Compare commits

...

78 Commits

Author SHA1 Message Date
bb23651087 update docker image version in readme 2021-07-10 13:05:13 -04:00
78f3c897e2 libscan version sync 2021-07-10 12:52:24 -04:00
a2209e91ca add fast-epub arg, tweak thread pool, error handling for nftw 2021-07-10 12:52:04 -04:00
ba31531d3a Return 404 when thumbnail is not found 2021-07-10 12:45:30 -04:00
d5a47b8dab Fix segfault in exec-script 2021-06-23 19:46:52 -04:00
d8c0b80524 Update README.md 2021-06-23 10:26:20 -04:00
142a4869e6 Bump version 2021-06-23 08:19:05 -04:00
ddb7f8d5d7 Fix some bugs in serve.c caused by mongoose upgrade 2021-06-23 08:18:11 -04:00
dfb8c67490 thread safety for debug info table 2021-06-14 15:04:08 -04:00
3da2c8cae3 Update CI scripts, Dockerfiles, enable arm64 build again 2021-06-14 14:02:16 -04:00
2f0e999b06 Update README.md 2021-06-13 09:50:56 -04:00
bf28dc8993 Merge pull request #164 from simon987/dev
v2.10.1
2021-06-13 09:50:23 -04:00
c6fee7f6e2 update argparse 2021-06-13 09:41:18 -04:00
201c2a1a47 Update CI things 2021-06-13 09:26:27 -04:00
7c46ad632a Update readme 2021-06-11 20:44:47 -04:00
5b8c13fd13 Handle GPS metadata in the UI 2021-06-11 20:41:05 -04:00
efa4a06e56 Fix meta_key UB problem 2021-06-11 20:19:36 -04:00
81670ee107 Fix subtitle problems 2021-06-11 10:05:33 -04:00
f9dac80905 Fix file download in mongoose 7.x 2021-06-09 13:34:38 -04:00
f8d9b718c0 Fix memory leak in RAW parsing 2021-06-09 08:22:31 -04:00
6f5fdc2935 Fix for segfault in some comic files 2021-06-07 09:01:46 -04:00
a01f6dff1f Use 16-bit ints for meta keys (wip) 2021-06-07 08:40:12 -04:00
22dd58e140 add signal handler w/ debug info 2021-05-08 16:23:24 -04:00
f3e07fb7f7 Merge pull request #155 from dpieski/patch-4
Create feature_request.md
2021-05-06 20:17:29 -04:00
7990e5cd2e Update feature_request.md 2021-05-06 20:16:59 -04:00
e3ca660983 Merge pull request #153 from dpieski/patch-1
Create bug_report.md
2021-05-06 20:15:52 -04:00
b87fb25458 Update bug_report.md 2021-05-06 20:15:41 -04:00
c7a77869ad Merge pull request #154 from dpieski/patch-2
Create config.yml
2021-05-06 20:09:36 -04:00
523c123e2e Enable advanced search with query_string 2021-05-06 20:07:20 -04:00
fc7f30d670 Add tests for subtitle 2021-05-05 16:10:55 -04:00
152fe11669 Set passphrase arg in arc_ctx 2021-05-05 15:52:46 -04:00
33f97f6bfb Increase scan queue size 2021-05-05 14:25:35 -04:00
71f9dfcfe0 sync libscan 2021-05-05 14:21:01 -04:00
5f657d61b3 Merge pull request #157 from simon987/mongoose-7
Update to mongoose 7.x, change Docker build
2021-05-05 14:18:36 -04:00
908def1016 Fix build, update dockerfile 2021-05-05 14:13:46 -04:00
db3d312835 wip 2021-05-05 13:55:57 -04:00
32c9cb28a3 Read subtitles from media files, fix bug in text_buffer 2021-05-05 13:55:57 -04:00
f839127129 Change encoding for antiword PDF 2021-05-05 13:55:57 -04:00
8111a6c143 Workaround for UTF8 .doc files 2021-05-05 13:55:57 -04:00
707a570828 Pause all other audio tags on play #148 2021-04-17 13:24:21 -04:00
Andrew
5073b00225 Create feature_request.md
Created basic feature request template.
2021-04-13 11:25:48 -05:00
Andrew
4923d1b51f Update bug_report.md
Forgot an exclamation mark
2021-04-13 11:20:46 -05:00
Andrew
097e332015 Create config.yml
Does two things:
1. Creates a link to the USAGE page. 
2. Removes "Open Blank Issue" option on the New Issue page.
2021-04-13 11:10:08 -05:00
Andrew
d4babe216b Update bug_report.md
Added a bug to the title just because. Not necessary, just wanted to see how it looks.
2021-04-13 10:58:32 -05:00
Andrew
44511a2202 Create bug_report.md
Beginnings of a Bug Report template for #151
2021-04-13 10:49:43 -05:00
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
5fe9c9efa3 Tweak CI settings 2021-01-16 11:14:18 -05:00
75e4e93ddd Enable docker image builds 2021-01-16 10:57:55 -05:00
013c54daa0 Fix tag delete 2020-12-31 12:55:37 -05:00
54308ef5e2 Update tags tab automatically 2020-12-31 12:45:23 -05:00
638c2a5c1a Update binary names (again) 2020-12-31 11:03:25 -05:00
9587caddd9 Don't build tests by default, fix enlarge button 2020-12-31 10:55:34 -05:00
f5bbe0dc97 Update binary names 2020-12-31 10:54:30 -05:00
f87eac1f90 Update submodules 2020-12-31 10:26:05 -05:00
ddafbab6a6 Update readme 2020-12-31 10:26:05 -05:00
b91d574756 Add md5 client-side lib 2020-12-31 10:26:05 -05:00
576140e542 fix submodules 2020-12-31 10:26:05 -05:00
050c1283a3 Remove UUID dep, fix incremental scan, use MD5(path) as unique id, version bump 2020-12-31 10:26:05 -05:00
c6e1ba03bc Better support for .doc files 2020-12-31 10:26:05 -05:00
10e32f707f Update README.md 2020-12-31 10:26:05 -05:00
86e83bafaf Update README.md 2020-12-31 10:26:05 -05:00
51a40c8819 Add .doc support 2020-12-31 10:26:05 -05:00
acc557
36281a5108 Use relative path for loading csv in stats 2020-12-31 10:26:05 -05:00
acc557
76a0bda48b Update search.html
Fix relative stats URL
2020-12-31 10:26:05 -05:00
0cf29a660c Fix relative image URL #122 2020-12-31 10:26:05 -05:00
6cd0741848 update build instructions 2020-12-31 10:26:05 -05:00
bc120f349d Setup ARM CI builds 2020-12-23 10:26:26 -05:00
8cac8c98d7 Update dev builds template 2020-12-22 14:45:16 -05:00
30921ac52e Setup drone ci 2020-12-22 14:09:45 -05:00
95bbe39afc Update libmupdf 2020-10-25 09:44:30 -04:00
72ce217f9c Optionally ES schema from file #117 2020-10-25 09:44:30 -04:00
641a8ec90c sidecar files #114, version bump 2020-10-25 09:44:30 -04:00
7a505c2287 Fix typo 2020-10-25 09:44:30 -04:00
12f162d760 Fix #110 2020-10-25 09:44:30 -04:00
4b4ab12fac Version bump 2020-09-22 21:08:24 -04:00
ae283f77ad Fix #112 2020-09-22 21:08:24 -04:00
56 changed files with 1706 additions and 965 deletions

25
.dockerignore Normal file
View File

@@ -0,0 +1,25 @@
.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/
VERSION

72
.drone.yml Normal file
View File

@@ -0,0 +1,72 @@
kind: pipeline
type: docker
name: amd64
platform:
os: linux
arch: amd64
steps:
- name: build
image: simon987/sist2-build
commands:
- ./ci/build.sh
- name: docker
image: plugins/docker
settings:
username:
from_secret: DOCKER_USER
password:
from_secret: DOCKER_PASSWORD
repo: simon987/sist2
context: ./
dockerfile: ./Dockerfile
auto_tag: true
auto_tag_suffix: x64-linux
when:
event:
- tag
- 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}/${DRONE_BRANCH}_${DRONE_BUILD_NUMBER}_${DRONE_COMMIT}/
source:
- ./VERSION
- ./sist2-x64-linux
- ./sist2-x64-linux-debug
---
kind: pipeline
type: docker
name: arm64
platform:
arch: arm64
steps:
- name: build
image: simon987/sist2-build-arm64
commands:
- ./ci/build_arm64.sh
- name: scp files
image: appleboy/drone-scp
settings:
host:
from_secret: SSH_HOST
port:
from_secret: SSH_PORT
user:
from_secret: SSH_USER
key:
from_secret: SSH_KEY
target: /files/sist2/${DRONE_REPO_OWNER}_${DRONE_REPO_NAME}/arm_${DRONE_BRANCH}_${DRONE_BUILD_NUMBER}_${DRONE_COMMIT}/
source:
- ./sist2-arm64-linux

40
.github/ISSUE_TEMPLATE/bug_report.md vendored Normal file
View File

@@ -0,0 +1,40 @@
---
name: "🐞 Bug Report"
about: Submit a bug report
title: ''
labels: bug
assignees: ''
---
**Device Information (please complete the following information):**
- OS: `[e.g., Ubuntu 20.04, WSL2]`
- Deployment: `[Linux, Linux ARM64 or Docker]`
- Browser *(if relevant)*: `[e.g., chrome, safari]`
- SIST2 Version: `[e.g., v2.9.0]`
- Elasticsearch Version *(if relevant)* : ``
**Command with arguments**
<!-- `ex: "scan ~/Documents -o ./i2 --threads 3 -q 1.0` -->
**Describe the bug**
<!-- A clear and concise description of what the bug is. -->
**Steps To Reproduce**
Please be specific!
1. Go to '...'
2. Click on '....'
3. etc.
**Expected behavior**
<!-- A clear and concise description of what you expected to happen. -->
**Actual Behavior**
<!-- A clear and concise description of what actually happens. -->
**Screenshots**
<!-- If applicable, add screenshots to help explain your problem. -->
**Additional context**
<!-- Add any other context about the problem here. If applicable, please include why you think the bug is occurring and/or troubleshooting you have already performed. -->
<!-- If the issue is related to the `scan` module, please attach the files necessary to reproduce the error or email them to me[at]simon987.net. -->

5
.github/ISSUE_TEMPLATE/config.yml vendored Normal file
View File

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

View File

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

3
.gitignore vendored
View File

@@ -1,6 +1,5 @@
.idea
thumbs
test
*.cbp
CMakeCache.txt
CMakeFiles
@@ -17,3 +16,5 @@ bundle.js
vgcore.*
build/
third-party/
*.idx/
VERSION

View File

@@ -1,69 +0,0 @@
import jetbrains.buildServer.configs.kotlin.v2019_2.*
import jetbrains.buildServer.configs.kotlin.v2019_2.buildSteps.ExecBuildStep
import jetbrains.buildServer.configs.kotlin.v2019_2.buildSteps.exec
import jetbrains.buildServer.configs.kotlin.v2019_2.triggers.vcs
import jetbrains.buildServer.configs.kotlin.v2019_2.vcs.GitVcsRoot
/*
The settings script is an entry point for defining a TeamCity
project hierarchy. The script should contain a single call to the
project() function with a Project instance or an init function as
an argument.
VcsRoots, BuildTypes, Templates, and subprojects can be
registered inside the project using the vcsRoot(), buildType(),
template(), and subProject() methods respectively.
To debug settings scripts in command-line, run the
mvnDebug org.jetbrains.teamcity:teamcity-configs-maven-plugin:generate
command and attach your debugger to the port 8000.
To debug in IntelliJ Idea, open the 'Maven Projects' tool window (View
-> Tool Windows -> Maven Projects), find the generate task node
(Plugins -> teamcity-configs -> teamcity-configs:generate), the
'Debug' option is available in the context menu for the task.
*/
version = "2019.2"
project {
vcsRoot(HttpsGithubComSimon987sist2refsHeadsMaster)
buildType(Build)
}
object Build : BuildType({
name = "Build"
artifactRules = """
sist2
sist2_scan
""".trimIndent()
vcs {
root(HttpsGithubComSimon987sist2refsHeadsMaster)
}
steps {
exec {
name = "Build"
path = "./ci/build.sh"
dockerImage = "simon987/general_ci"
dockerImagePlatform = ExecBuildStep.ImagePlatform.Linux
dockerPull = true
}
}
triggers {
vcs {
}
}
})
object HttpsGithubComSimon987sist2refsHeadsMaster : GitVcsRoot({
name = "https://github.com/simon987/sist2#refs/heads/master"
url = "https://github.com/simon987/sist2"
})

