Merge pull request #164 from simon987/dev

v2.10.1
This commit is contained in:
simon987 2021-06-13 09:50:23 -04:00 committed by GitHub
commit bf28dc8993
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
33 changed files with 525 additions and 333 deletions

24
.dockerignore Normal file
View File

@ -0,0 +1,24 @@
.idea
*/thumbs
*.cbp
CMakeCache.txt
CMakeFiles
cmake-build-debug
cmake_install.cmake
Makefile
*.out
LOG
sist2*
index.sist2/
bundle*.css
bundle.js
**/*.a
**/vgcore.*
build/
.git/
third-party/libscan/libscan-test-files/
**/ext_ffmpeg
**/ext_libmobi
**/scan_a_test
Dockerfile
*.idx/

View File

@ -8,7 +8,7 @@ platform:
steps:
- name: build
image: simon987/ubuntu_ci
image: simon987/sist2-build
commands:
- ./ci/build.sh
- name: docker
@ -19,8 +19,8 @@ steps:
password:
from_secret: DOCKER_PASSWORD
repo: simon987/sist2
context: ./Docker/
dockerfile: ./Docker/Dockerfile
context: ./
dockerfile: ./Dockerfile
auto_tag: true
auto_tag_suffix: x64-linux
when:
@ -41,32 +41,32 @@ steps:
source:
- ./VERSION
- ./sist2-x64-linux
- ./sist2-x64-linux-debug.tar.gz
- ./sist2-x64-linux-debug
---
kind: pipeline
type: docker
name: arm64
platform:
arch: arm64
steps:
- name: build
image: simon987/ubuntu_ci_arm
commands:
- ./ci/build_arm64.sh
- name: scp files
image: appleboy/drone-scp
settings:
host:
from_secret: SSH_HOST
port:
from_secret: SSH_PORT
user:
from_secret: SSH_USER
key:
from_secret: SSH_KEY
target: /files/sist2/${DRONE_REPO_OWNER}_${DRONE_REPO_NAME}/arm_${DRONE_BRANCH}_${DRONE_BUILD_NUMBER}_${DRONE_COMMIT}/
source:
- ./sist2-arm64-linux
#---
#kind: pipeline
#type: docker
#name: arm64
#
#platform:
# arch: arm64
#
#steps:
# - name: build
# image: simon987/ubuntu_ci_arm
# commands:
# - ./ci/build_arm64.sh
# - name: scp files
# image: appleboy/drone-scp
# settings:
# host:
# from_secret: SSH_HOST
# port:
# from_secret: SSH_PORT
# user:
# from_secret: SSH_USER
# key:
# from_secret: SSH_KEY
# target: /files/sist2/${DRONE_REPO_OWNER}_${DRONE_REPO_NAME}/arm_${DRONE_BRANCH}_${DRONE_BUILD_NUMBER}_${DRONE_COMMIT}/
# source:
# - ./sist2-arm64-linux

1
.gitignore vendored
View File

@ -16,3 +16,4 @@ bundle.js
vgcore.*
build/
third-party/
*.idx/

View File

@ -5,7 +5,7 @@ project(sist2 C)
option(SIST_DEBUG "Build a debug executable" on)
set(BUILD_TESTS off)
set(BUILD_TESTS on)
add_subdirectory(third-party/libscan)
set(ARGPARSE_SHARED off)
add_subdirectory(third-party/argparse)
@ -36,14 +36,15 @@ add_executable(sist2
target_link_directories(sist2 PRIVATE BEFORE ${_VCPKG_INSTALLED_DIR}/${VCPKG_TARGET_TRIPLET}/lib/)
set(CMAKE_FIND_LIBRARY_SUFFIXES .a .lib)
find_package(PkgConfig REQUIRED)
pkg_search_module(GLIB REQUIRED glib-2.0)
find_package(lmdb CONFIG REQUIRED)
find_package(cJSON CONFIG REQUIRED)
find_package(unofficial-glib CONFIG REQUIRED)
find_package(unofficial-mongoose CONFIG REQUIRED)
find_package(CURL CONFIG REQUIRED)
#find_package(OpenSSL REQUIRED)
target_include_directories(
sist2 PUBLIC
@ -51,6 +52,7 @@ target_include_directories(
${CMAKE_SOURCE_DIR}/third-party/utf8.h/
${CMAKE_SOURCE_DIR}/third-party/libscan/
${CMAKE_SOURCE_DIR}/
${GLIB_INCLUDE_DIRS}
)
target_compile_options(
@ -103,7 +105,7 @@ target_link_libraries(
lmdb
cjson
argparse
unofficial::glib::glib
${GLIB_LDFLAGS}
unofficial::mongoose::mongoose
CURL::libcurl

View File

@ -1,22 +0,0 @@
FROM ubuntu:19.10
MAINTAINER simon987 <me@simon987.net>
RUN apt update
RUN apt install -y libglib2.0-0 libcurl4 libmagic1 libharfbuzz-bin libopenjp2-7 libarchive13 liblzma5 libzstd1 liblz4-1 \
curl libtiff5 libpng16-16 libpcre3
RUN mkdir -p /usr/share/tessdata && \
cd /usr/share/tessdata/ && \
curl -o /usr/share/tessdata/hin.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/hin.traineddata &&\
curl -o /usr/share/tessdata/jpn.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/jpn.traineddata &&\
curl -o /usr/share/tessdata/eng.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/eng.traineddata &&\
curl -o /usr/share/tessdata/fra.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/fra.traineddata &&\
curl -o /usr/share/tessdata/rus.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/rus.traineddata &&\
curl -o /usr/share/tessdata/spa.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/spa.traineddata && ls -lh
ADD sist2_arm64 /root/sist2
ENV LANG C.UTF-8
ENV LC_ALL C.UTF-8
ENTRYPOINT ["/root/sist2"]

View File

@ -1,13 +0,0 @@
rm ./sist2_arm64
cp ../sist2_arm64.gz .
gzip -d sist2_arm64.gz
version=$(./sist2_arm64 --version)
echo "Version ${version}"
docker build . -t simon987/sist2-arm64:"${version}" -t simon987/sist2-arm64:latest
docker push simon987/sist2-arm64:"${version}"
docker push simon987/sist2-arm64:latest
docker run --rm simon987/sist2-arm64 -v

View File

@ -1,6 +1,14 @@
FROM ubuntu:20.04
FROM simon987/sist2-build as build
MAINTAINER simon987 <me@simon987.net>
WORKDIR /build/
ADD . /build/
RUN cmake -DSIST_DEBUG=off -DBUILD_TESTS=off -DCMAKE_TOOLCHAIN_FILE=/vcpkg/scripts/buildsystems/vcpkg.cmake .
RUN make -j$(nproc)
RUN strip sist2
FROM ubuntu:20.10
RUN apt update
RUN apt install -y libglib2.0-0 libcurl4 libmagic1 libharfbuzz-bin libopenjp2-7 libarchive13 liblzma5 libzstd1 liblz4-1 \
curl libtiff5 libpng16-16 libpcre3
@ -12,9 +20,9 @@ RUN mkdir -p /usr/share/tessdata && \
curl -o /usr/share/tessdata/eng.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/eng.traineddata &&\
curl -o /usr/share/tessdata/fra.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/fra.traineddata &&\
curl -o /usr/share/tessdata/rus.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/rus.traineddata &&\
curl -o /usr/share/tessdata/spa.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/spa.traineddata && ls -lh
curl -o /usr/share/tessdata/spa.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/spa.traineddata
ADD sist2 /root/sist2
COPY --from=build /build/sist2 /root/sist2
ENV LANG C.UTF-8
ENV LC_ALL C.UTF-8

