sp").SmartPhoto({animationSpeed: 0, swipeTopToClose: true, showAnimation: false, forceInterval: 50});
+        }, 100);
 
+        if (!after) {
+            docCount = 0;
+        }
+        reachedEnd = hits.length !== SIZE;
+        insertHits(resultContainer, hits);
         searchBusy = false;
     });
 }
@@ -471,21 +478,136 @@ function updateIndices() {
 document.getElementById("indices").addEventListener("change", updateIndices);
 updateIndices();
 
-//Suggest
-function getPathChoices() {
-    return new Promise(getPaths => {
-        $.jsonPost("es", {
-            suggest: {
-                path: {
-                    prefix: pathBar.value,
-                    completion: {
-                        field: "suggest-path",
-                        skip_duplicates: true,
-                        size: 10000
-                    }
+window.onkeyup = function (e) {
+    if (e.key === "/" || e.key === "Escape") {
+        const bar = document.getElementById("searchBar");
+        bar.scrollIntoView();
+        bar.focus();
+    }
+};
+
+function getNextDepth(node) {
+    let q = {
+        query: {
+            bool: {
+                filter: [
+                    {term: {index: node.index}},
+                    {term: {_depth: node.depth + 1}}
+                ]
+            }
+        },
+        aggs: {
+            paths: {
+                terms: {
+                    field: "path",
+                    size: 10000
                 }
             }
-        }).then(resp => getPaths(resp["suggest"]["path"][0]["options"].map(opt => opt["_source"]["path"])));
+        },
+        size: 0
+    }
+
+    if (node.depth > 0) {
+        q.query.bool.must = {
+            prefix: {
+                path: node.id,
+            }
+        };
+    }
+
+    return $.jsonPost("es", q).then(resp => {
+        const buckets = resp["aggregations"]["paths"]["buckets"];
+        if (!buckets) {
+            return false;
+        }
+        return buckets
+            .filter(bucket => bucket.key.length > node.id.length || node.id.startsWith("/"))
+            .sort((a, b) => a.key > b.key)
+            .map(bucket => {
+                const i = bucket.key.lastIndexOf("/");
+                const name = (i === -1 || i === 1) ? bucket.key : bucket.key.slice(i + 1);
+
+                return {
+                    id: bucket.key,
+                    text: `${name}/ (${bucket.doc_count})`,
+                    depth: node.depth + 1,
+                    index: node.index,
+                    children: true,
+                }
+            })
     })
 }
 
+function handlePathTreeClick(tree) {
+    return (event, node, handler) => {
+
+        if (node.depth !== 0) {
+            $("#pathBar").val(node.id)
+            $("#pathTreeModal").modal("hide")
+            searchDebounced();
+        }
+
+        handler();
+    }
+}
+
+function createPathTree(target) {
+    let pathTree = new InspireTree({
+        data: function (node, resolve, reject) {
+            return getNextDepth(node);
+        }
+    });
+
+    selectedIndices.forEach(index => {
+        pathTree.addNode({
+            id: "/" + index,
+            text: `/[${indexMap[index]}]`,
+            index: index,
+            depth: 0,
+            children: true
+        })
+    })
+
+    new InspireTreeDOM(pathTree, {
+        target: target
+    });
+
+    pathTree.on("node.click", handlePathTreeClick(pathTree));
+
+    const button = document.querySelector("#pathBarHelper")
+    const tooltip = document.querySelector("#pathTreeTooltip")
+    console.log(button)
+    console.log(tooltip)
+    Popper.createPopper(button, tooltip ,{
+        trigger: "click",
+        placement: "right",
+    });
+}
+
+function updateSettings() {
+    CONF.options.display = $("#settingDisplay").val();
+    CONF.options.fuzzy = $("#settingFuzzy").prop("checked");
+    CONF.options.highlight = $("#settingHighlight").prop("checked");
+    CONF.save();
+
+    searchDebounced();
+
+    $.toast({
+        heading: "Settings updated",
+        text: "Settings saved to browser storage",
+        stack: 3,
+        bgColor: "#00a4bc",
+        textColor: "#fff",
+        position: 'bottom-right',
+        hideAfter: 3000,
+        loaderBg: "#08c7e8",
+    });
+}
+
+function loadSettings() {
+    CONF.load();
+
+    $("#settingDisplay").val(CONF.options.display);
+    $("#settingFuzzy").prop("checked", CONF.options.fuzzy);
+    $("#settingHighlight").prop("checked", CONF.options.highlight);
+}