View File

@@ -5,12 +5,16 @@ project(sist2 C)
option(SIST_DEBUG "Build a debug executable" on)
set(BUILD_TESTS on)
add_subdirectory(third-party/libscan)
set(ARGPARSE_SHARED off)
add_subdirectory(third-party/argparse)
add_executable(
sist2
add_executable(sist2
# argparse
third-party/argparse/argparse.h third-party/argparse/argparse.c
src/main.c
src/sist.h
src/io/walk.h src/io/walk.c
@@ -25,25 +29,22 @@ add_executable(
src/util.c src/util.h
src/ctx.h src/types.h
src/log.c src/log.h
# argparse
third-party/argparse/argparse.h third-party/argparse/argparse.c
src/cli.c src/cli.h
src/stats.c src/stats.h src/ctx.c)
src/stats.c src/stats.h src/ctx.c
src/parsing/sidecar.c src/parsing/sidecar.h)
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_library(UUID_LIB NAMES uuid)
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(
@@ -67,13 +69,13 @@ if (SIST_DEBUG)
-fstack-protector
-fno-omit-frame-pointer
-fsanitize=address
-O2
-fno-inline
# -O2
)
target_link_options(
sist2
PRIVATE
-fsanitize=address
# -static
)
set_target_properties(
sist2
@@ -81,7 +83,6 @@ if (SIST_DEBUG)
OUTPUT_NAME sist2_debug
)
else ()
# set(VCPKG_BUILD_TYPE release)
target_compile_options(
sist2
PRIVATE
@@ -104,15 +105,15 @@ target_link_libraries(
lmdb
cjson
argparse
unofficial::glib::glib
${GLIB_LDFLAGS}
unofficial::mongoose::mongoose
# OpenSSL::SSL OpenSSL::Crypto
CURL::libcurl
${UUID_LIB}
pthread
magic
c
scan
)

View File

@@ -1,14 +0,0 @@
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

@@ -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

@@ -1,9 +1,15 @@
FROM ubuntu:19.10
FROM simon987/sist2-build as build
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
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 && apt install -y curl
RUN mkdir -p /usr/share/tessdata && \
cd /usr/share/tessdata/ && \
@@ -12,9 +18,9 @@ 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

View File

@@ -1,9 +1,15 @@
FROM ubuntu:19.10
FROM simon987/sist2-build-arm64 as build
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
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 && apt install -y curl
RUN mkdir -p /usr/share/tessdata && \
cd /usr/share/tessdata/ && \
@@ -12,9 +18,9 @@ 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_arm64 /root/sist2
COPY --from=build /build/sist2 /root/sist2
ENV LANG C.UTF-8
ENV LC_ALL C.UTF-8

View File

@@ -1,8 +1,8 @@
![GitHub](https://img.shields.io/github/license/simon987/sist2.svg)
[![CodeFactor](https://www.codefactor.io/repository/github/simon987/sist2/badge?s=05daa325188aac4eae32c786f3d9cf4e0593f822)](https://www.codefactor.io/repository/github/simon987/sist2)
[![Development snapshots](https://ci.simon987.net/app/rest/builds/buildType(Sist2_Build)/statusIcon)](https://files.simon987.net/artifacts/Sist2/Build/)
[![Development snapshots](https://ci.simon987.net/api/badges/simon987/sist2/status.svg)](https://files.simon987.net/.gate/sist2/simon987_sist2/)
**Demo**: [sist2.simon987.net](https://sist2.simon987.net/)
**Demo**: [sist2.simon987.net](https://sist2.simon987.net/?i=Demo%20files)
# sist2
@@ -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
@@ -52,15 +50,13 @@ sist2 (Simple incremental search tool)
```
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. *(or)* Download a [development snapshot](https://files.simon987.net/.gate/sist2/simon987_sist2/) *(Not recommended!)*
1. *(or)* `docker pull simon987/sist2:2.10.3-x64-linux`
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
@@ -69,69 +65,88 @@ 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
File type | Library | Content | Thumbnail | Metadata
:---|:---|:---|:---|:---
pdf,xps,fb2,epub | MuPDF | text+ocr | yes | title |
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 | - |
tar, zip, rar, 7z, ar ... | Libarchive | yes\* | - | no |
docx, xlsx, pptx | *(none)* | yes | if embedded | creator, modified_by, title |
doc (MS Word 97-2003) | antiword | yes | yes | author, title |
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
### With docker (recommended)
```bash
git clone --recursive https://github.com/simon987/sist2/
cd sist2
docker build . -f ./Dockerfile -t my-sist2-image
docker run --rm my-sist2-image cat /root/sist2 > sist2-x64-linux
```
### On a linux computer
1. Install compile-time dependencies
```bash
vcpkg install lmdb cjson glib libarchive[core,bzip2,libxml2,lz4,lzma,lzo] pthread tesseract libxml2 ffmpeg zstd gtest mongoose libuuid libmagic libraw curl[core,ssl] jbig2dec brotli libmupdf
apt install gcc g++ python3 yasm ragel automake autotools-dev wget libtool libssl-dev curl zip unzip tar xorg-dev libglu1-mesa-dev libxcursor-dev libxml2-dev libxinerama-dev gettext nasm git
```
2. Build
1. Apply vcpkg patches, as per [sist2-build](https://github.com/simon987/sist2-build) Dockerfile
1. Install vcpkg dependencies
```bash
vcpkg install curl[core,openssl]
vcpkg install lmdb cjson glib brotli libarchive[core,bzip2,libxml2,lz4,lzma,lzo] pthread tesseract libxml2 libmupdf gtest mongoose libuuid libmagic libraw jasper lcms gumbo
```
1. Build
```bash
git clone --recursive https://github.com/simon987/sist2/
cmake -DCMAKE_TOOLCHAIN_FILE=<VCPKG_ROOT>/scripts/buildsystems/vcpkg.cmake .
cmake -DSIST_DEBUG=off -DCMAKE_TOOLCHAIN_FILE=<VCPKG_ROOT>/scripts/buildsystems/vcpkg.cmake .
make
```

View File

@@ -2,16 +2,18 @@
VCPKG_ROOT="/vcpkg"
rm *.gz
rm *.gz &>/dev/null
git submodule update --init --recursive
rm -rf CMakeFiles CMakeCache.txt
cmake -DSIST_DEBUG=off -DVCPKG_BUILD_TYPE=release -DCMAKE_TOOLCHAIN_FILE="${VCPKG_ROOT}/scripts/buildsystems/vcpkg.cmake" .
make -j 12
cmake -DSIST_DEBUG=off -DCMAKE_TOOLCHAIN_FILE="${VCPKG_ROOT}/scripts/buildsystems/vcpkg.cmake" .
make -j $(nproc)
strip sist2
gzip -9 sist2
./sist2 -v > VERSION
mv sist2 sist2-x64-linux
rm -rf CMakeFiles CMakeCache.txt
cmake -DSIST_DEBUG=on -DVCPKG_BUILD_TYPE=debug -DCMAKE_TOOLCHAIN_FILE="${VCPKG_ROOT}/scripts/buildsystems/vcpkg.cmake" .
make -j 12
cp /usr/lib/x86_64-linux-gnu/libasan.so.2.0.0 libasan.so.2
tar -czf sist2_debug.tar.gz sist2_debug libasan.so.2
cmake -DSIST_DEBUG=on -DCMAKE_TOOLCHAIN_FILE="${VCPKG_ROOT}/scripts/buildsystems/vcpkg.cmake" .
make -j $(nproc)
mv sist2_debug sist2-x64-linux-debug

View File

@@ -2,11 +2,12 @@
VCPKG_ROOT="/vcpkg"
rm *.gz
rm *.gz &>/dev/null
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 4
make -j $(nproc)
strip sist2
mv sist2 sist2_arm64
gzip -9 sist2_arm64
mv sist2 sist2-arm64-linux

View File

@@ -16,6 +16,7 @@
* [link to specific indices](#link-to-specific-indices)
* [exec-script](#exec-script)
* [tagging](#tagging)
* [sidecar files](#sidecar-files)
```
Usage: sist2 scan [OPTION]... PATH
@@ -45,6 +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
@@ -52,6 +54,8 @@ Index options
--es-index=<str> Elasticsearch index name. DEFAULT=sist2
-p, --print Just print JSON documents to stdout.
--script-file=<str> Path to user script.
--mappings-file=<str> Path to Elasticsearch mappings.
--settings-file=<str> Path to Elasticsearch settings.
--async-script Execute user script asynchronously.
--batch-size=<int> Index batch size. DEFAULT: 100
-f, --force-reset Reset Elasticsearch mappings and settings. (You must use this option the first time you use the index command)
@@ -88,7 +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.
@@ -120,6 +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
@@ -153,10 +158,13 @@ documents.idx/
├── agg_mime.csv
├── agg_date.csv
├── add_size.csv
├── thumbs
├── thumbs/
| ├── data.mdb
| └── lock.mdb
── tags
── tags/
| ├── data.mdb
| └── lock.mdb
└── meta/
├── data.mdb
└── lock.mdb
```
@@ -183,9 +191,11 @@ by a third party application. The 'external' index must have the following forma
my_index/
├── descriptor.json
├── _index_0
└── thumbs
├── data.mdb
└── lock.mdb
└── thumbs/
| ├── data.mdb
| └── lock.mdb
└── meta/
└── <empty>
```
*descriptor.json*:
@@ -233,9 +243,11 @@ The `_text.*` items will be indexed and searchable as **text** fields (fuzzy sea
*thumbs/*:
LMDB key-value store. Keys are **binary** 128-bit UUID4s (`_id` field)
LMDB key-value store. Keys are **binary** 16-byte md5 hash* (`_id` field)
and values are raw image bytes.
*\* Hash is calculated from the full path of the file, including the extension, relative to the index root*
Importing an external `binary` type index is technically possible but
it is currently unsupported and has no guaranties of back/forward compatibility.
@@ -251,6 +263,10 @@ it is currently unsupported and has no guaranties of back/forward compatibility.
Print index in JSON format to stdout.
* `--script-file`
Path to user script. See [Scripting](scripting.md).
* `--mappings-file`
Path to custom Elasticsearch mappings. If none is specified, [the bundled mappings](https://github.com/simon987/sist2/tree/master/schema) will be used.
* `--settings-file`
Path to custom Elasticsearch settings. *(See above)*
* `--async-script`
Use `wait_for_completion=false` elasticsearch option while executing user script.
(See [Elasticsearch documentation](https://www.elastic.co/guide/en/elasticsearch/reference/current/tasks.html))
@@ -260,7 +276,6 @@ it is currently unsupported and has no guaranties of back/forward compatibility.
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
@@ -342,10 +357,48 @@ You can safely copy the `/tags/` database to another index.
See [Automatic tagging](#automatic-tagging) for information about tag
hierarchies and tag colors.
\* *It can take a few seconds to take effect in new search queries, and the page needs
to be reloaded for the tag tab to update*
\* *It can take a few seconds to take effect in new search queries.*
### Automatic tagging
See [scripting](scripting.md) documentation.
# Sidecar files
When scanning, sist2 will read metadata from `.s2meta` JSON files and overwrite the
original document's metadata. Sidecar metadata files will also work inside archives.
Sidecar files themselves are not saved in the index.
This feature is useful to leverage third-party applications such as speech-to-text or
OCR to add additional metadata to a file.
**Example**
```
~/Documents/
├── Video.mp4
└── Video.mp4.s2meta
```
The sidecar file must have exactly the same file path and the `.s2meta` suffix.
`Video.mp4.s2meta`:
```json
{
"content": "This sidecar file will overwrite some metadata fields of Video.mp4",
"author": "Some author",
"duration": 12345,
"bitrate": 67890,
"some_arbitrary_field": [1,2,3]
}
```
```
sist2 scan ~/Documents -o ./docs.idx
sist2 index ./docs.idx
```
*NOTE*: It is technically possible to overwrite the `tag` value using sidecar files, however,
it is not currently possible to restore both manual tags and sidecar tags without user scripts
while reindexing.