1
Dockerfile.arm64 Normal file
View File

@ -0,0 +1 @@
# TODO

View File

@ -25,14 +25,12 @@ sist2 (Simple incremental search tool)
* OCR support with tesseract \*\*\*
* Stats page & disk utilisation visualization
\* See [format support](#format-support)
\*\* See [Archive files](#archive-files)
\*\*\* See [OCR](#ocr)
![stats](docs/stats.png)
## Getting Started
1. Have an Elasticsearch (>= 6.X.X) instance running
@ -57,10 +55,8 @@ sist2 (Simple incremental search tool)
1. See [Usage guide](docs/USAGE.md)
\* *Windows users*: **sist2** runs under [WSL](https://en.wikipedia.org/wiki/Windows_Subsystem_for_Linux)
## Example usage
See [Usage guide](docs/USAGE.md) for more details
@ -69,7 +65,6 @@ See [Usage guide](docs/USAGE.md) for more details
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
@ -78,8 +73,8 @@ pdf,xps,fb2,epub | MuPDF | text+ocr | yes | author, title |
cbz,cbr | *(none)* | - | yes | - |
`audio/*` | ffmpeg | - | yes | ID3 tags |
`video/*` | ffmpeg | - | yes | title, comment, artist |
`image/*` | ffmpeg | - | yes | [Common EXIF tags](https://github.com/simon987/sist2/blob/efdde2734eca9b14a54f84568863b7ffd59bdba3/src/parsing/media.c#L190) |
raw, rw2, dng, cr2, crw, dcr, k25, kdc, mrw, pef, xf3, arw, sr2, srf, erf | LibRaw | - | yes | Common EXIF tags |
`image/*` | ffmpeg | - | yes | [Common EXIF tags](https://github.com/simon987/sist2/blob/efdde2734eca9b14a54f84568863b7ffd59bdba3/src/parsing/media.c#L190), GPS tags |
raw, rw2, dng, cr2, crw, dcr, k25, kdc, mrw, pef, xf3, arw, sr2, srf, erf | LibRaw | - | yes | Common EXIF tags, GPS tags |
ttf,ttc,cff,woff,fnt,otf | Freetype2 | - | yes, `bmp` | Name & style |
`text/plain` | *(none)* | yes | no | - |
html, xml | *(none)* | yes | no | - |
@ -91,38 +86,37 @@ mobi, azw, azw3 | libmobi | yes | no | author, title |
\* *See [Archive files](#archive-files)*
### Archive files
**sist2** will scan files stored into archive files (zip, tar, 7z...) as if
they were directly in the file system. Recursive (archives inside archives)
**sist2** will scan files stored into archive files (zip, tar, 7z...) as if they were directly in the file system.
Recursive (archives inside archives)
scan is also supported.
**Limitations**:
* Support for parsing media files with formats that require *seek* (e.g. `.gif`, `.mp4` w/ fragmented metadata etc.)
is limitted (see `--mem-buffer` option)
* Archive files are scanned sequentially, by a single thread. On systems where
**sist2** is not I/O bound, scans might be faster when larger archives are split
into smaller parts.
**sist2** is not I/O bound, scans might be faster when larger archives are split into smaller parts.
### OCR
You can enable OCR support for pdf,xps,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).
`--ocr <lang>` option. Download the language data files with your package manager (`apt install tesseract-ocr-eng`) or
directly [from Github](https://github.com/tesseract-ocr/tesseract/wiki/Data-Files).
The `simon987/sist2` image comes with common languages
(hin, jpn, eng, fra, rus, spa) pre-installed.
Examples
```bash
sist2 scan --ocr jpn ~/Books/Manga/
sist2 scan --ocr eng ~/Books/Textbooks/
```
## Build from source
You can compile **sist2** by yourself if you don't want to use the pre-compiled
binaries (GCC 7+ required).
You can compile **sist2** by yourself if you don't want to use the pre-compiled binaries (GCC 7+ required).
1. Install compile-time dependencies

View File

@ -8,7 +8,7 @@ git submodule update --init --recursive
rm -rf CMakeFiles CMakeCache.txt
cmake -DSIST_DEBUG=off -DCMAKE_TOOLCHAIN_FILE="${VCPKG_ROOT}/scripts/buildsystems/vcpkg.cmake" .
make -j 33
make -j $(nproc)
strip sist2
./sist2 -v > VERSION
cp sist2 Docker/
@ -16,7 +16,5 @@ mv sist2 sist2-x64-linux
rm -rf CMakeFiles CMakeCache.txt
cmake -DSIST_DEBUG=on -DCMAKE_TOOLCHAIN_FILE="${VCPKG_ROOT}/scripts/buildsystems/vcpkg.cmake" .
make -j 33
cp /usr/lib/x86_64-linux-gnu/libasan.so.2.0.0 libasan.so.2
make -j $(nproc)
mv sist2_debug sist2-x64-linux-debug
tar -czf sist2-x64-linux-debug.tar.gz sist2-x64-linux-debug libasan.so.2

View File

@ -46,6 +46,7 @@ Scan options
--fast Only index file names & mime type
--treemap-threshold=<str> Relative size threshold for treemap (see USAGE.md). DEFAULT: 0.0005
--mem-buffer=<int> Maximum memory buffer size per thread in MB for files inside archives (see USAGE.md). DEFAULT: 2000
--read-subtitles Read subtitles from media files
Index options
-t, --threads=<int> Number of threads. DEFAULT=1
@ -91,7 +92,7 @@ Made by simon987 <me@simon987.net>. Released under GPL-3.0
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))
* `--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.
@ -123,6 +124,7 @@ Made by simon987 <me@simon987.net>. Released under GPL-3.0
larger than this number will be read sequentially and no *seek* operations will be supported.
To check if a media file can be parsed without *seek*, execute `cat file.mp4 | ffprobe -`
* `--read-subtitles` When enabled, will attempt to read the subtitles stream from media files.
### Scan examples

View File

@ -105,10 +105,10 @@
"analyzer": "my_nGram",
"type": "text"
},
"_keyword.*": {
"_keyword.*": {
"type": "keyword"
},
"_text.*": {
"_text.*": {
"analyzer": "content_analyzer",
"type": "text",
"fields": {
@ -165,6 +165,30 @@
"exif_user_comment": {
"type": "text"
},
"exif_gps_longitude_ref": {
"type": "keyword",
"index": false
},
"exif_gps_longitude_dms": {
"type": "keyword",
"index": false
},
"exif_gps_longitude_dec": {
"type": "keyword",
"index": false
},
"exif_gps_latitude_ref": {
"type": "keyword",
"index": false
},
"exif_gps_latitude_dms": {
"type": "keyword",
"index": false
},
"exif_gps_latitude_dec": {
"type": "keyword",
"index": false
},
"author": {
"type": "text"
},

6
scripts/reset.sh Executable file
View File

@ -0,0 +1,6 @@
#!/usr/bin/env bash
make clean
rm -rf CMakeFiles/ CMakeCache.txt Makefile \
third-party/libscan/CMakeFiles third-party/libscan/CMakeCache.txt third-party/libscan/third-party/ext_ffmpeg \
third-party/libscan/third-party/ext_libmobi third-party/libscan/Makefile

View File

@ -227,6 +227,7 @@ int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
LOG_DEBUGF("cli.c", "arg depth=%d", args->depth)
LOG_DEBUGF("cli.c", "arg path=%s", args->path)
LOG_DEBUGF("cli.c", "arg archive=%s", args->archive)
LOG_DEBUGF("cli.c", "arg archive_passphrase=%s", args->archive_passphrase)
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)

View File

@ -18,6 +18,7 @@ typedef struct scan_args {
char *path;
char *archive;
archive_mode_t archive_mode;
char *archive_passphrase;
char *tesseract_lang;
const char *tesseract_path;
char *exclude_regex;
@ -25,6 +26,7 @@ typedef struct scan_args {
const char* treemap_threshold_str;
double treemap_threshold;
int max_memory_buffer;
int read_subtitles;
} scan_args_t;
scan_args_t *scan_args_create();

View File

@ -40,6 +40,8 @@ typedef struct {
pcre_extra *exclude_extra;
int fast;
GHashTable *dbg_current_files;
scan_arc_ctx_t arc_ctx;
scan_comic_ctx_t comic_ctx;
scan_ebook_ctx_t ebook_ctx;