web/search.html

@@ -11,27 +11,44 @@
 
 <nav class="navbar navbar-expand-lg">
     <a class="navbar-brand" href="/">sist2</a>
-    <span class="badge badge-pill version">v1.2.5</span>
+    <span class="badge badge-pill version">v1.3.2</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>
+    <button style="margin-left: auto" class="btn" type="button" data-toggle="modal" data-target="#settings" onclick="loadSettings()">Settings</button>
+    <a id="theme" class="btn" title="Toggle theme" href="/">Theme</a>
 </nav>
 
 <div class="container">
     <div class="card">
         <div class="card-body">
+
             <div class="form-group">
-                <input id="pathBar" type="search" class="form-control" placeholder="Filter path">
+                <div class="input-group">
+                    <div class="input-group-prepend">
+                        <button id="pathBarHelper" class="btn btn-outline-secondary" data-toggle="modal" data-target="#pathTreeModal">
+                            <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 576 512" width="20px"><path d="M288 224h224a32 32 0 0 0 32-32V64a32 32 0 0 0-32-32H400L368 0h-80a32 32 0 0 0-32 32v64H64V8a8 8 0 0 0-8-8H40a8 8 0 0 0-8 8v392a16 16 0 0 0 16 16h208v64a32 32 0 0 0 32 32h224a32 32 0 0 0 32-32V352a32 32 0 0 0-32-32H400l-32-32h-80a32 32 0 0 0-32 32v64H64V128h192v64a32 32 0 0 0 32 32zm0 96h66.74l32 32H512v128H288zm0-288h66.74l32 32H512v128H288z"/></svg>
+                        </button>
+                    </div>
+                    <input id="pathBar" type="search" class="form-control" placeholder="Filter path">
+                </div>
             </div>
+
             <div class="input-group">
                 <div class="input-group-prepend">
                     <div class="input-group-text">
-                        <span title="Toggle fuzzy searching"  onclick="document.getElementById('fuzzyToggle').click()">Fuzzy&nbsp</span>
+                        <span title="Toggle fuzzy searching" onclick="document.getElementById('fuzzyToggle').click()">Fuzzy&nbsp</span>
                         <input title="Toggle fuzzy searching" type="checkbox" id="fuzzyToggle"
                                onclick="toggleFuzzy()" checked>
                     </div>
                 </div>
                 <input id="searchBar" type="search" class="form-control" placeholder="Search">
-
+                <div class="input-group-append">
+                    <button class="btn btn-outline-secondary small-btn" type="button" data-toggle="modal"
+                            data-target="#help">?
+                    </button>
+                    <button class="btn btn-outline-secondary large-btn" type="button" data-toggle="modal"
+                            data-target="#help">Help
+                    </button>
+                </div>
             </div>
 
             <input title="File size" id="sizeSlider" name="size">
@@ -45,10 +62,12 @@
                 <div class="col" id="treeTabs">
                     <ul class="nav nav-tabs" role="tablist">
                         <li class="nav-item">
-                            <a class="nav-link active" data-toggle="tab" href="#mime" role="tab" aria-controls="home" aria-selected="true">Mime Types</a>
+                            <a class="nav-link active" data-toggle="tab" href="#mime" role="tab" aria-controls="home"
+                               aria-selected="true">Mime Types</a>
                         </li>
                         <li class="nav-item">
-                            <a class="nav-link" data-toggle="tab" href="#tag" role="tab" aria-controls="profile" aria-selected="false" title="User-defined tags">Tags</a>
+                            <a class="nav-link" data-toggle="tab" href="#tag" role="tab" aria-controls="profile"
+                               aria-selected="false" title="User-defined tags">Tags</a>
                         </li>
                     </ul>
                     <div class="tab-content" id="myTabContent">
@@ -79,6 +98,118 @@
         </div>
     </div>
 
