Compare commits

..

3 Commits

Author SHA1 Message Date
50771bd1dc Read subtitles from media files, fix bug in text_buffer 2021-03-26 19:48:16 -04:00
bc884e137c Change encoding for antiword PDF 2021-01-16 12:17:43 -05:00
ce1e241dea Workaround for UTF8 .doc files 2021-01-16 12:13:56 -05:00
9 changed files with 24 additions and 23 deletions

View File

@@ -11,21 +11,6 @@ steps:
image: simon987/ubuntu_ci
commands:
- ./ci/build.sh
- name: docker
image: plugins/docker
settings:
username:
from_secret: DOCKER_USER
password:
from_secret: DOCKER_PASSWORD
repo: simon987/sist2
context: ./Docker/
dockerfile: ./Docker/Dockerfile
auto_tag: true
auto_tag_suffix: x64-linux
when:
event:
- tag
- name: scp files
image: appleboy/drone-scp
settings:
@@ -39,7 +24,6 @@ steps:
from_secret: SSH_KEY
target: /files/sist2/${DRONE_REPO_OWNER}_${DRONE_REPO_NAME}/${DRONE_BRANCH}_${DRONE_BUILD_NUMBER}_${DRONE_COMMIT}/
source:
- ./VERSION
- ./sist2-x64-linux
- ./sist2-x64-linux-debug.tar.gz
@@ -67,6 +51,6 @@ steps:
from_secret: SSH_USER
key:
from_secret: SSH_KEY
target: /files/sist2/${DRONE_REPO_OWNER}_${DRONE_REPO_NAME}/arm_${DRONE_BRANCH}_${DRONE_BUILD_NUMBER}_${DRONE_COMMIT}/
target: /files/sist2/${DRONE_REPO_OWNER}_${DRONE_REPO_NAME}/${DRONE_BRANCH}_${DRONE_BUILD_NUMBER}_${DRONE_COMMIT}/
source:
- ./sist2-arm64-linux

View File

@@ -1,4 +1,4 @@
FROM ubuntu:20.04
FROM ubuntu:19.10
MAINTAINER simon987 <me@simon987.net>
RUN apt update

14
Docker/build.sh Executable file
View File

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

View File

@@ -10,8 +10,6 @@ rm -rf CMakeFiles CMakeCache.txt
cmake -DSIST_DEBUG=off -DCMAKE_TOOLCHAIN_FILE="${VCPKG_ROOT}/scripts/buildsystems/vcpkg.cmake" .
make -j 33
strip sist2
./sist2 -v > VERSION
cp sist2 Docker/
mv sist2 sist2-x64-linux
rm -rf CMakeFiles CMakeCache.txt

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

@@ -25,6 +25,7 @@ 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

@@ -132,6 +132,7 @@ 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
@@ -448,6 +449,7 @@ 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"),