File diff suppressed because one or more lines are too long

View File

@ -15,9 +15,13 @@ typedef struct {
char has_parent;
} line_t;
#define META_NEXT 0xFFFF
void skip_meta(FILE *file) {
enum metakey key = getc(file);
while (key != '\n') {
enum metakey key = 0;
fread(&key, sizeof(uint16_t), 1, file);
while (key != META_NEXT) {
if (IS_META_INT(key)) {
fseek(file, sizeof(int), SEEK_CUR);
} else if (IS_META_LONG(key)) {
@ -26,7 +30,7 @@ void skip_meta(FILE *file) {
while ((getc(file))) {}
}
key = getc(file);
fread(&key, sizeof(uint16_t), 1, file);
}
}
@ -66,7 +70,7 @@ index_descriptor_t read_index_descriptor(char *path) {
}
char *buf = malloc(info.st_size + 1);
int ret = read(fd, buf, info.st_size);
size_t ret = read(fd, buf, info.st_size);
if (ret == -1) {
LOG_FATALF("serialize.c", "Could not read index descriptor: %s", strerror(errno));
}
@ -152,8 +156,20 @@ char *get_meta_key_text(enum metakey meta_key) {
return "thumbnail";
case MetaPages:
return "pages";
case MetaExifGpsLongitudeRef:
return "exif_gps_longitude_ref";
case MetaExifGpsLongitudeDMS:
return "exif_gps_longitude_dms";
case MetaExifGpsLongitudeDec:
return "exif_gps_longitude_dec";
case MetaExifGpsLatitudeRef:
return "exif_gps_latitude_ref";
case MetaExifGpsLatitudeDMS:
return "exif_gps_latitude_dms";
case MetaExifGpsLatitudeDec:
return "exif_gps_latitude_dec";
default:
return NULL;
LOG_FATALF("serialize.c", "FIXME: Unknown meta key: %d", meta_key)
}
}
@ -183,7 +199,7 @@ void write_document(document_t *doc) {
meta_line_t *meta = doc->meta_head;
while (meta != NULL) {
dyn_buffer_write_char(&buf, meta->key);
dyn_buffer_write_short(&buf, (uint16_t) meta->key);
if (IS_META_INT(meta->key)) {
dyn_buffer_write_int(&buf, meta->int_val);
@ -197,7 +213,7 @@ void write_document(document_t *doc) {
meta = meta->next;
free(tmp);
}
dyn_buffer_write_char(&buf, '\n');
dyn_buffer_write_short(&buf, META_NEXT);
int res = write(index_fd, buf.buf, buf.cur);
if (res == -1) {
@ -221,7 +237,7 @@ void read_index_bin(const char *path, const char *index_id, index_func func) {
FILE *file = fopen(path, "rb");
while (TRUE) {
buf.cur = 0;
size_t _ = fread((void *) &line, 1, sizeof(line_t), file);
size_t _ = fread((void *) &line, sizeof(line_t), 1, file);
if (feof(file)) {
break;
}
@ -268,9 +284,10 @@ void read_index_bin(const char *path, const char *index_id, index_func func) {
cJSON_AddStringToObject(document, "path", "");
}
enum metakey key = getc(file);
size_t ret = 0;
while (key != '\n') {
enum metakey key = 0;
fread(&key, sizeof(uint16_t), 1, file);
size_t ret;
while (key != META_NEXT) {
switch (key) {
case MetaPages:
case MetaWidth:
@ -308,6 +325,12 @@ void read_index_bin(const char *path, const char *index_id, index_func func) {
case MetaAuthor:
case MetaModifiedBy:
case MetaThumbnail:
case MetaExifGpsLongitudeDMS:
case MetaExifGpsLongitudeDec:
case MetaExifGpsLongitudeRef:
case MetaExifGpsLatitudeDMS:
case MetaExifGpsLatitudeDec:
case MetaExifGpsLatitudeRef:
case MetaTitle: {
buf.cur = 0;
while ((c = getc(file)) != 0) {
@ -323,7 +346,7 @@ void read_index_bin(const char *path, const char *index_id, index_func func) {
LOG_FATALF("serialize.c", "Invalid meta key (corrupt index): %x", key)
}
key = getc(file);
fread(&key, sizeof(uint16_t), 1, file);
}
cJSON *meta_obj = NULL;
@ -458,7 +481,7 @@ void incremental_read(GHashTable *table, const char *filepath) {
incremental_put(table, line.path_md5, line.mtime);
while ((getc(file))) {}
while ((getc(file)) != 0) {}
skip_meta(file);
}
fclose(file);
@ -508,11 +531,11 @@ void incremental_copy(store_t *store, store_t *dst_store, const char *filepath,
free(buf);
}
enum metakey key;
enum metakey key = 0;
while (1) {
key = getc(file);
fwrite(&key, sizeof(char), 1, dst_file);
if (key == '\n') {
fread(&key, sizeof(uint16_t), 1, file);
fwrite(&key, sizeof(uint16_t), 1, dst_file);
if (key == META_NEXT) {
break;
}

View File

@ -4,6 +4,7 @@
store_t *store_create(char *path, size_t chunk_size) {
store_t *store = malloc(sizeof(struct store_t));
#if (SIST_FAKE_STORE != 1)
store->chunk_size = chunk_size;
pthread_rwlock_init(&store->lock, NULL);
@ -28,15 +29,18 @@ store_t *store_create(char *path, size_t chunk_size) {
mdb_txn_begin(store->env, NULL, 0, &txn);
mdb_dbi_open(txn, NULL, 0, &store->dbi);
mdb_txn_commit(txn);
#endif
return store;
}
void store_destroy(store_t *store) {
#if (SIST_FAKE_STORE != 1)
pthread_rwlock_destroy(&store->lock);
mdb_close(store->env, store->dbi);
mdb_env_close(store->env);
#endif
free(store);
}
@ -56,6 +60,8 @@ void store_write(store_t *store, char *key, size_t key_len, char *buf, size_t bu
}
}
#if (SIST_FAKE_STORE != 1)
MDB_val mdb_key;
mdb_key.mv_data = key;
mdb_key.mv_size = key_len;
@ -92,10 +98,13 @@ void store_write(store_t *store, char *key, size_t key_len, char *buf, size_t bu
if (put_ret != 0) {
LOG_ERROR("store.c", mdb_strerror(put_ret))
}
#endif
}
char *store_read(store_t *store, char *key, size_t key_len, size_t *ret_vallen) {
char *buf = NULL;
#if (SIST_FAKE_STORE != 1)
MDB_val mdb_key;
mdb_key.mv_data = key;
mdb_key.mv_size = key_len;
@ -116,6 +125,7 @@ char *store_read(store_t *store, char *key, size_t key_len, size_t *ret_vallen)
}
mdb_txn_abort(txn);
#endif
return buf;
}

View File

@ -21,7 +21,7 @@
#define EPILOG "Made by simon987 <me@simon987.net>. Released under GPL-3.0"
static const char *const Version = "2.9.0";
static const char *const Version = "2.10.1";
static const char *const usage[] = {
"sist2 scan [OPTION]... PATH",
"sist2 index [OPTION]... INDEX",
@ -30,6 +30,69 @@ static const char *const usage[] = {
NULL,
};
#include<signal.h>
#include<unistd.h>
static __sighandler_t sigsegv_handler = NULL;
static __sighandler_t sigabrt_handler = NULL;
void sig_handler(int signum) {
LogCtx.verbose = 1;
LogCtx.very_verbose = 1;
LOG_ERROR("*SIGNAL HANDLER*", "=============================================\n\n");
LOG_ERRORF("*SIGNAL HANDLER*", "Uh oh! Caught fatal signal: %s", strsignal(signum));
GHashTableIter iter;
g_hash_table_iter_init(&iter, ScanCtx.dbg_current_files);
void *key;
void *value;
while (g_hash_table_iter_next(&iter, &key, &value)) {
parse_job_t *job = value;
if (isatty(STDERR_FILENO)) {
LOG_DEBUGF(
"*SIGNAL HANDLER*",
"Thread \033[%dm[%04llX]\033[0m was working on job '%s'",
31 + ((unsigned int) key) % 7, key, job->filepath
);
} else {
LOG_DEBUGF(
"*SIGNAL HANDLER*",
"THREAD [%04llX] was working on job %s",
key, job->filepath
);
}
}
tpool_dump_debug_info(ScanCtx.pool);
LOG_INFO(
"*SIGNAL HANDLER*",
"Please consider creating a bug report at https://github.com/simon987/sist2/issues !"
)
LOG_INFO(
"*SIGNAL HANDLER*",
"sist2 is an open source project and relies on the collaboration of its users to diagnose and fix bugs"
)
#ifndef SIST_DEBUG
LOG_WARNING(
"*SIGNAL HANDLER*",
"You are running sist2 in release mode! Please consider downloading the debug binary from the Github "
"releases page to provide additionnal information when submitting a bug report."
)
#endif
if (signum == SIGSEGV && sigsegv_handler != NULL) {
sigsegv_handler(signum);
} else if (signum == SIGABRT && sigabrt_handler != NULL) {
sigabrt_handler(signum);
}
}
void init_dir(const char *dirpath) {
char path[PATH_MAX];
snprintf(path, PATH_MAX, "%sdescriptor.json", dirpath);
@ -99,6 +162,13 @@ void initialize_scan_context(scan_args_t *args) {
ScanCtx.arc_ctx.log = _log;
ScanCtx.arc_ctx.logf = _logf;
ScanCtx.arc_ctx.parse = (parse_callback_t) parse;
if (args->archive_passphrase != NULL) {
strcpy(ScanCtx.arc_ctx.passphrase, args->archive_passphrase);
} else {
ScanCtx.arc_ctx.passphrase[0] = 0;
}
ScanCtx.dbg_current_files = g_hash_table_new(g_int64_hash, g_int64_equal);
// Comic
ScanCtx.comic_ctx.log = _log;
@ -132,6 +202,7 @@ void initialize_scan_context(scan_args_t *args) {
ScanCtx.media_ctx.logf = _logf;
ScanCtx.media_ctx.store = _store;
ScanCtx.media_ctx.max_media_buffer = (long) args->max_memory_buffer * 1024 * 1024;
ScanCtx.media_ctx.read_subtitles = args->read_subtitles;
init_media();
// OOXML
@ -399,6 +470,9 @@ void sist2_web(web_args_t *args) {
int main(int argc, const char *argv[]) {
sigsegv_handler = signal(SIGSEGV, sig_handler);
sigabrt_handler = signal(SIGABRT, sig_handler);
setlocale(LC_ALL, "");
scan_args_t *scan_args = scan_args_create();
@ -439,6 +513,9 @@ int main(int argc, const char *argv[]) {
OPT_STRING(0, "archive", &scan_args->archive, "Archive file mode (skip|list|shallow|recurse). "
"skip: Don't parse, list: only get file names as text, "
"shallow: Don't parse archives inside archives. DEFAULT: recurse"),
OPT_STRING(0, "archive-passphrase", &scan_args->archive_passphrase,
"Passphrase for encrypted archive files"),
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"),
@ -448,6 +525,7 @@ int main(int argc, const char *argv[]) {
OPT_INTEGER(0, "mem-buffer", &scan_args->max_memory_buffer,
"Maximum memory buffer size per thread in MB for files inside archives "
"(see USAGE.md). DEFAULT: 2000"),
OPT_BOOLEAN(0, "read-subtitles", &scan_args->read_subtitles, "Read subtitles from media files."),
OPT_GROUP("Index options"),
OPT_INTEGER('t', "threads", &common_threads, "Number of threads. DEFAULT=1"),