View File

@@ -30,6 +30,10 @@
"mime": {
"type": "keyword"
},
"parent": {
"type": "keyword",
"index": false
},
"thumbnail": {
"type": "keyword",
"index": false
@@ -101,10 +105,10 @@
"analyzer": "my_nGram",
"type": "text"
},
"_keyword.*": {
"_keyword.*": {
"type": "keyword"
},
"_text.*": {
"_text.*": {
"analyzer": "content_analyzer",
"type": "text",
"fields": {
@@ -161,6 +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"
},

View File

@@ -449,3 +449,4 @@ image/x-sony-arw, arw
image/x-sony-sr2, sr2
image/x-sony-srf, srf
image/x-epson-erf, erf
sist2/sidecar, s2meta
1 application/arj arj
449 image/x-sony-sr2 sr2
450 image/x-sony-srf srf
451 image/x-epson-erf erf
452 sist2/sidecar s2meta

View File

@@ -3,6 +3,7 @@ noparse = set()
ext_in_hash = set()
major_mime = {
"sist2": 0,
"model": 1,
"example": 2,
"message": 3,
@@ -122,7 +123,11 @@ def mime_id(mime):
elif mime in raw:
mime_id += " | 0x00800000"
elif mime == "application/x-empty":
cnt -= 1
return "1"
elif mime == "sist2/sidecar":
cnt -= 1
return "2"
return mime_id

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

@@ -56,6 +56,12 @@ void scan_args_destroy(scan_args_t *args) {
void index_args_destroy(index_args_t *args) {
//todo
if (args->es_mappings_path) {
free(args->es_mappings);
}
if (args->es_settings_path) {
free(args->es_settings);
}
free(args);
}
@@ -221,35 +227,37 @@ 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)
LOG_DEBUGF("cli.c", "arg fast=%d", args->fast)
LOG_DEBUGF("cli.c", "arg fast_epub=%d", args->fast_epub)
LOG_DEBUGF("cli.c", "arg treemap_threshold=%f", args->treemap_threshold)
LOG_DEBUGF("cli.c", "arg max_memory_buffer=%d", args->max_memory_buffer)
return 0;
}
int load_script(const char *script_path, char **dst) {
int load_external_file(const char *file_path, char **dst) {
struct stat info;
int res = stat(script_path, &info);
int res = stat(file_path, &info);
if (res == -1) {
fprintf(stderr, "Error opening script file '%s': %s\n", script_path, strerror(errno));
LOG_ERRORF("cli.c", "Error opening file '%s': %s\n", file_path, strerror(errno))
return 1;
}
int fd = open(script_path, O_RDONLY);
int fd = open(file_path, O_RDONLY);
if (fd == -1) {
fprintf(stderr, "Error opening script file '%s': %s\n", script_path, strerror(errno));
LOG_ERRORF("cli.c", "Error opening file '%s': %s\n", file_path, strerror(errno))
return 1;
}
*dst = malloc(info.st_size + 1);
res = read(fd, *dst, info.st_size);
if (res < 0) {
fprintf(stderr, "Error reading script file '%s': %s\n", script_path, strerror(errno));
LOG_ERRORF("cli.c", "Error reading file '%s': %s\n", file_path, strerror(errno))
return 1;
}
@@ -293,7 +301,19 @@ int index_args_validate(index_args_t *args, int argc, const char **argv) {
}
if (args->script_path != NULL) {
if (load_script(args->script_path, &args->script) != 0) {
if (load_external_file(args->script_path, &args->script) != 0) {
return 1;
}
}
if (args->es_settings_path != NULL) {
if (load_external_file(args->es_settings_path, &args->es_settings) != 0) {
return 1;
}
}
if (args->es_mappings_path != NULL) {
if (load_external_file(args->es_mappings_path, &args->es_mappings) != 0) {
return 1;
}
}
@@ -309,6 +329,10 @@ int index_args_validate(index_args_t *args, int argc, const char **argv) {
LOG_DEBUGF("cli.c", "arg async_script=%s", args->async_script)
LOG_DEBUGF("cli.c", "arg script=%s", args->script)
LOG_DEBUGF("cli.c", "arg print=%d", args->print)
LOG_DEBUGF("cli.c", "arg es_mappings_path=%s", args->es_mappings_path)
LOG_DEBUGF("cli.c", "arg es_mappings=%s", args->es_mappings)
LOG_DEBUGF("cli.c", "arg es_settings_path=%s", args->es_settings_path)
LOG_DEBUGF("cli.c", "arg es_settings=%s", args->es_settings)
LOG_DEBUGF("cli.c", "arg batch_size=%d", args->batch_size)
LOG_DEBUGF("cli.c", "arg force_reset=%d", args->force_reset)
@@ -445,7 +469,7 @@ int exec_args_validate(exec_args_t *args, int argc, const char **argv) {
LOG_FATAL("cli.c", "--script-file argument is required");
}
if (load_script(args->script_path, &args->script) != 0) {
if (load_external_file(args->script_path, &args->script) != 0) {
return 1;
}

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 +26,8 @@ typedef struct scan_args {
const char* treemap_threshold_str;
double treemap_threshold;
int max_memory_buffer;
int read_subtitles;
int fast_epub;
} scan_args_t;
scan_args_t *scan_args_create();
@@ -39,6 +42,10 @@ typedef struct index_args {
const char *index_path;
const char *script_path;
char *script;
const char *es_settings_path;
char *es_settings;
const char *es_mappings_path;
char *es_mappings;
int print;
int batch_size;
int async_script;

View File

@@ -13,6 +13,7 @@
#include "libscan/text/text.h"
#include "libscan/mobi/scan_mobi.h"
#include "libscan/raw/raw.h"
#include "libscan/msdoc/msdoc.h"
#include "src/io/store.h"
#include <glib.h>
@@ -39,6 +40,14 @@ typedef struct {
pcre_extra *exclude_extra;
int fast;
GHashTable *dbg_current_files;
pthread_mutex_t dbg_current_files_mu;
int dbg_failed_files_count;
int dbg_skipped_files_count;
int dbg_excluded_files_count;
pthread_mutex_t dbg_file_counts_mu;
scan_arc_ctx_t arc_ctx;
scan_comic_ctx_t comic_ctx;
scan_ebook_ctx_t ebook_ctx;
@@ -48,6 +57,7 @@ typedef struct {
scan_text_ctx_t text_ctx;
scan_mobi_ctx_t mobi_ctx;
scan_raw_ctx_t raw_ctx;
scan_msdoc_ctx_t msdoc_ctx;
} ScanCtx_t;
typedef struct {
@@ -63,6 +73,8 @@ typedef struct {
tpool_t *pool;
store_t *tag_store;
GHashTable *tags;
store_t *meta_store;
GHashTable *meta;
} IndexCtx_t;
typedef struct {

View File

@@ -30,11 +30,11 @@ void elastic_cleanup() {
}
}
void print_json(cJSON *document, const char uuid_str[UUID_STR_LEN]) {
void print_json(cJSON *document, const char id_str[MD5_STR_LENGTH]) {
cJSON *line = cJSON_CreateObject();
cJSON_AddStringToObject(line, "_id", uuid_str);
cJSON_AddStringToObject(line, "_id", id_str);
cJSON_AddStringToObject(line, "_index", IndexCtx.es_index);
cJSON_AddStringToObject(line, "_type", "_doc");
cJSON_AddItemReferenceToObject(line, "_source", document);
@@ -52,13 +52,13 @@ void index_json_func(void *arg) {
elastic_index_line(line);
}
void index_json(cJSON *document, const char uuid_str[UUID_STR_LEN]) {
void index_json(cJSON *document, const char index_id_str[MD5_STR_LENGTH]) {
char *json = cJSON_PrintUnformatted(document);
size_t json_len = strlen(json);
es_bulk_line_t *bulk_line = malloc(sizeof(es_bulk_line_t) + json_len + 2);
memcpy(bulk_line->line, json, json_len);
memcpy(bulk_line->uuid_str, uuid_str, UUID_STR_LEN);
memcpy(bulk_line->path_md5_str, index_id_str, MD5_STR_LENGTH);
*(bulk_line->line + json_len) = '\n';
*(bulk_line->line + json_len + 1) = '\0';
bulk_line->next = NULL;
@@ -67,7 +67,7 @@ void index_json(cJSON *document, const char uuid_str[UUID_STR_LEN]) {
tpool_add_work(IndexCtx.pool, index_json_func, bulk_line);
}
void execute_update_script(const char *script, int async, const char index_id[UUID_STR_LEN]) {
void execute_update_script(const char *script, int async, const char index_id[MD5_STR_LENGTH]) {
if (Indexer == NULL) {
Indexer = create_indexer(IndexCtx.es_url, IndexCtx.es_index);
@@ -129,9 +129,9 @@ void *create_bulk_buffer(int max, int *count, size_t *buf_len) {
while (line != NULL && *count < max) {
char action_str[256];
snprintf(
action_str, 256,
action_str, sizeof(action_str),
"{\"index\":{\"_id\":\"%s\",\"_type\":\"_doc\",\"_index\":\"%s\"}}\n",
line->uuid_str, Indexer->es_index
line->path_md5_str, Indexer->es_index
);
size_t action_str_len = strlen(action_str);
@@ -220,7 +220,7 @@ void _elastic_flush(int max) {
if (r->status_code == 413) {
if (max <= 1) {
LOG_ERRORF("elastic.c", "Single document too large, giving up: {%s}", Indexer->line_head->uuid_str)
LOG_ERRORF("elastic.c", "Single document too large, giving up: {%s}", Indexer->line_head->path_md5_str)
free_response(r);
free(buf);
delete_queue(1);
@@ -356,7 +356,7 @@ void finish_indexer(char *script, int async_script, char *index_id) {
free_response(r);
}
void elastic_init(int force_reset) {
void elastic_init(int force_reset, const char* user_mappings, const char* user_settings) {
// Check if index exists
char url[4096];
@@ -392,13 +392,13 @@ void elastic_init(int force_reset) {
free_response(r);
snprintf(url, sizeof(url), "%s/%s/_settings", IndexCtx.es_url, IndexCtx.es_index);
r = web_put(url, settings_json);
LOG_INFOF("elastic.c", "Update settings <%d>", r->status_code);
r = web_put(url, user_settings ? user_settings : settings_json);
LOG_INFOF("elastic.c", "Update user_settings <%d>", r->status_code);
free_response(r);
snprintf(url, sizeof(url), "%s/%s/_mappings/_doc?include_type_name=true", IndexCtx.es_url, IndexCtx.es_index);
r = web_put(url, mappings_json);
LOG_INFOF("elastic.c", "Update mappings <%d>", r->status_code);
r = web_put(url, user_mappings ? user_mappings : mappings_json);
LOG_INFOF("elastic.c", "Update user_mappings <%d>", r->status_code);
free_response(r);
snprintf(url, sizeof(url), "%s/%s/_open", IndexCtx.es_url, IndexCtx.es_index);
@@ -408,9 +408,9 @@ void elastic_init(int force_reset) {
}
}
cJSON *elastic_get_document(const char *uuid_str) {
cJSON *elastic_get_document(const char *id_str) {
char url[4096];
snprintf(url, sizeof(url), "%s/%s/_doc/%s", WebCtx.es_url, WebCtx.es_index, uuid_str);
snprintf(url, sizeof(url), "%s/%s/_doc/%s", WebCtx.es_url, WebCtx.es_index, id_str);
response_t *r = web_get(url, 3);
cJSON *json = NULL;

View File

@@ -5,7 +5,7 @@
typedef struct es_bulk_line {
struct es_bulk_line *next;
char uuid_str[UUID_STR_LEN];
char path_md5_str[MD5_STR_LENGTH];
char line[0];
} es_bulk_line_t;
@@ -16,21 +16,21 @@ typedef struct es_indexer es_indexer_t;
void elastic_index_line(es_bulk_line_t *line);
void print_json(cJSON *document, const char uuid_str[UUID_STR_LEN]);
void print_json(cJSON *document, const char index_id_str[MD5_STR_LENGTH]);
void index_json(cJSON *document, const char uuid_str[UUID_STR_LEN]);
void index_json(cJSON *document, const char index_id_str[MD5_STR_LENGTH]);
es_indexer_t *create_indexer(const char *url, const char *index);
void elastic_cleanup();
void finish_indexer(char *script, int async_script, char *index_id);
void elastic_init(int force_reset);
void elastic_init(int force_reset, const char* user_mappings, const char* user_settings);
cJSON *elastic_get_document(const char *uuid_str);
cJSON *elastic_get_document(const char *id_str);
char *elastic_get_status();
void execute_update_script(const char *script, int async, const char index_id[UUID_STR_LEN]);
void execute_update_script(const char *script, int async, const char index_id[MD5_STR_LENGTH]);
#endif