+    <div class="modal" id="help" tabindex="-1" role="dialog" aria-labelledby="modal-title" aria-hidden="true">
+        <div class="modal-dialog modal-lg modal-dialog-centered" role="document">
+            <div class="modal-content">
+                <div class="modal-header">
+                    <h5 class="modal-title">Search help</h5>
+                    <button type="button" class="close" data-dismiss="modal" aria-label="Close">
+                        <span aria-hidden="true">&times;</span>
+                    </button>
+                </div>
+                <div class="modal-body">
+
+                    <table class="table">
+                        <tbody>
+                        <tr>
+                            <td><code>+</code></td>
+                            <td>signifies AND operation</td>
+                        </tr>
+                        <tr>
+                            <td><code>|</code></td>
+                            <td>signifies OR operation</td>
+                        </tr>
+                        <tr>
+                            <td><code>-</code></td>
+                            <td>negates a single token</td>
+                        </tr>
+                        <tr>
+                            <td><code>""</code></td>
+                            <td>wraps a number of tokens to signify a phrase for searching</td>
+                        </tr>
+                        <tr>
+                            <td><code>*</code></td>
+                            <td>at the end of a term signifies a prefix query</td>
+                        </tr>
+                        <tr>
+                            <td><code>(</code> and <code>)</code></td>
+                            <td>signify precedence</td>
+                        </tr>
+                        <tr>
+                            <td><code>~N</code></td>
+                            <td>after a word signifies edit distance (fuzziness)</td>
+                        </tr>
+                        <tr>
+                            <td><code>~N</code></td>
+                            <td>after a phrase signifies slop amount</td>
+                        </tr>
+                        </tbody>
+                    </table>
+
+                    <p>For example: <code>"fried eggs" +(eggplant | potato) -frittata</code> will match the phrase
+                        <i>fried eggs</i> and either <i>eggplant</i> or <i>potato</i>, but will ignore results
+                        containing <i>frittata</i>.</p>
+
+                    <p>When neither <code>+</code> or <code>|</code> is specified, the default operator is <code>+</code> (and).</p>
+                    <p>When the <b>Fuzzy</b> option is checked, partial matches are also returned.</p>
+                    <br>
+                    <p>For more information, see <a target="_blank"
+                                                    href="//www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl-simple-query-string-query.html">Elasticsearch
+                        documentation</a></p>
+                </div>
+            </div>
+        </div>
+    </div>
+
+    <div class="modal" id="settings" tabindex="-1" role="dialog" aria-labelledby="modal-title" aria-hidden="true">
+        <div class="modal-dialog modal-dialog-centered" role="document">
+            <div class="modal-content">
+                <div class="modal-header">
+                    <h5 class="modal-title">Settings</h5>
+                    <button type="button" class="close" data-dismiss="modal" aria-label="Close">
+                        <span aria-hidden="true">&times;</span>
+                    </button>
+                </div>
+                <div class="modal-body">
+                    <div class="custom-control custom-checkbox">
+                        <input type="checkbox" class="custom-control-input" id="settingHighlight">
+                        <label class="custom-control-label" for="settingHighlight">Enable highlighting</label>
+                    </div>
+
+                    <div class="custom-control custom-checkbox">
+                        <input type="checkbox" class="custom-control-input" id="settingFuzzy">
+                        <label class="custom-control-label" for="settingFuzzy">Set fuzzy search by default</label>
+                    </div>
+
+                    <label for="settingDisplay">Display</label>
+                    <select id="settingDisplay" class="form-control form-control-sm">
+                        <option value="grid">Grid</option>
+                        <option value="list">List</option>
+                    </select>
+
+                    <br>
+                    <button style="float: right" class="btn btn-primary" onclick="updateSettings()">Update settings</button>
+                </div>
+            </div>
+        </div>
+    </div>
+
+    <div class="modal" id="pathTreeModal" tabindex="-1" role="dialog" aria-labelledby="modal-title" aria-hidden="true">
+        <div class="modal-dialog modal-lg" role="document">
+            <div class="modal-content">
+                <div class="modal-header">
+                    <h5 class="modal-title">Select path</h5>
+                    <button type="button" class="close" data-dismiss="modal" aria-label="Close">
+                        <span aria-hidden="true">&times;</span>
+                    </button>
+                </div>
+                <div class="modal-body">
+                    <div id="pathTree" class="tree"></div>
+                </div>
+            </div>
+        </div>
+    </div>
+
     <div id="searchResults"></div>
 </div>