View File

@ -41,11 +41,18 @@ void fs_reset(struct vfile *f) {
#define IS_GIT_OBJ (strlen(doc.filepath + doc.base) == 38 && (strstr(doc.filepath, "objects") != NULL))
void set_dbg_current_file(parse_job_t *job) {
unsigned long long pid = (unsigned long long) pthread_self();
g_hash_table_replace(ScanCtx.dbg_current_files, GINT_TO_POINTER(pid), job);
}
void parse(void *arg) {
parse_job_t *job = arg;
document_t doc;
set_dbg_current_file(job);
doc.filepath = job->filepath;
doc.ext = (short) job->ext;
doc.base = (short) job->base;

View File

@ -192,6 +192,19 @@ function makeUserTag(tag, hit) {
return userTag;
}
function makeGpsMetaRow(tbody, latitude, longitude) {
tbody.append($("<tr>")
.append($("<td>").text("Exif GPS"))
.append($("<td>")
.append($("<a>")
.text(`${latitude}, ${longitude}`)
.attr("href", `https://maps.google.com/?q=${latitude},${longitude}&ll=${latitude},${longitude}&t=k&z=17`)
.attr("target", "_blank")
)
)
);
}
function infoButtonCb(hit) {
return () => {
getDocumentInfo(hit["_id"]).then(doc => {
@ -229,13 +242,25 @@ function infoButtonCb(hit) {
.text(new Date(doc["mtime"] * 1000).toISOString().split(".")[0].replace("T", " "))
.attr("title", doc["mtime"]))
);
// Exif GPS
if ("exif_gps_longitude_dec" in doc) {
makeGpsMetaRow(tbody, doc["exif_gps_latitude_dec"], doc["exif_gps_longitude_dec"])
} else if ("exif_gps_longitude_dms" in doc) {
makeGpsMetaRow(
tbody,
dmsToDecimal(doc["exif_gps_latitude_dms"], doc["exif_gps_latitude_ref"]),
dmsToDecimal(doc["exif_gps_longitude_dms"], doc["exif_gps_longitude_ref"]),
)
}
const displayFields = new Set([
"mime", "size", "path", "title", "width", "height", "duration", "audioc", "videoc",
"bitrate", "artist", "album", "album_artist", "genre", "title", "font_name", "tag", "author",
"modified_by", "pages"
]);
Object.keys(doc)
.filter(key => key.startsWith("_keyword.") || key.startsWith("_text.") || displayFields.has(key) || key.startsWith("exif_"))
.filter(key => key.startsWith("_keyword.") || key.startsWith("_text.") || displayFields.has(key) || (key.startsWith("exif_") && !key.includes("gps")))
.forEach(key => {
tbody.append($("<tr>")
.append($("<td>").text(key))
@ -350,6 +375,14 @@ function createDocCard(hit) {
audio.setAttribute("controls", "");
audio.setAttribute("type", hit["_source"]["mime"]);
audio.setAttribute("src", "f/" + hit["_id"]);
audio.addEventListener("play", () => {
// Pause all currently playing audio tags
$("audio").each(function () {
if (this !== audio) {
this.pause();
}
});
});
docCard.appendChild(audio)
}

View File

@ -511,8 +511,8 @@ function search(after = null) {
searchResults.appendChild(preload);
}
let query = searchBar.value;
let empty = query === "";
let searchBarValue = searchBar.value;
let empty = searchBarValue === "";
let condition = empty ? "should" : "must";
let filters = [
{range: {size: {gte: size_min, lte: size_max}}},
@ -561,19 +561,32 @@ function search(after = null) {
filters.push({range: {mtime: {lte: date_max}}})
}
let query;
if (CONF.options.queryMode === "simple") {
query = {
simple_query_string: {
query: searchBarValue,
fields: fields,
default_operator: "and"
}
}
} else {
query = {
query_string: {
query: searchBarValue,
default_field: "name",
default_operator: "and"
}
}
}
let q = {
"_source": {
excludes: ["content", "_tie"]
},
query: {
bool: {
[condition]: {
simple_query_string: {
query: query,
fields: fields,
default_operator: "and"
}
},
[condition]: query,
filter: filters
}
},
@ -611,7 +624,9 @@ function search(after = null) {
}
}
$.jsonPost("es", q).then(searchResult => {
const showError = CONF.options.queryMode === "advanced";
$.jsonPost("es", q, showError).then(searchResult => {
let hits = searchResult["hits"]["hits"];
if (hits) {
lastDoc = hits[hits.length - 1];
@ -645,7 +660,25 @@ function search(after = null) {
reachedEnd = hits.length !== SIZE;
insertHits(resultContainer, hits);
searchBusy = false;
});
}).fail(() => {
searchBusy = false;
if (!after) {
preload.remove();
}
console.log("QUERY:")
console.log(q)
$.toast({
heading: "Query error",
text: "Could not parse or execute query, please check the Advanced search documentation. " +
"See server logs for more information.",
stack: false,
bgColor: "#FF8F00",
textColor: "#FFF3E0",
position: 'bottom-right',
hideAfter: false
});
})
}