File diff suppressed because one or more lines are too long

View File

@@ -6,18 +6,22 @@
static __thread int index_fd = -1;
typedef struct {
unsigned char uuid[16];
unsigned long ino;
unsigned char path_md5[MD5_DIGEST_LENGTH];
unsigned long size;
unsigned int mime;
int mtime;
short base;
short ext;
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)) {
@@ -26,13 +30,13 @@ void skip_meta(FILE *file) {
while ((getc(file))) {}
}
key = getc(file);
fread(&key, sizeof(uint16_t), 1, file);
}
}
void write_index_descriptor(char *path, index_descriptor_t *desc) {
cJSON *json = cJSON_CreateObject();
cJSON_AddStringToObject(json, "uuid", desc->uuid);
cJSON_AddStringToObject(json, "id", desc->id);
cJSON_AddStringToObject(json, "version", desc->version);
cJSON_AddStringToObject(json, "root", desc->root);
cJSON_AddStringToObject(json, "name", desc->name);
@@ -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));
}
@@ -82,7 +86,7 @@ index_descriptor_t read_index_descriptor(char *path) {
strcpy(descriptor.rewrite_url, cJSON_GetObjectItem(json, "rewrite_url")->valuestring);
descriptor.root_len = (short) strlen(descriptor.root);
strcpy(descriptor.version, cJSON_GetObjectItem(json, "version")->valuestring);
strcpy(descriptor.uuid, cJSON_GetObjectItem(json, "uuid")->valuestring);
strcpy(descriptor.id, cJSON_GetObjectItem(json, "id")->valuestring);
if (cJSON_GetObjectItem(json, "type") == NULL) {
strcpy(descriptor.type, INDEX_TYPE_BIN);
} else {
@@ -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) {
@@ -219,9 +235,9 @@ void read_index_bin(const char *path, const char *index_id, index_func func) {
dyn_buffer_t buf = dyn_buffer_create();
FILE *file = fopen(path, "rb");
while (1) {
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;
}
@@ -229,8 +245,8 @@ void read_index_bin(const char *path, const char *index_id, index_func func) {
cJSON *document = cJSON_CreateObject();
cJSON_AddStringToObject(document, "index", index_id);
char uuid_str[UUID_STR_LEN];
uuid_unparse(line.uuid, uuid_str);
char path_md5_str[MD5_STR_LENGTH];
buf2hex(line.path_md5, sizeof(line.path_md5), path_md5_str);
const char *mime_text = mime_get_mime_text(line.mime);
if (mime_text == NULL) {
@@ -247,14 +263,6 @@ void read_index_bin(const char *path, const char *index_id, index_func func) {
}
dyn_buffer_write_char(&buf, '\0');
if (IndexCtx.tags != NULL) {
const char *tags_string = g_hash_table_lookup(IndexCtx.tags, buf.buf);
if (tags_string != NULL) {
cJSON *tags_arr = cJSON_Parse(tags_string);
cJSON_AddItemToObject(document, "tag", tags_arr);
}
}
cJSON_AddStringToObject(document, "extension", buf.buf + line.ext);
if (*(buf.buf + line.ext - 1) == '.') {
*(buf.buf + line.ext - 1) = '\0';
@@ -276,9 +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:
@@ -316,6 +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) {
@@ -331,11 +346,39 @@ 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);
}
func(document, uuid_str);
cJSON *meta_obj = NULL;
if (IndexCtx.meta != NULL) {
const char *meta_string = g_hash_table_lookup(IndexCtx.meta, path_md5_str);
if (meta_string != NULL) {
meta_obj = cJSON_Parse(meta_string);
cJSON *child;
for (child = meta_obj->child; child != NULL; child = child->next) {
char meta_key[4096];
strcpy(meta_key, child->string);
cJSON_DeleteItemFromObject(document, meta_key);
cJSON_AddItemReferenceToObject(document, meta_key, child);
}
}
}
if (IndexCtx.tags != NULL) {
const char *tags_string = g_hash_table_lookup(IndexCtx.tags, path_md5_str);
if (tags_string != NULL) {
cJSON *tags_arr = cJSON_Parse(tags_string);
cJSON_DeleteItemFromObject(document, "tag");
cJSON_AddItemToObject(document, "tag", tags_arr);
}
}
func(document, path_md5_str);
cJSON_Delete(document);
if (meta_obj) {
cJSON_Delete(meta_obj);
}
}
dyn_buffer_destroy(&buf);
fclose(file);
@@ -359,7 +402,7 @@ const char *json_type_array_fields[] = {
void read_index_json(const char *path, UNUSED(const char *index_id), index_func func) {
FILE *file = fopen(path, "r");
while (1) {
while (TRUE) {
char *line = NULL;
size_t len;
size_t read = getline(&line, &len, file);
@@ -379,7 +422,7 @@ void read_index_json(const char *path, UNUSED(const char *index_id), index_func
}
cJSON *document = cJSON_CreateObject();
const char *uuid_str = cJSON_GetObjectItem(input, "_id")->valuestring;
const char *id_str = cJSON_GetObjectItem(input, "_id")->valuestring;
for (int i = 0; i < (sizeof(json_type_copy_fields) / sizeof(json_type_copy_fields[0])); i++) {
cJSON *value = cJSON_GetObjectItem(input, json_type_copy_fields[i]);
@@ -407,7 +450,7 @@ void read_index_json(const char *path, UNUSED(const char *index_id), index_func
}
}
func(document, uuid_str);
func(document, id_str);
cJSON_Delete(document);
cJSON_Delete(input);
@@ -415,7 +458,7 @@ void read_index_json(const char *path, UNUSED(const char *index_id), index_func
fclose(file);
}
void read_index(const char *path, const char index_id[UUID_STR_LEN], const char *type, index_func func) {
void read_index(const char *path, const char index_id[MD5_STR_LENGTH], const char *type, index_func func) {
if (strcmp(type, INDEX_TYPE_BIN) == 0) {
read_index_bin(path, index_id, func);
@@ -428,15 +471,17 @@ void incremental_read(GHashTable *table, const char *filepath) {
FILE *file = fopen(filepath, "rb");
line_t line;
LOG_DEBUGF("serialize.c", "Incremental read %s", filepath)
while (1) {
size_t ret = fread((void *) &line, 1, sizeof(line_t), file);
size_t ret = fread((void *) &line, sizeof(line_t), 1, file);
if (ret != 1 || feof(file)) {
break;
}
incremental_put(table, line.ino, line.mtime);
incremental_put(table, line.path_md5, line.mtime);
while ((getc(file))) {}
while ((getc(file)) != 0) {}
skip_meta(file);
}
fclose(file);
@@ -452,33 +497,47 @@ void incremental_copy(store_t *store, store_t *dst_store, const char *filepath,
FILE *dst_file = fopen(dst_filepath, "ab");
line_t line;
while (1) {
size_t ret = fread((void *) &line, 1, sizeof(line_t), file);
LOG_DEBUGF("serialize.c", "Incremental copy %s", filepath)
while (TRUE) {
size_t ret = fread((void *) &line, sizeof(line_t), 1, file);
if (ret != 1 || feof(file)) {
break;
}
if (incremental_get(copy_table, line.ino)) {
// Assume that files with parents still exist.
// One way to "fix" this would be to check if the parent is marked for copy but it would consistently
// delete files with grandparents, which is a side-effect worse than having orphaned files
if (line.has_parent || incremental_get(copy_table, line.path_md5)) {
fwrite(&line, sizeof(line), 1, dst_file);
size_t buf_len;
char *buf = store_read(store, (char *) line.uuid, 16, &buf_len);
store_write(dst_store, (char *) line.uuid, 16, buf, buf_len);
free(buf);
// Copy filepath
char filepath_buf[PATH_MAX];
char c;
char *ptr = filepath_buf;
while ((c = (char) getc(file))) {
fwrite(&c, sizeof(c), 1, dst_file);
*ptr++ = c;
}
fwrite("\0", sizeof(c), 1, dst_file);
*ptr = '\0';
fwrite(filepath_buf, (ptr - filepath_buf) + 1, 1, dst_file);
enum metakey key;
// Copy tn store contents
size_t buf_len;
char path_md5[MD5_DIGEST_LENGTH];
MD5((unsigned char *) filepath_buf, (ptr - filepath_buf), (unsigned char *) path_md5);
char *buf = store_read(store, path_md5, sizeof(path_md5), &buf_len);
if (buf_len != 0) {
store_write(dst_store, path_md5, sizeof(path_md5), buf, buf_len);
free(buf);
}
enum metakey key = 0;
while (1) {
key = getc(file);
if (key == '\n') {
fread(&key, sizeof(uint16_t), 1, file);
fwrite(&key, sizeof(uint16_t), 1, dst_file);
if (key == META_NEXT) {
break;
}
fwrite(&key, sizeof(char), 1, dst_file);
if (IS_META_INT(key)) {
int val;
@@ -494,14 +553,12 @@ void incremental_copy(store_t *store, store_t *dst_store, const char *filepath,
}
fwrite("\0", sizeof(c), 1, dst_file);
}
if (ret != 1) {
break;
}
}
} else {
while ((getc(file))) {}
skip_meta(file);
}
}
fclose(file);
fclose(dst_file);
}

View File

@@ -7,14 +7,14 @@
#include <sys/syscall.h>
#include <glib.h>
typedef void(*index_func)(cJSON *, const char[UUID_STR_LEN]);
typedef void(*index_func)(cJSON *, const char[MD5_STR_LENGTH]);
void incremental_copy(store_t *store, store_t *dst_store, const char *filepath,
const char *dst_filepath, GHashTable *copy_table);
void write_document(document_t *doc);
void read_index(const char *path, const char[UUID_STR_LEN], const char *type, index_func);
void read_index(const char *path, const char[MD5_STR_LENGTH], const char *type, index_func);
void incremental_read(GHashTable *table, const char *filepath);

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);
@@ -28,26 +29,39 @@ 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);
}
void store_flush(store_t *store) {
mdb_env_sync(store->env, TRUE);
}
void store_write(store_t *store, char *key, size_t key_len, char *buf, size_t buf_len) {
if (LogCtx.very_verbose) {
char uuid_str[UUID_STR_LEN];
uuid_unparse((unsigned char *) key, uuid_str);
LOG_DEBUGF("store.c", "Store write {%s} %lu bytes", uuid_str, buf_len)
if (key_len == MD5_DIGEST_LENGTH) {
char path_md5_str[MD5_STR_LENGTH];
buf2hex((unsigned char *) key, MD5_DIGEST_LENGTH, path_md5_str);
LOG_DEBUGF("store.c", "Store write {%s} %lu bytes", path_md5_str, buf_len)
} else {
LOG_DEBUGF("store.c", "Store write {%s} %lu bytes", key, buf_len)
}
}
#if (SIST_FAKE_STORE != 1)
MDB_val mdb_key;
mdb_key.mv_data = key;
mdb_key.mv_size = key_len;
@@ -84,10 +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;
@@ -108,6 +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;
}
@@ -136,7 +154,9 @@ GHashTable *store_read_all(store_t *store) {
count += 1;
}
LOG_DEBUGF("store.c", "Read tags for %d documents", count);
const char *path;
mdb_env_get_path(store->env, &path);
LOG_DEBUGF("store.c", "Read %d entries from %s", count, path);
mdb_cursor_close(cur);
mdb_txn_abort(txn);

View File

@@ -8,6 +8,7 @@
#define STORE_SIZE_TN 1024 * 1024 * 5
#define STORE_SIZE_TAG 1024 * 16
#define STORE_SIZE_META STORE_SIZE_TAG
typedef struct store_t {
MDB_dbi dbi;
@@ -23,6 +24,8 @@ void store_destroy(store_t *store);
void store_write(store_t *store, char *key, size_t key_len, char *buf, size_t buf_len);
void store_flush(store_t *store);
char *store_read(store_t *store, char *key, size_t key_len, size_t *ret_vallen);
GHashTable *store_read_all(store_t *store);