View File

@ -70,7 +70,7 @@ function strUnescape(str) {
for (let i = 0; i < str.length; i++) {
const c = str[i];
const next = str[i+1];
const next = str[i + 1];
if (c === ']') {
if (next === ']') {
@ -102,7 +102,8 @@ const _defaults = {
treemapSize: "large",
suggestPath: true,
fragmentSize: 100,
columns: 5
columns: 5,
queryMode: "simple"
};
function loadSettings() {
@ -120,6 +121,7 @@ function loadSettings() {
$("#settingSuggestPath").prop("checked", CONF.options.suggestPath);
$("#settingFragmentSize").val(CONF.options.fragmentSize);
$("#settingColumns").val(CONF.options.columns);
$("#settingQueryMode").val(CONF.options.queryMode);
}
function Settings() {
@ -127,6 +129,7 @@ function Settings() {
this._onUpdate = function () {
$("#fuzzyToggle").prop("checked", this.options.fuzzy);
$("#searchBar").attr("placeholder", this.options.queryMode === "simple" ? "Search" : "Advanced search");
updateColumnStyle();
};
@ -165,6 +168,7 @@ function updateSettings() {
CONF.options.suggestPath = $("#settingSuggestPath").prop("checked");
CONF.options.fragmentSize = $("#settingFragmentSize").val();
CONF.options.columns = $("#settingColumns").val();
CONF.options.queryMode = $("#settingQueryMode").val();
CONF.save();
if (typeof searchDebounced !== "undefined") {
@ -187,14 +191,16 @@ function updateSettings() {
});
}
jQuery["jsonPost"] = function (url, data) {
jQuery["jsonPost"] = function (url, data, showError = true) {
return jQuery.ajax({
url: url,
type: "post",
data: JSON.stringify(data),
contentType: "application/json"
}).fail(err => {
showEsError();
if (showError) {
showEsError();
}
console.log(err);
});
};
@ -212,7 +218,7 @@ function updateColumnStyle() {
const style = document.getElementById("style");
if (style) {
style.innerHTML =
`
`
@media screen and (min-width: 1500px) {
.container {
max-width: 1440px;
@ -230,3 +236,13 @@ function updateColumnStyle() {
`
}
}
function dmsToDecimal(dms, ref) {
const tokens = dms.split(",")
const d = Number(tokens[0].trim().split(":")[0]) / Number(tokens[0].trim().split(":")[1])
const m = Number(tokens[1].trim().split(":")[0]) / Number(tokens[1].trim().split(":")[1])
const s = Number(tokens[2].trim().split(":")[0]) / Number(tokens[2].trim().split(":")[1])
return (d + (m / 60) + (s / 3600)) * (ref === "S" || ref === "W" ? -1 : 1)
}

View File

@ -12,7 +12,7 @@
<nav class="navbar navbar-expand-lg">
<a class="navbar-brand" href="/">sist2</a>
<span class="badge badge-pill version">2.9.0</span>
<span class="badge badge-pill version">2.10.1</span>
<span class="tagline">Lightning-fast file system indexer and search tool </span>
<a class="btn ml-auto" href="stats">Stats</a>
<button class="btn" type="button" data-toggle="modal" data-target="#settings" onclick="loadSettings()">Settings
@ -120,6 +120,8 @@
</div>
<div class="modal-body">
<h2>Simple search</h2>
<table class="table">
<tbody>
<tr>
@ -168,6 +170,12 @@
<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>
<h2>Advanced search</h2>
<p>For documentation about the advanced search mode, see <a target="_blank"
href="//www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl-query-string-query.html#query-string-syntax">Elasticsearch
documentation</a></p>
</div>
</div>
</div>
@ -207,10 +215,16 @@
<br/>
<div class="form-group">
<input type="number" class="form-control" id="settingFragmentSize">
<label for="settingFragmentSize">Highlight context size in characters</label>
<input type="number" class="form-control" id="settingFragmentSize">
</div>
<label for="settingQueryMode">Search mode</label>
<select id="settingQueryMode" class="form-control form-control-sm">
<option value="simple">Simple</option>
<option value="advanced">Advanced</option>
</select>
<label for="settingDisplay">Display</label>
<select id="settingDisplay" class="form-control form-control-sm">
<option value="grid">Grid</option>

View File

@ -10,7 +10,7 @@
<nav class="navbar navbar-expand-lg">
<a class="navbar-brand" href="/">sist2</a>
<span class="badge badge-pill version">2.9.0</span>
<span class="badge badge-pill version">2.10.1</span>
<span class="tagline">Lightning-fast file system indexer and search tool </span>
<a style="margin-left: auto" class="btn" href="/">Back</a>
<button class="btn" type="button" data-toggle="modal" data-target="#settings"
@ -84,10 +84,16 @@
<br/>
<div class="form-group">
<input type="number" class="form-control" id="settingFragmentSize">
<label for="settingFragmentSize">Highlight context size in characters</label>
<input type="number" class="form-control" id="settingFragmentSize">
</div>
<label for="settingQueryMode">Search mode</label>
<select id="settingQueryMode" class="form-control form-control-sm">
<option value="simple">Simple</option>
<option value="advanced">Advanced</option>
</select>
<label for="settingDisplay">Display</label>
<select id="settingDisplay" class="form-control form-control-sm">
<option value="grid">Grid</option>

View File

@ -3,7 +3,7 @@
#include "sist.h"
#include <pthread.h>
#define MAX_QUEUE_SIZE 10000
#define MAX_QUEUE_SIZE 1000000
typedef void (*thread_func_t)(void *arg);
@ -52,6 +52,13 @@ static tpool_work_t *tpool_work_create(thread_func_t func, void *arg) {
return work;
}
void tpool_dump_debug_info(tpool_t *pool) {
LOG_DEBUGF("tpool.c", "pool->thread_cnt = %d", pool->thread_cnt)
LOG_DEBUGF("tpool.c", "pool->work_cnt = %d", pool->work_cnt)
LOG_DEBUGF("tpool.c", "pool->done_cnt = %d", pool->done_cnt)
LOG_DEBUGF("tpool.c", "pool->stop = %d", pool->stop)
}
/**
* Pop work object from thread pool
*/
@ -83,7 +90,7 @@ int tpool_add_work(tpool_t *pool, thread_func_t func, void *arg) {
}
while ((pool->work_cnt - pool->done_cnt) >= MAX_QUEUE_SIZE) {
usleep(100000);
usleep(10000);
}
pthread_mutex_lock(&(pool->work_mutex));
@ -150,6 +157,7 @@ static void *tpool_worker(void *arg) {
if (pool->cleanup_func != NULL) {
LOG_INFO("tpool.c", "Executing cleanup function")
pool->cleanup_func();
LOG_DEBUG("tpool.c", "Done executing cleanup function")
}
pthread_cond_signal(&(pool->working_cond));

View File

@ -10,10 +10,12 @@ typedef void (*thread_func_t)(void *arg);
tpool_t *tpool_create(size_t num, void (*cleanup_func)(), int free_arg);
void tpool_start(tpool_t *pool);
void tpool_destroy(tpool_t *tm);
void tpool_destroy(tpool_t *pool);
int tpool_add_work(tpool_t *pool, thread_func_t func, void *arg);
void tpool_wait(tpool_t *tm);
void tpool_wait(tpool_t *pool);
void tpool_dump_debug_info(tpool_t *pool);
#endif

View File

@ -8,18 +8,8 @@
#include <src/ctx.h>
#include <mongoose.h>
static int has_prefix(const struct mg_str *str, const struct mg_str *prefix) {
return str->len > prefix->len && memcmp(str->p, prefix->p, prefix->len) == 0;
}
static int is_equal(const struct mg_str *s1, const struct mg_str *s2) {
return s1->len == s2->len && memcmp(s1->p, s2->p, s2->len) == 0;
}
static void send_response_line(struct mg_connection *nc, int status_code, int length, char *extra_headers) {
static void send_response_line(struct mg_connection *nc, int status_code, size_t length, char *extra_headers) {
mg_printf(
nc,
"HTTP/1.1 %d %s\r\n"
@ -62,36 +52,32 @@ store_t *get_tag_store(const char *index_id) {
void search_index(struct mg_connection *nc) {
send_response_line(nc, 200, sizeof(search_html), "Content-Type: text/html");
mg_send(nc, search_html, sizeof(search_html));
nc->flags |= MG_F_SEND_AND_CLOSE;
}
void stats(struct mg_connection *nc) {
send_response_line(nc, 200, sizeof(stats_html), "Content-Type: text/html");
mg_send(nc, stats_html, sizeof(stats_html));
nc->flags |= MG_F_SEND_AND_CLOSE;
}
void stats_files(struct mg_connection *nc, struct http_message *hm, struct mg_str *path) {
void stats_files(struct mg_connection *nc, struct mg_http_message *hm) {
if (path->len != MD5_STR_LENGTH + 4) {
mg_http_send_error(nc, 404, NULL);
nc->flags |= MG_F_SEND_AND_CLOSE;
if (hm->uri.len != MD5_STR_LENGTH + 4) {
mg_http_reply(nc, 404, "", "");
return;
}
char arg_md5[MD5_STR_LENGTH];
memcpy(arg_md5, hm->uri.p + 3, MD5_STR_LENGTH);
memcpy(arg_md5, hm->uri.ptr + 3, MD5_STR_LENGTH);
*(arg_md5 + MD5_STR_LENGTH - 1) = '\0';
index_t *index = get_index_by_id(arg_md5);
if (index == NULL) {
mg_http_send_error(nc, 404, NULL);
nc->flags |= MG_F_SEND_AND_CLOSE;
mg_http_reply(nc, 404, "", "");
return;
}
const char *file;
switch (atoi(hm->uri.p + 3 + MD5_STR_LENGTH)) {
switch (atoi(hm->uri.ptr + 3 + MD5_STR_LENGTH)) {
case 1:
file = "treemap.csv";
break;
@ -105,54 +91,41 @@ void stats_files(struct mg_connection *nc, struct http_message *hm, struct mg_st
file = "date_agg.csv";
break;
default:
nc->flags |= MG_F_SEND_AND_CLOSE;
return;
}
char disposition[8192];
snprintf(disposition, sizeof(disposition), "Content-Disposition: inline; filename=\"%s\"", file);
snprintf(disposition, sizeof(disposition), "Content-Disposition: inline; filename=\"%s\"\r\n", file);
char full_path[PATH_MAX];
strcpy(full_path, index->path);
strcat(full_path, file);
mg_http_serve_file(nc, hm, full_path, mg_mk_str("text/csv"), mg_mk_str(disposition));
nc->flags |= MG_F_SEND_AND_CLOSE;
mg_http_serve_file(nc, hm, full_path, "text/csv", disposition);
}
void javascript_lib(struct mg_connection *nc) {
send_response_line(nc, 200, sizeof(bundle_js), "Content-Type: application/javascript");
mg_send(nc, bundle_js, sizeof(bundle_js));
nc->flags |= MG_F_SEND_AND_CLOSE;
}
void javascript_search(struct mg_connection *nc) {
send_response_line(nc, 200, sizeof(search_js), "Content-Type: application/javascript");
mg_send(nc, search_js, sizeof(search_js));
nc->flags |= MG_F_SEND_AND_CLOSE;
}
int client_requested_dark_theme(struct http_message *hm) {
struct mg_str *cookie_header = mg_get_http_header(hm, "cookie");
int client_requested_dark_theme(struct mg_http_message *hm) {
struct mg_str *cookie_header = mg_http_get_header(hm, "cookie");
if (cookie_header == NULL) {
return FALSE;
}
char buf[4096];
char *sist_cookie = buf;
if (mg_http_parse_header2(cookie_header, "sist", &sist_cookie, sizeof(buf)) == 0) {
return FALSE;
}
struct mg_str sist_cookie = mg_http_get_header_var(*cookie_header, mg_str_n("sist", 4));
int ret = strcmp(sist_cookie, "dark") == 0;
if (sist_cookie != buf) {
free(sist_cookie);
}
return ret;
return mg_strcmp(sist_cookie, mg_str_n("dark", 4)) == 0;
}
void style(struct mg_connection *nc, struct http_message *hm) {
void style(struct mg_connection *nc, struct mg_http_message *hm) {
if (client_requested_dark_theme(hm)) {
send_response_line(nc, 200, sizeof(bundle_dark_css), "Content-Type: text/css");
@ -161,11 +134,9 @@ void style(struct mg_connection *nc, struct http_message *hm) {
send_response_line(nc, 200, sizeof(bundle_css), "Content-Type: text/css");
mg_send(nc, bundle_css, sizeof(bundle_css));
}
nc->flags |= MG_F_SEND_AND_CLOSE;
}
void img_sprite_skin_flat(struct mg_connection *nc, struct http_message *hm) {
void img_sprite_skin_flat(struct mg_connection *nc, struct mg_http_message *hm) {
if (client_requested_dark_theme(hm)) {
send_response_line(nc, 200, sizeof(sprite_skin_flat_dark_png), "Content-Type: image/png");
mg_send(nc, sprite_skin_flat_dark_png, sizeof(sprite_skin_flat_dark_png));
@ -173,25 +144,22 @@ void img_sprite_skin_flat(struct mg_connection *nc, struct http_message *hm) {
send_response_line(nc, 200, sizeof(sprite_skin_flat_png), "Content-Type: image/png");
mg_send(nc, sprite_skin_flat_png, sizeof(sprite_skin_flat_png));
}
nc->flags |= MG_F_SEND_AND_CLOSE;
}
void thumbnail(struct mg_connection *nc, struct http_message *hm, struct mg_str *path) {
void thumbnail(struct mg_connection *nc, struct mg_http_message *hm) {
if (path->len != 68) {
LOG_DEBUGF("serve.c", "Invalid thumbnail path: %.*s", (int) path->len, path->p)
mg_http_send_error(nc, 404, NULL);
nc->flags |= MG_F_SEND_AND_CLOSE;
if (hm->uri.len != 68) {
LOG_DEBUGF("serve.c", "Invalid thumbnail path: %.*s", (int) hm->uri.len, hm->uri.ptr)
mg_http_reply(nc, 404, "", "Not found");
return;
}
char arg_file_md5[MD5_STR_LENGTH];
char arg_index[MD5_STR_LENGTH];
memcpy(arg_index, hm->uri.p + 3, MD5_STR_LENGTH);
memcpy(arg_index, hm->uri.ptr + 3, MD5_STR_LENGTH);
*(arg_index + MD5_STR_LENGTH - 1) = '\0';
memcpy(arg_file_md5, hm->uri.p + 3 + MD5_STR_LENGTH, MD5_STR_LENGTH);
memcpy(arg_file_md5, hm->uri.ptr + 3 + MD5_STR_LENGTH, MD5_STR_LENGTH);
*(arg_file_md5 + MD5_STR_LENGTH - 1) = '\0';
unsigned char md5_buf[MD5_DIGEST_LENGTH];
@ -200,8 +168,7 @@ void thumbnail(struct mg_connection *nc, struct http_message *hm, struct mg_str
store_t *store = get_store(arg_index);
if (store == NULL) {
LOG_DEBUGF("serve.c", "Could not get store for index: %s", arg_index)
mg_http_send_error(nc, 404, NULL);
nc->flags |= MG_F_SEND_AND_CLOSE;
mg_http_reply(nc, 404, "", "Not found");
return;
}
@ -212,26 +179,24 @@ void thumbnail(struct mg_connection *nc, struct http_message *hm, struct mg_str
mg_send(nc, data, data_len);
free(data);
}
nc->flags |= MG_F_SEND_AND_CLOSE;
}
void search(struct mg_connection *nc, struct http_message *hm) {
void search(struct mg_connection *nc, struct mg_http_message *hm) {
if (hm->body.len == 0) {
LOG_DEBUG("serve.c", "Client sent empty body, ignoring request")
mg_http_send_error(nc, 500, NULL);
nc->flags |= MG_F_SEND_AND_CLOSE;
mg_http_reply(nc, 500, "", "Invalid request");
return;
}
char *body = malloc(hm->body.len + 1);
memcpy(body, hm->body.p, hm->body.len);
memcpy(body, hm->body.ptr, hm->body.len);
*(body + hm->body.len) = '\0';
char url[4096];
snprintf(url, 4096, "%s/%s/_search", WebCtx.es_url, WebCtx.es_index);
nc->user_data = web_post_async(url, body);
nc->fn_data = web_post_async(url, body);
}
void serve_file_from_url(cJSON *json, index_t *idx, struct mg_connection *nc) {
@ -253,16 +218,13 @@ void serve_file_from_url(cJSON *json, index_t *idx, struct mg_connection *nc) {
idx->desc.rewrite_url, path_unescaped, name_unescaped, strlen(ext) == 0 ? "" : ".", ext);
dyn_buffer_t encoded = url_escape(url);
mg_http_send_redirect(
nc, 308,
(struct mg_str) MG_MK_STR_N(encoded.buf, encoded.cur),
(struct mg_str) MG_NULL_STR
);
dyn_buffer_write_char(&encoded, '\0');
mg_http_reply(nc, 308, "Location: %s", encoded.buf);
dyn_buffer_destroy(&encoded);
nc->flags |= MG_F_SEND_AND_CLOSE;
}
void serve_file_from_disk(cJSON *json, index_t *idx, struct mg_connection *nc, struct http_message *hm) {
void serve_file_from_disk(cJSON *json, index_t *idx, struct mg_connection *nc, struct mg_http_message *hm) {
const char *path = cJSON_GetObjectItem(json, "path")->valuestring;
const char *name = cJSON_GetObjectItem(json, "name")->valuestring;
@ -283,10 +245,10 @@ void serve_file_from_disk(cJSON *json, index_t *idx, struct mg_connection *nc, s
LOG_DEBUGF("serve.c", "Serving file from disk: %s", full_path)
char disposition[8192];
snprintf(disposition, sizeof(disposition), "Content-Disposition: inline; filename=\"%s%s%s\"",
snprintf(disposition, sizeof(disposition), "Content-Disposition: inline; filename=\"%s%s%s\"\r\n",
name, strlen(ext) == 0 ? "" : ".", ext);
mg_http_serve_file(nc, hm, full_path, mg_mk_str(mime), mg_mk_str(disposition));
mg_http_serve_file(nc, hm, full_path, mime, disposition);
}
void index_info(struct mg_connection *nc) {
@ -310,22 +272,19 @@ void index_info(struct mg_connection *nc) {
mg_send(nc, json_str, strlen(json_str));
free(json_str);
cJSON_Delete(json);
nc->flags |= MG_F_SEND_AND_CLOSE;
}
void document_info(struct mg_connection *nc, struct http_message *hm, struct mg_str *path) {
void document_info(struct mg_connection *nc, struct mg_http_message *hm) {
if (path->len != MD5_STR_LENGTH + 2) {
LOG_DEBUGF("serve.c", "Invalid document_info path: %.*s", (int) path->len, path->p)
mg_http_send_error(nc, 404, NULL);
nc->flags |= MG_F_SEND_AND_CLOSE;
if (hm->uri.len != MD5_STR_LENGTH + 2) {
LOG_DEBUGF("serve.c", "Invalid document_info path: %.*s", (int) hm->uri.len, hm->uri.ptr)
mg_http_reply(nc, 404, "", "Not found");
return;
}
char arg_md5[MD5_STR_LENGTH];
memcpy(arg_md5, hm->uri.p + 3, MD5_STR_LENGTH);
memcpy(arg_md5, hm->uri.ptr + 3, MD5_STR_LENGTH);
*(arg_md5 + MD5_STR_LENGTH - 1) = '\0';
cJSON *doc = elastic_get_document(arg_md5);
@ -334,16 +293,14 @@ void document_info(struct mg_connection *nc, struct http_message *hm, struct mg_
cJSON *index_id = cJSON_GetObjectItem(source, "index");
if (index_id == NULL) {