View File

@@ -20,7 +20,7 @@ parse_job_t *create_fs_parse_job(const char *filepath, const struct stat *info,
job->vfile.info = *info;
memset(job->parent, 0, 16);
memset(job->parent, 0, MD5_DIGEST_LENGTH);
job->vfile.filepath = job->filepath;
job->vfile.read = fs_read;
@@ -41,6 +41,10 @@ int handle_entry(const char *filepath, const struct stat *info, int typeflag, st
if (ScanCtx.exclude != NULL && EXCLUDED(filepath)) {
LOG_DEBUGF("walk.c", "Excluded: %s", filepath)
pthread_mutex_lock(&ScanCtx.dbg_file_counts_mu);
ScanCtx.dbg_excluded_files_count += 1;
pthread_mutex_unlock(&ScanCtx.dbg_file_counts_mu);
return 0;
}
@@ -51,6 +55,8 @@ int handle_entry(const char *filepath, const struct stat *info, int typeflag, st
return 0;
}
#define MAX_FILE_DESCRIPTORS 64
int walk_directory_tree(const char *dirpath) {
return nftw(dirpath, handle_entry, 15, FTW_PHYS);
return nftw(dirpath, handle_entry, MAX_FILE_DESCRIPTORS, FTW_PHYS | FTW_DEPTH);
}

View File

@@ -21,7 +21,7 @@
#define EPILOG "Made by simon987 <me@simon987.net>. Released under GPL-3.0"
static const char *const Version = "2.8.3";
static const char *const Version = "2.10.3";
static const char *const usage[] = {
"sist2 scan [OPTION]... PATH",
"sist2 index [OPTION]... INDEX",
@@ -30,13 +30,77 @@ 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);
uuid_t uuid;
uuid_generate(uuid);
uuid_unparse(uuid, ScanCtx.index.desc.uuid);
unsigned char index_md5[MD5_DIGEST_LENGTH];
MD5((unsigned char *) ScanCtx.index.desc.name, strlen(ScanCtx.index.desc.name), index_md5);
buf2hex(index_md5, MD5_DIGEST_LENGTH, ScanCtx.index.desc.id);
time(&ScanCtx.index.desc.timestamp);
strcpy(ScanCtx.index.desc.version, Version);
strcpy(ScanCtx.index.desc.type, INDEX_TYPE_BIN);
@@ -98,6 +162,16 @@ 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_full(g_int64_hash, g_int64_equal, NULL, NULL);
pthread_mutex_init(&ScanCtx.dbg_current_files_mu, NULL);
pthread_mutex_init(&ScanCtx.dbg_file_counts_mu, NULL);
// Comic
ScanCtx.comic_ctx.log = _log;
@@ -117,6 +191,7 @@ void initialize_scan_context(scan_args_t *args) {
ScanCtx.ebook_ctx.log = _log;
ScanCtx.ebook_ctx.logf = _logf;
ScanCtx.ebook_ctx.store = _store;
ScanCtx.ebook_ctx.fast_epub_parse = args->fast_epub;
// Font
ScanCtx.font_ctx.enable_tn = args->size > 0;
@@ -131,6 +206,7 @@ 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
@@ -149,6 +225,14 @@ void initialize_scan_context(scan_args_t *args) {
ScanCtx.text_ctx.log = _log;
ScanCtx.text_ctx.logf = _logf;
// MSDOC
ScanCtx.msdoc_ctx.tn_size = args->size;
ScanCtx.msdoc_ctx.content_size = args->content_size;
ScanCtx.msdoc_ctx.log = _log;
ScanCtx.msdoc_ctx.logf = _logf;
ScanCtx.msdoc_ctx.store = _store;
ScanCtx.msdoc_ctx.msdoc_mime = mime_get_mime_by_string(ScanCtx.mime_table, "application/msword");
ScanCtx.threads = args->threads;
ScanCtx.depth = args->depth;
@@ -168,6 +252,37 @@ void initialize_scan_context(scan_args_t *args) {
}
void load_incremental_index(const scan_args_t *args) {
ScanCtx.original_table = incremental_get_table();
ScanCtx.copy_table = incremental_get_table();
DIR *dir = opendir(args->incremental);
if (dir == NULL) {
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) {
char file_path[PATH_MAX];
snprintf(file_path, PATH_MAX, "%s%s", args->incremental, de->d_name);
incremental_read(ScanCtx.original_table, file_path);
}
}
closedir(dir);
LOG_INFOF("main.c", "Loaded %d items in to mtime table.", g_hash_table_size(ScanCtx.original_table))
}
void sist2_scan(scan_args_t *args) {
ScanCtx.mime_table = mime_get_mime_table();
@@ -182,46 +297,28 @@ void sist2_scan(scan_args_t *args) {
mkdir(store_path, S_IWUSR | S_IRUSR | S_IXUSR);
ScanCtx.index.store = store_create(store_path, STORE_SIZE_TN);
snprintf(store_path, PATH_MAX, "%smeta", ScanCtx.index.path);
mkdir(store_path, S_IWUSR | S_IRUSR | S_IXUSR);
ScanCtx.index.meta_store = store_create(store_path, STORE_SIZE_META);
scan_print_header();
if (args->incremental != NULL) {
ScanCtx.original_table = incremental_get_table();
ScanCtx.copy_table = incremental_get_table();
DIR *dir = opendir(args->incremental);
if (dir == NULL) {
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) {
char file_path[PATH_MAX];
snprintf(file_path, PATH_MAX, "%s/%s", args->incremental, de->d_name);
incremental_read(ScanCtx.original_table, file_path);
}
}
closedir(dir);
LOG_INFOF("main.c", "Loaded %d items in to mtime table.", g_hash_table_size(ScanCtx.original_table))
load_incremental_index(args);
}
ScanCtx.pool = tpool_create(args->threads, thread_cleanup, TRUE);
tpool_start(ScanCtx.pool);
walk_directory_tree(ScanCtx.index.desc.root);
int walk_ret = walk_directory_tree(ScanCtx.index.desc.root);
if (walk_ret == -1) {
LOG_FATALF("main.c", "walk_directory_tree() failed! %s (%d)", strerror(errno), errno)
}
tpool_wait(ScanCtx.pool);
tpool_destroy(ScanCtx.pool);
generate_stats(&ScanCtx.index, args->treemap_threshold, ScanCtx.index.path);
LOG_DEBUGF("main.c", "Skipped files: %d", ScanCtx.dbg_skipped_files_count)
LOG_DEBUGF("main.c", "Excluded files: %d", ScanCtx.dbg_excluded_files_count)
LOG_DEBUGF("main.c", "Failed files: %d", ScanCtx.dbg_failed_files_count)
if (args->incremental != NULL) {
char dst_path[PATH_MAX];
@@ -238,7 +335,7 @@ void sist2_scan(scan_args_t *args) {
while ((de = readdir(dir)) != NULL) {
if (strncmp(de->d_name, "_index_", sizeof("_index_") - 1) == 0) {
char file_path[PATH_MAX];
snprintf(file_path, PATH_MAX, "%s/%s", args->incremental, de->d_name);
snprintf(file_path, PATH_MAX, "%s%s", args->incremental, de->d_name);
incremental_copy(source, ScanCtx.index.store, file_path, dst_path, ScanCtx.copy_table);
}
}
@@ -253,6 +350,8 @@ void sist2_scan(scan_args_t *args) {
store_destroy(source_tags);
}
generate_stats(&ScanCtx.index, args->treemap_threshold, ScanCtx.index.path);
store_destroy(ScanCtx.index.store);
}
@@ -263,7 +362,7 @@ void sist2_index(index_args_t *args) {
IndexCtx.batch_size = args->batch_size;
if (!args->print) {
elastic_init(args->force_reset);
elastic_init(args->force_reset, args->es_mappings, args->es_settings);
}
char descriptor_path[PATH_MAX];
@@ -289,6 +388,10 @@ void sist2_index(index_args_t *args) {
IndexCtx.tag_store = store_create(path_tmp, STORE_SIZE_TAG);
IndexCtx.tags = store_read_all(IndexCtx.tag_store);
snprintf(path_tmp, sizeof(path_tmp), "%s/meta", args->index_path);
IndexCtx.meta_store = store_create(path_tmp, STORE_SIZE_META);
IndexCtx.meta = store_read_all(IndexCtx.meta_store);
index_func f;
if (args->print) {
f = print_json;
@@ -311,7 +414,7 @@ void sist2_index(index_args_t *args) {
if (strncmp(de->d_name, "_index_", sizeof("_index_") - 1) == 0) {
char file_path[PATH_MAX];
snprintf(file_path, PATH_MAX, "%s/%s", args->index_path, de->d_name);
read_index(file_path, desc.uuid, desc.type, f);
read_index(file_path, desc.id, desc.type, f);
}
}
closedir(dir);
@@ -321,7 +424,7 @@ void sist2_index(index_args_t *args) {
tpool_destroy(IndexCtx.pool);
if (!args->print) {
finish_indexer(args->script, args->async_script, desc.uuid);
finish_indexer(args->script, args->async_script, desc.id);
}
store_destroy(IndexCtx.tag_store);
@@ -338,10 +441,11 @@ void sist2_exec_script(exec_args_t *args) {
index_descriptor_t desc = read_index_descriptor(descriptor_path);
IndexCtx.es_url = args->es_url;
IndexCtx.es_index = args->es_index;
LOG_DEBUGF("main.c", "descriptor version %s (%s)", desc.version, desc.type)
execute_update_script(args->script, args->async_script, desc.uuid);
execute_update_script(args->script, args->async_script, desc.id);
free(args->script);
}
@@ -382,6 +486,9 @@ 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();
@@ -422,6 +529,9 @@ 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"),
@@ -431,6 +541,8 @@ 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_BOOLEAN(0, "fast-epub", &scan_args->fast_epub, "Faster but less accurate EPUB parsing (no thumbnails, metadata)"),
OPT_GROUP("Index options"),
OPT_INTEGER('t', "threads", &common_threads, "Number of threads. DEFAULT=1"),
@@ -438,6 +550,8 @@ int main(int argc, const char *argv[]) {
OPT_STRING(0, "es-index", &common_es_index, "Elasticsearch index name. DEFAULT=sist2"),
OPT_BOOLEAN('p', "print", &index_args->print, "Just print JSON documents to stdout."),
OPT_STRING(0, "script-file", &common_script_path, "Path to user script."),
OPT_STRING(0, "mappings-file", &index_args->es_mappings_path, "Path to Elasticsearch mappings."),
OPT_STRING(0, "settings-file", &index_args->es_settings_path, "Path to Elasticsearch settings."),
OPT_BOOLEAN(0, "async-script", &common_async_script, "Execute user script asynchronously."),
OPT_INTEGER(0, "batch-size", &index_args->batch_size, "Index batch size. DEFAULT: 100"),
OPT_BOOLEAN('f', "force-reset", &index_args->force_reset, "Reset Elasticsearch mappings and settings. "
@@ -515,7 +629,7 @@ int main(int argc, const char *argv[]) {
}
sist2_web(web_args);
} else if (strcmp(argv[0], "exec-script") == 0) {
} else if (strcmp(argv[0], "exec-script") == 0) {
int err = exec_args_validate(exec_args, argc, argv);
if (err != 0) {

View File

@@ -6,6 +6,7 @@
#define MAJOR_MIME(mime_id) (mime_id & 0x000F0000) >> 16
#define MIME_EMPTY 1
#define MIME_SIST2_SIDECAR 2
#define DONT_PARSE 0x80000000
#define SHOULD_PARSE(mime_id) (ScanCtx.fast == 0 && (mime_id & DONT_PARSE) != DONT_PARSE && mime_id != 0)