cJSON_Delete(doc);
mg_http_send_error(nc, 404, NULL);
nc->flags |= MG_F_SEND_AND_CLOSE;
mg_http_reply(nc, 404, "", "Not found");
return;
}
index_t *idx = get_index_by_id(index_id->valuestring);
if (idx == NULL) {
cJSON_Delete(doc);
mg_http_send_error(nc, 404, NULL);
nc->flags |= MG_F_SEND_AND_CLOSE;
mg_http_reply(nc, 404, "", "Not found");
return;
}
@ -352,21 +309,18 @@ void document_info(struct mg_connection *nc, struct http_message *hm, struct mg_
mg_send(nc, json_str, (int) strlen(json_str));
free(json_str);
cJSON_Delete(doc);
nc->flags |= MG_F_SEND_AND_CLOSE;
}
void file(struct mg_connection *nc, struct http_message *hm, struct mg_str *path) {
void file(struct mg_connection *nc, struct mg_http_message *hm) {
if (path->len != MD5_STR_LENGTH + 2) {
LOG_DEBUGF("serve.c", "Invalid file path: %.*s", (int) path->len, path->p)
mg_http_send_error(nc, 404, NULL);
nc->flags |= MG_F_SEND_AND_CLOSE;
if (hm->uri.len != MD5_STR_LENGTH + 2) {
LOG_DEBUGF("serve.c", "Invalid file path: %.*s", (int) hm->uri.len, hm->uri.ptr)
mg_http_reply(nc, 404, "", "Not found");
return;
}
char arg_md5[MD5_STR_LENGTH];
memcpy(arg_md5, hm->uri.p + 3, MD5_STR_LENGTH);
memcpy(arg_md5, hm->uri.ptr + 3, MD5_STR_LENGTH);
*(arg_md5 + MD5_STR_LENGTH - 1) = '\0';
const char *next = arg_md5;
@ -380,8 +334,7 @@ void file(struct mg_connection *nc, struct http_message *hm, struct mg_str *path
index_id = cJSON_GetObjectItem(source, "index");
if (index_id == NULL) {
cJSON_Delete(doc);
mg_http_send_error(nc, 404, NULL);
nc->flags |= MG_F_SEND_AND_CLOSE;
mg_http_reply(nc, 404, "", "Not found");
return;
}
cJSON *parent = cJSON_GetObjectItem(source, "parent");
@ -395,8 +348,7 @@ void file(struct mg_connection *nc, struct http_message *hm, struct mg_str *path
if (idx == NULL) {
cJSON_Delete(doc);
nc->flags |= MG_F_SEND_AND_CLOSE;
mg_http_send_error(nc, 404, NULL);
mg_http_reply(nc, 404, "", "Not found");
return;
}
@ -417,8 +369,6 @@ void status(struct mg_connection *nc) {
}
free(status);
nc->flags |= MG_F_SEND_AND_CLOSE;
}
typedef struct {
@ -464,35 +414,32 @@ tag_req_t *parse_tag_request(cJSON *json) {
return req;
}
void tag(struct mg_connection *nc, struct http_message *hm, struct mg_str *path) {
if (path->len != MD5_STR_LENGTH + 4) {
LOG_DEBUGF("serve.c", "Invalid tag path: %.*s", (int) path->len, path->p)
mg_http_send_error(nc, 404, NULL);
nc->flags |= MG_F_SEND_AND_CLOSE;
void tag(struct mg_connection *nc, struct mg_http_message *hm) {
if (hm->uri.len != MD5_STR_LENGTH + 4) {
LOG_DEBUGF("serve.c", "Invalid tag path: %.*s", (int) hm->uri.len, hm->uri.ptr)
mg_http_reply(nc, 404, "", "Not found");
return;
}
char arg_index[MD5_STR_LENGTH];
memcpy(arg_index, hm->uri.p + 5, MD5_STR_LENGTH);
memcpy(arg_index, hm->uri.ptr + 5, MD5_STR_LENGTH);
*(arg_index + MD5_STR_LENGTH - 1) = '\0';
if (hm->body.len < 2 || hm->method.len != 4 || memcmp(&hm->method, "POST", 4) == 0) {
LOG_DEBUG("serve.c", "Invalid tag request")
mg_http_send_error(nc, 400, NULL);
nc->flags |= MG_F_SEND_AND_CLOSE;
mg_http_reply(nc, 404, "", "Not found");
return;
}
store_t *store = get_tag_store(arg_index);
if (store == NULL) {
LOG_DEBUGF("serve.c", "Could not get tag store for index: %s", arg_index)
mg_http_send_error(nc, 404, NULL);
nc->flags |= MG_F_SEND_AND_CLOSE;
mg_http_reply(nc, 404, "", "Not found");
return;
}
char *body = malloc(hm->body.len + 1);
memcpy(body, hm->body.p, hm->body.len);
memcpy(body, hm->body.ptr, hm->body.len);
*(body + hm->body.len) = '\0';
cJSON *json = cJSON_Parse(body);
@ -501,8 +448,7 @@ void tag(struct mg_connection *nc, struct http_message *hm, struct mg_str *path)
LOG_DEBUGF("serve.c", "Could not parse tag request", arg_index)
cJSON_Delete(json);
free(body);
mg_http_send_error(nc, 400, NULL);
nc->flags |= MG_F_SEND_AND_CLOSE;
mg_http_reply(nc, 400, "", "Invalid request");
return;
}
@ -545,7 +491,7 @@ void tag(struct mg_connection *nc, struct http_message *hm, struct mg_str *path)
char url[4096];
snprintf(url, sizeof(url), "%s/%s/_update/%s", WebCtx.es_url, WebCtx.es_index, arg_req->doc_id);
nc->user_data = web_post_async(url, buf);
nc->fn_data = web_post_async(url, buf);
} else {
cJSON_AddItemToArray(arr, cJSON_CreateString(arg_req->name));
@ -565,7 +511,7 @@ void tag(struct mg_connection *nc, struct http_message *hm, struct mg_str *path)
char url[4096];
snprintf(url, sizeof(url), "%s/%s/_update/%s", WebCtx.es_url, WebCtx.es_index, arg_req->doc_id);
nc->user_data = web_post_async(url, buf);
nc->fn_data = web_post_async(url, buf);
}
char *json_str = cJSON_PrintUnformatted(arr);
@ -579,92 +525,73 @@ void tag(struct mg_connection *nc, struct http_message *hm, struct mg_str *path)
free(body);
}
int validate_auth(struct mg_connection *nc, struct http_message *hm) {
int validate_auth(struct mg_connection *nc, struct mg_http_message *hm) {
char user[256] = {0,};
char pass[256] = {0,};
int ret = mg_get_http_basic_auth(hm, user, sizeof(user), pass, sizeof(pass));
if (ret == -1 || strcmp(user, WebCtx.auth_user) != 0 || strcmp(pass, WebCtx.auth_pass) != 0) {
mg_printf(nc, "HTTP/1.1 401 Unauthorized\r\n"
"WWW-Authenticate: Basic realm=\"sist2\"\r\n"
"Content-Length: 0\r\n\r\n");
nc->flags |= MG_F_SEND_AND_CLOSE;
mg_http_creds(hm, user, sizeof(user), pass, sizeof(pass));
if (strcmp(user, WebCtx.auth_user) != 0 || strcmp(pass, WebCtx.auth_pass) != 0) {
mg_http_reply(nc, 401, "WWW-Authenticate: Basic realm=\"sist2\"", "");
return FALSE;
}
return TRUE;
}
static void ev_router(struct mg_connection *nc, int ev, void *p) {
struct mg_str scheme;
struct mg_str user_info;
struct mg_str host;
unsigned int port;
struct mg_str path;
struct mg_str query;
struct mg_str fragment;
if (ev == MG_EV_HTTP_REQUEST) {
struct http_message *hm = (struct http_message *) p;
if (mg_parse_uri(hm->uri, &scheme, &user_info, &host, &port, &path, &query, &fragment) != 0) {
mg_http_send_error(nc, 400, NULL);
nc->flags |= MG_F_SEND_AND_CLOSE;
return;
}
static void ev_router(struct mg_connection *nc, int ev, void *ev_data, UNUSED(void *fn_data)) {
if (ev == MG_EV_HTTP_MSG) {
struct mg_http_message *hm = (struct mg_http_message *) ev_data;
if (WebCtx.auth_enabled == TRUE) {
if (!validate_auth(nc, hm)) {
nc->is_closing = 1;
return;
}
}
if (is_equal(&path, &((struct mg_str) MG_MK_STR("/")))) {
if (mg_http_match_uri(hm, "/")) {
search_index(nc);
} else if (is_equal(&path, &((struct mg_str) MG_MK_STR("/css")))) {
} else if (mg_http_match_uri(hm, "/css")) {
style(nc, hm);
} else if (is_equal(&path, &((struct mg_str) MG_MK_STR("/stats")))) {
} else if (mg_http_match_uri(hm, "/stats")) {
stats(nc);
} else if (is_equal(&path, &((struct mg_str) MG_MK_STR("/jslib")))) {
} else if (mg_http_match_uri(hm, "/jslib")) {
javascript_lib(nc);
} else if (is_equal(&path, &((struct mg_str) MG_MK_STR("/jssearch")))) {
} else if (mg_http_match_uri(hm, "/jssearch")) {
javascript_search(nc);
} else if (is_equal(&path, &((struct mg_str) MG_MK_STR("/img/sprite-skin-flat.png")))) {
} else if (mg_http_match_uri(hm, "/img/sprite-skin-flat.png")) {
img_sprite_skin_flat(nc, hm);
} else if (is_equal(&path, &((struct mg_str) MG_MK_STR("/es")))) {
} else if (mg_http_match_uri(hm, "/es")) {
search(nc, hm);
} else if (is_equal(&path, &((struct mg_str) MG_MK_STR("/i")))) {
} else if (mg_http_match_uri(hm, "/i")) {
index_info(nc);
} else if (is_equal(&path, &((struct mg_str) MG_MK_STR("/status")))) {
} else if (mg_http_match_uri(hm, "/status")) {
status(nc);
} else if (has_prefix(&path, &((struct mg_str) MG_MK_STR("/f/")))) {
file(nc, hm, &path);
} else if (has_prefix(&path, &((struct mg_str) MG_MK_STR("/t/")))) {
thumbnail(nc, hm, &path);
} else if (has_prefix(&path, &((struct mg_str) MG_MK_STR("/s/")))) {
stats_files(nc, hm, &path);
} else if (has_prefix(&path, &((struct mg_str) MG_MK_STR("/tag/")))) {
if (WebCtx.tag_auth_enabled == TRUE) {
if (!validate_auth(nc, hm)) {
return;
}
} else if (mg_http_match_uri(hm, "/f/*")) {
file(nc, hm);
} else if (mg_http_match_uri(hm, "/t/*/*")) {
thumbnail(nc, hm);
} else if (mg_http_match_uri(hm, "/s/*/*")) {
stats_files(nc, hm);
} else if (mg_http_match_uri(hm, "/tag/*")) {
if (WebCtx.tag_auth_enabled == TRUE && !validate_auth(nc, hm)) {
nc->is_closing = 1;
return;
}
tag(nc, hm, &path);
} else if (has_prefix(&path, &((struct mg_str) MG_MK_STR("/d/")))) {
document_info(nc, hm, &path);
tag(nc, hm);
} else if (mg_http_match_uri(hm, "/d/*")) {
document_info(nc, hm);
} else {
mg_http_send_error(nc, 404, NULL);
nc->flags |= MG_F_SEND_AND_CLOSE;
mg_http_reply(nc, 404, "", "Page not found");
}
} else if (ev == MG_EV_POLL) {
if (nc->user_data != NULL) {
if (nc->fn_data != NULL) {
//Waiting for ES reply
subreq_ctx_t *ctx = (subreq_ctx_t *) nc->user_data;
subreq_ctx_t *ctx = (subreq_ctx_t *) nc->fn_data;
web_post_async_poll(ctx);
if (ctx->done == TRUE) {
response_t *r = ctx->response;
if (r->status_code == 200) {
@ -684,14 +611,14 @@ static void ev_router(struct mg_connection *nc, int ev, void *p) {
free(json_str);
free(tmp);
}
mg_http_send_error(nc, 500, NULL);
mg_http_reply(nc, 500, "", "");
}
free_response(r);
free(ctx->data);
free(ctx);
nc->flags |= MG_F_SEND_AND_CLOSE;
nc->user_data = NULL;
nc->fn_data = NULL;
}
}
}
@ -702,15 +629,18 @@ void serve(const char *listen_address) {
printf("Starting web server @ http://%s\n", listen_address);
struct mg_mgr mgr;
mg_mgr_init(&mgr, NULL);
mg_mgr_init(&mgr);
struct mg_connection *nc = mg_bind(&mgr, listen_address, ev_router);
int ok = 1;
struct mg_connection *nc = mg_http_listen(&mgr, listen_address, ev_router, NULL);
if (nc == NULL) {
LOG_FATALF("serve.c", "Couldn't bind web server on address %s", listen_address)
}
mg_set_protocol_http_websocket(nc);
for (;;) {
while (ok) {
mg_mgr_poll(&mgr, 10);
}
mg_mgr_free(&mgr);
LOG_INFO("serve.c", "Finished web event loop")
}