View File

@@ -128,333 +128,334 @@ enum mime {
application_x_dvi=655480,
application_x_elc=655481,
application_x_empty=1,
application_x_envoy=655483,
application_x_esrehber=655484,
application_x_excel=655485,
application_x_executable=655486,
application_x_font_gdos=655487,
application_x_font_pf2=655488,
application_x_font_pfm=655489,
application_x_font_sfn=655490,
application_x_font_ttf=655491 | 0x20000000,
application_x_fptapplication_x_dbt=655492,
application_x_freelance=655493,
application_x_gamecube_rom=655494,
application_x_gdbm=655495,
application_x_gettext_translation=655496,
application_x_git=655497,
application_x_gsp=655498,
application_x_gss=655499,
application_x_gtar=655500,
application_x_gzip=655501,
application_x_hdf=655502,
application_x_helpfile=655503,
application_x_httpd_imap=655504,
application_x_ima=655505,
application_x_innosetup=655506,
application_x_internett_signup=655507,
application_x_inventor=655508,
application_x_ip2=655509,
application_x_java_applet=655510,
application_x_java_commerce=655511,
application_x_java_image=655512,
application_x_java_jmod=655513,
application_x_java_keystore=655514,
application_x_kdelnk=655515,
application_x_koan=655516,
application_x_latex=655517,
application_x_livescreen=655518,
application_x_lotus=655519,
application_x_lz4=655520 | 0x08000000,
application_x_lz4_json=655521,
application_x_lzh=655522,
application_x_lzh_compressed=655523,
application_x_lzip=655524 | 0x08000000,
application_x_lzma=655525 | 0x08000000,
application_x_lzop=655526 | 0x08000000,
application_x_lzx=655527,
application_x_mach_binary=655528,
application_x_mach_executable=655529,
application_x_magic_cap_package_1_0=655530,
application_x_mathcad=655531,
application_x_maxis_dbpf=655532,
application_x_meme=655533,
application_x_midi=655534,
application_x_mif=655535,
application_x_mix_transfer=655536,
application_x_mobipocket_ebook=655537 | 0x02000000,
application_x_ms_compress_szdd=655538,
application_x_ms_pdb=655539,
application_x_ms_reader=655540,
application_x_msaccess=655541,
application_x_n64_rom=655542,
application_x_navi_animation=655543,
application_x_navidoc=655544,
application_x_navimap=655545,
application_x_navistyle=655546,
application_x_nes_rom=655547,
application_x_netcdf=655548,
application_x_newton_compatible_pkg=655549,
application_x_nintendo_ds_rom=655550,
application_x_object=655551,
application_x_omc=655552,
application_x_omcdatamaker=655553,
application_x_omcregerator=655554,
application_x_pagemaker=655555,
application_x_pcl=655556,
application_x_pgp_keyring=655557,
application_x_pixclscript=655558,
application_x_pkcs7_certreqresp=655559,
application_x_pkcs7_signature=655560,
application_x_project=655561,
application_x_qpro=655562,
application_x_rar=655563 | 0x10000000,
application_x_rpm=655564,
application_x_sdp=655565,
application_x_sea=655566,
application_x_seelogo=655567,
application_x_setupscript=655568,
application_x_shar=655569,
application_x_sharedlib=655570,
application_x_shockwave_flash=655571,
application_x_snappy_framed=655572,
application_x_sprite=655573,
application_x_sqlite3=655574,
application_x_stargallery_thm=655575,
application_x_stuffit=655576,
application_x_sv4cpio=655577,
application_x_sv4crc=655578,
application_x_tar=655579 | 0x10000000,
application_x_tbook=655580,
application_x_terminfo=655581,
application_x_terminfo2=655582,
application_x_tex_tfm=655583,
application_x_texinfo=655584,
application_x_ustar=655585,
application_x_visio=655586,
application_x_vnd_audioexplosion_mzz=655587,
application_x_vnd_ls_xpix=655588,
application_x_vrml=655589,
application_x_wais_source=655590,
application_x_wine_extension_ini=655591,
application_x_wintalk=655592,
application_x_world=655593,
application_x_wri=655594,
application_x_x509_ca_cert=655595,
application_x_xz=655596 | 0x08000000,
application_x_zip=655597,
application_x_zstd=655598 | 0x08000000,
application_x_zstd_dictionary=655599,
application_xml=655600,
application_zip=655601 | 0x10000000,
application_zlib=655602,
audio_basic=458995 | 0x80000000,
audio_it=458996,
audio_make=458997,
audio_mid=458998,
audio_midi=458999,
audio_mp4=459000,
audio_mpeg=459001,
audio_ogg=459002,
audio_s3m=459003,
audio_tsp_audio=459004,
audio_tsplayer=459005,
audio_vnd_qcelp=459006,
audio_voxware=459007,
audio_x_aiff=459008,
audio_x_flac=459009,
audio_x_gsm=459010,
audio_x_hx_aac_adts=459011,
audio_x_jam=459012,
audio_x_liveaudio=459013,
audio_x_m4a=459014,
audio_x_midi=459015,
audio_x_mod=459016,
audio_x_mp4a_latm=459017,
audio_x_mpeg_3=459018,
audio_x_mpequrl=459019,
audio_x_nspaudio=459020,
audio_x_pn_realaudio=459021,
audio_x_psid=459022,
audio_x_realaudio=459023,
audio_x_s3m=459024,
audio_x_twinvq=459025,
audio_x_twinvq_plugin=459026,
audio_x_voc=459027,
audio_x_wav=459028,
audio_x_xbox_executable=459029 | 0x80000000,
audio_x_xbox360_executable=459030 | 0x80000000,
audio_xm=459031,
font_otf=327960 | 0x20000000,
font_sfnt=327961 | 0x20000000,
font_woff=327962 | 0x20000000,
font_woff2=327963 | 0x20000000,
image_bmp=524572,
image_cmu_raster=524573,
image_fif=524574,
image_florian=524575,
image_g3fax=524576,
image_gif=524577,
image_heic=524578,
image_ief=524579,
image_jpeg=524580,
image_jutvision=524581,
image_naplps=524582,
image_pict=524583,
image_png=524584,
image_svg=524585 | 0x80000000,
image_svg_xml=524586 | 0x80000000,
image_tiff=524587,
image_vnd_adobe_photoshop=524588 | 0x80000000,
image_vnd_djvu=524589 | 0x80000000,
image_vnd_fpx=524590,
image_vnd_microsoft_icon=524591,
image_vnd_rn_realflash=524592,
image_vnd_rn_realpix=524593,
image_vnd_wap_wbmp=524594,
image_vnd_xiff=524595,
image_webp=524596,
image_wmf=524597,
image_x_3ds=524598,
image_x_adobe_dng=524599 | 0x00800000,
image_x_award_bioslogo=524600,
image_x_canon_cr2=524601 | 0x00800000,
image_x_canon_crw=524602 | 0x00800000,
image_x_cmu_raster=524603,
image_x_cur=524604,
image_x_dcraw=524605 | 0x00800000,
image_x_dwg=524606,
image_x_eps=524607,
image_x_epson_erf=524608 | 0x00800000,
image_x_exr=524609,
image_x_fuji_raf=524610 | 0x00800000,
image_x_gem=524611,
image_x_icns=524612,
image_x_icon=524613 | 0x80000000,
image_x_jg=524614,
image_x_jps=524615,
image_x_kodak_dcr=524616 | 0x00800000,
image_x_kodak_k25=524617 | 0x00800000,
image_x_kodak_kdc=524618 | 0x00800000,
image_x_minolta_mrw=524619 | 0x00800000,
image_x_ms_bmp=524620,
image_x_niff=524621,
image_x_nikon_nef=524622 | 0x00800000,
image_x_olympus_orf=524623 | 0x00800000,
image_x_panasonic_raw=524624 | 0x00800000,
image_x_pcx=524625,
image_x_pentax_pef=524626 | 0x00800000,
image_x_pict=524627,
image_x_portable_bitmap=524628,
image_x_portable_graymap=524629,
image_x_portable_pixmap=524630,
image_x_quicktime=524631,
image_x_rgb=524632,
image_x_sigma_x3f=524633 | 0x00800000,
image_x_sony_arw=524634 | 0x00800000,
image_x_sony_sr2=524635 | 0x00800000,
image_x_sony_srf=524636 | 0x00800000,
image_x_tga=524637,
image_x_tiff=524638,
image_x_win_bitmap=524639,
image_x_xcf=524640 | 0x80000000,
image_x_xpixmap=524641 | 0x80000000,
image_x_xwindowdump=524642,
message_news=196963,
message_rfc822=196964,
model_vnd_dwf=65893,
model_vnd_gdl=65894,
model_vnd_gs_gdl=65895,
model_vrml=65896,
model_x_pov=65897,
text_PGP=590186,
text_asp=590187,
text_css=590188,
text_html=590189 | 0x01000000,
text_javascript=590190,
text_mcf=590191,
text_pascal=590192,
text_plain=590193,
text_richtext=590194,
text_rtf=590195,
text_scriplet=590196,
text_tab_separated_values=590197,
text_troff=590198,
text_uri_list=590199,
text_vnd_abc=590200,
text_vnd_fmi_flexstor=590201,
text_vnd_wap_wml=590202,
text_vnd_wap_wmlscript=590203,
text_webviewhtml=590204,
text_x_Algol68=590205,
text_x_asm=590206,
text_x_audiosoft_intra=590207,
text_x_awk=590208,
text_x_bcpl=590209,
text_x_c=590210,
text_x_c__=590211,
text_x_component=590212,
text_x_diff=590213,
text_x_fortran=590214,
text_x_java=590215,
text_x_la_asf=590216,
text_x_lisp=590217,
text_x_m=590218,
text_x_m4=590219,
text_x_makefile=590220,
text_x_ms_regedit=590221,
text_x_msdos_batch=590222,
text_x_objective_c=590223,
text_x_pascal=590224,
text_x_perl=590225,
text_x_php=590226,
text_x_po=590227,
text_x_python=590228,
text_x_ruby=590229,
text_x_sass=590230,
text_x_scss=590231,
text_x_server_parsed_html=590232,
text_x_setext=590233,
text_x_sgml=590234 | 0x01000000,
text_x_shellscript=590235,
text_x_speech=590236,
text_x_tcl=590237,
text_x_tex=590238,
text_x_uil=590239,
text_x_uuencode=590240,
text_x_vcalendar=590241,
text_x_vcard=590242,
text_xml=590243 | 0x01000000,
video_MP2T=393636,
video_animaflex=393637,
video_avi=393638,
video_avs_video=393639,
video_mp4=393640,
video_mpeg=393641,
video_quicktime=393642,
video_vdo=393643,
video_vivo=393644,
video_vnd_rn_realvideo=393645,
video_vosaic=393646,
video_webm=393647,
video_x_amt_demorun=393648,
video_x_amt_showrun=393649,
video_x_atomic3d_feature=393650,
video_x_dl=393651,
video_x_dv=393652,
video_x_fli=393653,
video_x_flv=393654,
video_x_isvideo=393655,
video_x_jng=393656 | 0x80000000,
video_x_m4v=393657,
video_x_matroska=393658,
video_x_mng=393659,
video_x_motion_jpeg=393660,
video_x_ms_asf=393661,
video_x_msvideo=393662,
video_x_qtc=393663,
video_x_sgi_movie=393664,
x_epoc_x_sisx_app=721345,
application_x_envoy=655482,
application_x_esrehber=655483,
application_x_excel=655484,
application_x_executable=655485,
application_x_font_gdos=655486,
application_x_font_pf2=655487,
application_x_font_pfm=655488,
application_x_font_sfn=655489,
application_x_font_ttf=655490 | 0x20000000,
application_x_fptapplication_x_dbt=655491,
application_x_freelance=655492,
application_x_gamecube_rom=655493,
application_x_gdbm=655494,
application_x_gettext_translation=655495,
application_x_git=655496,
application_x_gsp=655497,
application_x_gss=655498,
application_x_gtar=655499,
application_x_gzip=655500,
application_x_hdf=655501,
application_x_helpfile=655502,
application_x_httpd_imap=655503,
application_x_ima=655504,
application_x_innosetup=655505,