File diff suppressed because one or more lines are too long

View File

@ -17,17 +17,19 @@ def copy_files(files):
def sist2(*args):
print("./sist2 " + " ".join(args))
return subprocess.check_output(
args=["./sist2_debug", *args],
args=["./sist2", *args],
)
def sist2_index(files, *args):
path = copy_files(files)
shutil.rmtree("i", ignore_errors=True)
sist2("scan", path, "-o", "i", *args)
return iter(sist2_index_to_dict("i"))
shutil.rmtree("test_i", ignore_errors=True)
sist2("scan", path, "-o", "test_i", *args)
return iter(sist2_index_to_dict("test_i"))
def sist2_incremental_index(files, func=None, *args):
@ -36,14 +38,14 @@ def sist2_incremental_index(files, func=None, *args):
if func:
func(path)
shutil.rmtree("i_inc", ignore_errors=True)
sist2("scan", path, "-o", "i_inc", "--incremental", "i", *args)
return iter(sist2_index_to_dict("i_inc"))
shutil.rmtree("test_i_inc", ignore_errors=True)
sist2("scan", path, "-o", "test_i_inc", "--incremental", "test_i", *args)
return iter(sist2_index_to_dict("test_i_inc"))
def sist2_index_to_dict(index):
res = subprocess.check_output(
args=["./sist2_debug", "index", "--print", index],
args=["./sist2", "index", "--print", index],
)
for line in res.splitlines():

@ -1 +1 @@
Subproject commit 3f4e3594a6891b942d5a711781d5425111aa13bf
Subproject commit ffd9c23427d0cb105e27f27f0cf97b463b6a8bf8

2
third-party/libscan vendored

@ -1 +1 @@
Subproject commit ae9fadec473e6e4ade05259fe359c5366c3f3af6
Subproject commit 9be4f02851107edac65894a1fdde16a80cad43ac