application_x_internett_signup=655506,
application_x_inventor=655507,
application_x_ip2=655508,
application_x_java_applet=655509,
application_x_java_commerce=655510,
application_x_java_image=655511,
application_x_java_jmod=655512,
application_x_java_keystore=655513,
application_x_kdelnk=655514,
application_x_koan=655515,
application_x_latex=655516,
application_x_livescreen=655517,
application_x_lotus=655518,
application_x_lz4=655519 | 0x08000000,
application_x_lz4_json=655520,
application_x_lzh=655521,
application_x_lzh_compressed=655522,
application_x_lzip=655523 | 0x08000000,
application_x_lzma=655524 | 0x08000000,
application_x_lzop=655525 | 0x08000000,
application_x_lzx=655526,
application_x_mach_binary=655527,
application_x_mach_executable=655528,
application_x_magic_cap_package_1_0=655529,
application_x_mathcad=655530,
application_x_maxis_dbpf=655531,
application_x_meme=655532,
application_x_midi=655533,
application_x_mif=655534,
application_x_mix_transfer=655535,
application_x_mobipocket_ebook=655536 | 0x02000000,
application_x_ms_compress_szdd=655537,
application_x_ms_pdb=655538,
application_x_ms_reader=655539,
application_x_msaccess=655540,
application_x_n64_rom=655541,
application_x_navi_animation=655542,
application_x_navidoc=655543,
application_x_navimap=655544,
application_x_navistyle=655545,
application_x_nes_rom=655546,
application_x_netcdf=655547,
application_x_newton_compatible_pkg=655548,
application_x_nintendo_ds_rom=655549,
application_x_object=655550,
application_x_omc=655551,
application_x_omcdatamaker=655552,
application_x_omcregerator=655553,
application_x_pagemaker=655554,
application_x_pcl=655555,
application_x_pgp_keyring=655556,
application_x_pixclscript=655557,
application_x_pkcs7_certreqresp=655558,
application_x_pkcs7_signature=655559,
application_x_project=655560,
application_x_qpro=655561,
application_x_rar=655562 | 0x10000000,
application_x_rpm=655563,
application_x_sdp=655564,
application_x_sea=655565,
application_x_seelogo=655566,
application_x_setupscript=655567,
application_x_shar=655568,
application_x_sharedlib=655569,
application_x_shockwave_flash=655570,
application_x_snappy_framed=655571,
application_x_sprite=655572,
application_x_sqlite3=655573,
application_x_stargallery_thm=655574,
application_x_stuffit=655575,
application_x_sv4cpio=655576,
application_x_sv4crc=655577,
application_x_tar=655578 | 0x10000000,
application_x_tbook=655579,
application_x_terminfo=655580,
application_x_terminfo2=655581,
application_x_tex_tfm=655582,
application_x_texinfo=655583,
application_x_ustar=655584,
application_x_visio=655585,
application_x_vnd_audioexplosion_mzz=655586,
application_x_vnd_ls_xpix=655587,
application_x_vrml=655588,
application_x_wais_source=655589,
application_x_wine_extension_ini=655590,
application_x_wintalk=655591,
application_x_world=655592,
application_x_wri=655593,
application_x_x509_ca_cert=655594,
application_x_xz=655595 | 0x08000000,
application_x_zip=655596,
application_x_zstd=655597 | 0x08000000,
application_x_zstd_dictionary=655598,
application_xml=655599,
application_zip=655600 | 0x10000000,
application_zlib=655601,
audio_basic=458994 | 0x80000000,
audio_it=458995,
audio_make=458996,
audio_mid=458997,
audio_midi=458998,
audio_mp4=458999,
audio_mpeg=459000,
audio_ogg=459001,
audio_s3m=459002,
audio_tsp_audio=459003,
audio_tsplayer=459004,
audio_vnd_qcelp=459005,
audio_voxware=459006,
audio_x_aiff=459007,
audio_x_flac=459008,
audio_x_gsm=459009,
audio_x_hx_aac_adts=459010,
audio_x_jam=459011,
audio_x_liveaudio=459012,
audio_x_m4a=459013,
audio_x_midi=459014,
audio_x_mod=459015,
audio_x_mp4a_latm=459016,
audio_x_mpeg_3=459017,
audio_x_mpequrl=459018,
audio_x_nspaudio=459019,
audio_x_pn_realaudio=459020,
audio_x_psid=459021,
audio_x_realaudio=459022,
audio_x_s3m=459023,
audio_x_twinvq=459024,
audio_x_twinvq_plugin=459025,
audio_x_voc=459026,
audio_x_wav=459027,
audio_x_xbox_executable=459028 | 0x80000000,
audio_x_xbox360_executable=459029 | 0x80000000,
audio_xm=459030,
font_otf=327959 | 0x20000000,
font_sfnt=327960 | 0x20000000,
font_woff=327961 | 0x20000000,
font_woff2=327962 | 0x20000000,
image_bmp=524571,
image_cmu_raster=524572,
image_fif=524573,
image_florian=524574,
image_g3fax=524575,
image_gif=524576,
image_heic=524577,
image_ief=524578,
image_jpeg=524579,
image_jutvision=524580,
image_naplps=524581,
image_pict=524582,
image_png=524583,
image_svg=524584 | 0x80000000,
image_svg_xml=524585 | 0x80000000,
image_tiff=524586,
image_vnd_adobe_photoshop=524587 | 0x80000000,
image_vnd_djvu=524588 | 0x80000000,
image_vnd_fpx=524589,
image_vnd_microsoft_icon=524590,
image_vnd_rn_realflash=524591,
image_vnd_rn_realpix=524592,
image_vnd_wap_wbmp=524593,
image_vnd_xiff=524594,
image_webp=524595,
image_wmf=524596,
image_x_3ds=524597,
image_x_adobe_dng=524598 | 0x00800000,
image_x_award_bioslogo=524599,
image_x_canon_cr2=524600 | 0x00800000,
image_x_canon_crw=524601 | 0x00800000,
image_x_cmu_raster=524602,
image_x_cur=524603,
image_x_dcraw=524604 | 0x00800000,
image_x_dwg=524605,
image_x_eps=524606,
image_x_epson_erf=524607 | 0x00800000,
image_x_exr=524608,
image_x_fuji_raf=524609 | 0x00800000,
image_x_gem=524610,
image_x_icns=524611,
image_x_icon=524612 | 0x80000000,
image_x_jg=524613,
image_x_jps=524614,
image_x_kodak_dcr=524615 | 0x00800000,
image_x_kodak_k25=524616 | 0x00800000,
image_x_kodak_kdc=524617 | 0x00800000,
image_x_minolta_mrw=524618 | 0x00800000,
image_x_ms_bmp=524619,
image_x_niff=524620,
image_x_nikon_nef=524621 | 0x00800000,
image_x_olympus_orf=524622 | 0x00800000,
image_x_panasonic_raw=524623 | 0x00800000,
image_x_pcx=524624,
image_x_pentax_pef=524625 | 0x00800000,
image_x_pict=524626,
image_x_portable_bitmap=524627,
image_x_portable_graymap=524628,
image_x_portable_pixmap=524629,
image_x_quicktime=524630,
image_x_rgb=524631,
image_x_sigma_x3f=524632 | 0x00800000,
image_x_sony_arw=524633 | 0x00800000,
image_x_sony_sr2=524634 | 0x00800000,
image_x_sony_srf=524635 | 0x00800000,
image_x_tga=524636,
image_x_tiff=524637,
image_x_win_bitmap=524638,
image_x_xcf=524639 | 0x80000000,
image_x_xpixmap=524640 | 0x80000000,
image_x_xwindowdump=524641,
message_news=196962,
message_rfc822=196963,
model_vnd_dwf=65892,
model_vnd_gdl=65893,
model_vnd_gs_gdl=65894,
model_vrml=65895,
model_x_pov=65896,
sist2_sidecar=2,
text_PGP=590185,
text_asp=590186,
text_css=590187,
text_html=590188 | 0x01000000,
text_javascript=590189,
text_mcf=590190,
text_pascal=590191,
text_plain=590192,
text_richtext=590193,
text_rtf=590194,
text_scriplet=590195,
text_tab_separated_values=590196,
text_troff=590197,
text_uri_list=590198,
text_vnd_abc=590199,
text_vnd_fmi_flexstor=590200,
text_vnd_wap_wml=590201,
text_vnd_wap_wmlscript=590202,
text_webviewhtml=590203,
text_x_Algol68=590204,
text_x_asm=590205,
text_x_audiosoft_intra=590206,
text_x_awk=590207,
text_x_bcpl=590208,
text_x_c=590209,
text_x_c__=590210,
text_x_component=590211,
text_x_diff=590212,
text_x_fortran=590213,
text_x_java=590214,
text_x_la_asf=590215,
text_x_lisp=590216,
text_x_m=590217,
text_x_m4=590218,
text_x_makefile=590219,
text_x_ms_regedit=590220,
text_x_msdos_batch=590221,
text_x_objective_c=590222,
text_x_pascal=590223,
text_x_perl=590224,
text_x_php=590225,
text_x_po=590226,
text_x_python=590227,
text_x_ruby=590228,
text_x_sass=590229,
text_x_scss=590230,
text_x_server_parsed_html=590231,
text_x_setext=590232,
text_x_sgml=590233 | 0x01000000,
text_x_shellscript=590234,
text_x_speech=590235,
text_x_tcl=590236,
text_x_tex=590237,
text_x_uil=590238,
text_x_uuencode=590239,
text_x_vcalendar=590240,
text_x_vcard=590241,
text_xml=590242 | 0x01000000,
video_MP2T=393635,
video_animaflex=393636,
video_avi=393637,
video_avs_video=393638,
video_mp4=393639,
video_mpeg=393640,
video_quicktime=393641,
video_vdo=393642,
video_vivo=393643,
video_vnd_rn_realvideo=393644,
video_vosaic=393645,
video_webm=393646,
video_x_amt_demorun=393647,
video_x_amt_showrun=393648,
video_x_atomic3d_feature=393649,
video_x_dl=393650,
video_x_dv=393651,
video_x_fli=393652,
video_x_flv=393653,
video_x_isvideo=393654,
video_x_jng=393655 | 0x80000000,
video_x_m4v=393656,
video_x_matroska=393657,
video_x_mng=393658,
video_x_motion_jpeg=393659,
video_x_ms_asf=393660,
video_x_msvideo=393661,
video_x_qtc=393662,
video_x_sgi_movie=393663,
x_epoc_x_sisx_app=721344,
};
char *mime_get_mime_text(unsigned int mime_id) {switch (mime_id) {
case application_arj: return "application/arj";
@@ -906,6 +907,7 @@ case image_x_sony_arw: return "image/x-sony-arw";
case image_x_sony_sr2: return "image/x-sony-sr2";
case image_x_sony_srf: return "image/x-sony-srf";
case image_x_epson_erf: return "image/x-epson-erf";
case sist2_sidecar: return "sist2/sidecar";
default: return NULL;}}
GHashTable *mime_get_ext_table() {GHashTable *ext_table = g_hash_table_new(g_str_hash, g_str_equal);
g_hash_table_insert(ext_table, "arj", (gpointer)application_arj);
@@ -1449,6 +1451,7 @@ g_hash_table_insert(ext_table, "arw", (gpointer)image_x_sony_arw);
g_hash_table_insert(ext_table, "sr2", (gpointer)image_x_sony_sr2);
g_hash_table_insert(ext_table, "srf", (gpointer)image_x_sony_srf);
g_hash_table_insert(ext_table, "erf", (gpointer)image_x_epson_erf);
g_hash_table_insert(ext_table, "s2meta", (gpointer)sist2_sidecar);
return ext_table;}
GHashTable *mime_get_mime_table() {GHashTable *mime_table = g_hash_table_new(g_str_hash, g_str_equal);
g_hash_table_insert(mime_table, "application/arj", (gpointer)application_arj);
@@ -1900,5 +1903,6 @@ g_hash_table_insert(mime_table, "image/x-sony-arw", (gpointer)image_x_sony_arw);
g_hash_table_insert(mime_table, "image/x-sony-sr2", (gpointer)image_x_sony_sr2);
g_hash_table_insert(mime_table, "image/x-sony-srf", (gpointer)image_x_sony_srf);
g_hash_table_insert(mime_table, "image/x-epson-erf", (gpointer)image_x_epson_erf);
g_hash_table_insert(mime_table, "sist2/sidecar", (gpointer)sist2_sidecar);
return mime_table;}
#endif

View File

@@ -4,6 +4,7 @@
#include "src/ctx.h"
#include "mime.h"
#include "src/io/serialize.h"
#include "src/parsing/sidecar.h"
#include <magic.h>
@@ -40,34 +41,50 @@ 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();
pthread_mutex_lock(&ScanCtx.dbg_current_files_mu);
g_hash_table_replace(ScanCtx.dbg_current_files, GINT_TO_POINTER(pid), job);
pthread_mutex_unlock(&ScanCtx.dbg_current_files_mu);
}
void parse(void *arg) {
parse_job_t *job = arg;
document_t doc;
int inc_ts = incremental_get(ScanCtx.original_table, job->vfile.info.st_ino);
if (inc_ts != 0 && inc_ts == job->vfile.info.st_mtim.tv_sec) {
incremental_mark_file_for_copy(ScanCtx.copy_table, job->vfile.info.st_ino);
return;
}
set_dbg_current_file(job);
doc.filepath = job->filepath;
doc.ext = (short) job->ext;
doc.base = (short) job->base;
char *rel_path = doc.filepath + ScanCtx.index.desc.root_len;
MD5((unsigned char *) rel_path, strlen(rel_path), doc.path_md5);
doc.meta_head = NULL;
doc.meta_tail = NULL;
doc.mime = 0;
doc.size = job->vfile.info.st_size;
doc.ino = job->vfile.info.st_ino;
doc.mtime = job->vfile.info.st_mtim.tv_sec;
uuid_generate(doc.uuid);
int inc_ts = incremental_get(ScanCtx.original_table, doc.path_md5);
if (inc_ts != 0 && inc_ts == job->vfile.info.st_mtim.tv_sec) {
incremental_mark_file_for_copy(ScanCtx.copy_table, doc.path_md5);
pthread_mutex_lock(&ScanCtx.dbg_file_counts_mu);
ScanCtx.dbg_skipped_files_count += 1;
pthread_mutex_unlock(&ScanCtx.dbg_file_counts_mu);
return;
}
char *buf[MAGIC_BUF_SIZE];
if (LogCtx.very_verbose) {
char uuid_str[UUID_STR_LEN];
uuid_unparse(doc.uuid, uuid_str);
LOG_DEBUGF(job->filepath, "Starting parse job {%s}", uuid_str)
char path_md5_str[MD5_STR_LENGTH];
buf2hex(doc.path_md5, MD5_DIGEST_LENGTH, path_md5_str);
LOG_DEBUGF(job->filepath, "Starting parse job {%s}", path_md5_str)
}
if (job->vfile.info.st_size == 0) {
@@ -85,7 +102,8 @@ void parse(void *arg) {
// Get mime type with libmagic
if (!job->vfile.is_fs_file) {
LOG_WARNING(job->filepath, "Guessing mime type with libmagic inside archive files is not currently supported");
LOG_WARNING(job->filepath,
"Guessing mime type with libmagic inside archive files is not currently supported");
goto abort;
}
@@ -99,6 +117,10 @@ void parse(void *arg) {
}
CLOSE_FILE(job->vfile)
pthread_mutex_lock(&ScanCtx.dbg_file_counts_mu);
ScanCtx.dbg_failed_files_count += 1;
pthread_mutex_unlock(&ScanCtx.dbg_file_counts_mu);
return;
}
@@ -157,16 +179,26 @@ void parse(void *arg) {
parse_comic(&ScanCtx.comic_ctx, &job->vfile, &doc);
} else if (IS_MOBI(doc.mime)) {
parse_mobi(&ScanCtx.mobi_ctx, &job->vfile, &doc);
} else if (doc.mime == MIME_SIST2_SIDECAR) {
parse_sidecar(&job->vfile, &doc);
CLOSE_FILE(job->vfile)
return;
} else if (is_msdoc(&ScanCtx.msdoc_ctx, doc.mime)) {
parse_msdoc(&ScanCtx.msdoc_ctx, &job->vfile, &doc);
}
abort:
//Parent meta
if (!uuid_is_null(job->parent)) {
meta_line_t *meta_parent = malloc(sizeof(meta_line_t) + UUID_STR_LEN + 1);
if (!md5_digest_is_null(job->parent)) {
meta_line_t *meta_parent = malloc(sizeof(meta_line_t) + MD5_STR_LENGTH);
meta_parent->key = MetaParent;
uuid_unparse(job->parent, meta_parent->str_val);
buf2hex(job->parent, MD5_DIGEST_LENGTH, meta_parent->str_val);
APPEND_META((&doc), meta_parent)
doc.has_parent = TRUE;
} else {
doc.has_parent = FALSE;
}
write_document(&doc);

35
src/parsing/sidecar.c Normal file
View File

@@ -0,0 +1,35 @@
#include "sidecar.h"
#include "src/ctx.h"
void parse_sidecar(vfile_t *vfile, document_t *doc) {
LOG_DEBUGF("sidecar.c", "Parsing sidecar file %s", vfile->filepath)
size_t size;
char *buf = read_all(vfile, &size);
if (buf == NULL) {
LOG_ERRORF("sidecar.c", "Read error for %s", vfile->filepath)
return;
}
buf = realloc(buf, size + 1);
*(buf + size) = '\0';
cJSON *json = cJSON_Parse(buf);
if (json == NULL) {
LOG_ERRORF("sidecar.c", "Could not parse JSON sidecar %s", vfile->filepath)
return;
}
char *json_str = cJSON_PrintUnformatted(json);
unsigned char path_md5[MD5_DIGEST_LENGTH];
MD5((unsigned char *) vfile->filepath + ScanCtx.index.desc.root_len, doc->ext - 1 - ScanCtx.index.desc.root_len,
path_md5);
store_write(ScanCtx.index.meta_store, (char *) path_md5, sizeof(path_md5), json_str, strlen(json_str) + 1);
cJSON_Delete(json);
free(json_str);
free(buf);
}

8
src/parsing/sidecar.h Normal file
View File

@@ -0,0 +1,8 @@
#ifndef SIST2_SIDECAR_H
#define SIST2_SIDECAR_H
#include "src/sist.h"
void parse_sidecar(vfile_t *vfile, document_t *doc);
#endif

View File

@@ -23,9 +23,10 @@
#undef ABS
#define ABS(a) (((a) < 0) ? -(a) : (a))
#define UUID_STR_LEN 37
#define UNUSED(x) __attribute__((__unused__)) x
#define MD5_STR_LENGTH 33
#include "util.h"
#include "log.h"
#include "types.h"
@@ -47,5 +48,4 @@
#include <errno.h>
#include <ctype.h>
#endif

View File

@@ -1 +1 @@
.irs-bar,.irs-bar-edge,.irs-line-left,.irs-line-mid,.irs-line-right,.irs-slider{background:url("../img/sprite-skin-flat.png") repeat-x}.irs{height:40px}.irs-with-grid{height:60px}.irs-line{height:12px;top:25px}.irs-line-left{height:12px;background-position:0 -30px}.irs-line-mid{height:12px;background-position:0 0}.irs-line-right{height:12px;background-position:100% -30px}.irs-bar{height:12px;top:25px;background-position:0 -60px}.irs-bar-edge{top:25px;height:12px;width:9px;background-position:0 -90px}.irs-shadow{height:3px;top:34px;background:#000;opacity:0.25}.lt-ie9 .irs-shadow{filter: alpha(opacity=25)}.irs-slider{width:16px;height:18px;top:22px;background-position:0 -120px}.irs-slider.state_hover,.irs-slider:hover{background-position:0 -150px}.irs-max,.irs-min{color:#999;font-size:10px;line-height:1.333;text-shadow:none;top:0;padding:1px 3px;background:#e1e4e9;-moz-border-radius:4px;border-radius:4px}.irs-from,.irs-single,.irs-to{color:#fff;font-size:10px;line-height:1.333;text-shadow:none;padding:1px 5px;background:#2196F3;-moz-border-radius:4px;border-radius:4px}.irs-from:after,.irs-single:after,.irs-to:after{position:absolute;display:block;content:"";bottom:-6px;left:50%;width:0;height:0;margin-left:-3px;overflow:hidden;border:3px solid transparent;border-top-color:#2196F3}.irs-grid-pol{background:#e1e4e9}.irs-grid-text{color:#999}.irs-disabled{}
.irs-bar,.irs-bar-edge,.irs-line-left,.irs-line-mid,.irs-line-right,.irs-slider{background:url("./img/sprite-skin-flat.png") repeat-x}.irs{height:40px}.irs-with-grid{height:60px}.irs-line{height:12px;top:25px}.irs-line-left{height:12px;background-position:0 -30px}.irs-line-mid{height:12px;background-position:0 0}.irs-line-right{height:12px;background-position:100% -30px}.irs-bar{height:12px;top:25px;background-position:0 -60px}.irs-bar-edge{top:25px;height:12px;width:9px;background-position:0 -90px}.irs-shadow{height:3px;top:34px;background:#000;opacity:0.25}.lt-ie9 .irs-shadow{filter: alpha(opacity=25)}.irs-slider{width:16px;height:18px;top:22px;background-position:0 -120px}.irs-slider.state_hover,.irs-slider:hover{background-position:0 -150px}.irs-max,.irs-min{color:#999;font-size:10px;line-height:1.333;text-shadow:none;top:0;padding:1px 3px;background:#e1e4e9;-moz-border-radius:4px;border-radius:4px}.irs-from,.irs-single,.irs-to{color:#fff;font-size:10px;line-height:1.333;text-shadow:none;padding:1px 5px;background:#2196F3;-moz-border-radius:4px;border-radius:4px}.irs-from:after,.irs-single:after,.irs-to:after{position:absolute;display:block;content:"";bottom:-6px;left:50%;width:0;height:0;margin-left:-3px;overflow:hidden;border:3px solid transparent;border-top-color:#2196F3}.irs-grid-pol{background:#e1e4e9}.irs-grid-text{color:#999}.irs-disabled{}

1
src/static/js/8_md5.min.js vendored Normal file
View File

@@ -0,0 +1 @@
!function(n){"use strict";function d(n,t){var r=(65535&n)+(65535&t);return(n>>16)+(t>>16)+(r>>16)<<16|65535&r}function f(n,t,r,e,o,u){return d((c=d(d(t,n),d(e,u)))<<(f=o)|c>>>32-f,r);var c,f}function l(n,t,r,e,o,u,c){return f(t&r|~t&e,n,t,o,u,c)}function v(n,t,r,e,o,u,c){return f(t&e|r&~e,n,t,o,u,c)}function g(n,t,r,e,o,u,c){return f(t^r^e,n,t,o,u,c)}function m(n,t,r,e,o,u,c){return f(r^(t|~e),n,t,o,u,c)}function i(n,t){var r,e,o,u;n[t>>5]|=128<<t%32,n[14+(t+64>>>9<<4)]=t;for(var c=1732584193,f=-271733879,i=-1732584194,a=271733878,h=0;h<n.length;h+=16)c=l(r=c,e=f,o=i,u=a,n[h],7,-680876936),a=l(a,c,f,i,n[h+1],12,-389564586),i=l(i,a,c,f,n[h+2],17,606105819),f=l(f,i,a,c,n[h+3],22,-1044525330),c=l(c,f,i,a,n[h+4],7,-176418897),a=l(a,c,f,i,n[h+5],12,1200080426),i=l(i,a,c,f,n[h+6],17,-1473231341),f=l(f,i,a,c,n[h+7],22,-45705983),c=l(c,f,i,a,n[h+8],7,1770035416),a=l(a,c,f,i,n[h+9],12,-1958414417),i=l(i,a,c,f,n[h+10],17,-42063),f=l(f,i,a,c,n[h+11],22,-1990404162),c=l(c,f,i,a,n[h+12],7,1804603682),a=l(a,c,f,i,n[h+13],12,-40341101),i=l(i,a,c,f,n[h+14],17,-1502002290),c=v(c,f=l(f,i,a,c,n[h+15],22,1236535329),i,a,n[h+1],5,-165796510),a=v(a,c,f,i,n[h+6],9,-1069501632),i=v(i,a,c,f,n[h+11],14,643717713),f=v(f,i,a,c,n[h],20,-373897302),c=v(c,f,i,a,n[h+5],5,-701558691),a=v(a,c,f,i,n[h+10],9,38016083),i=v(i,a,c,f,n[h+15],14,-660478335),f=v(f,i,a,c,n[h+4],20,-405537848),c=v(c,f,i,a,n[h+9],5,568446438),a=v(a,c,f,i,n[h+14],9,-1019803690),i=v(i,a,c,f,n[h+3],14,-187363961),f=v(f,i,a,c,n[h+8],20,1163531501),c=v(c,f,i,a,n[h+13],5,-1444681467),a=v(a,c,f,i,n[h+2],9,-51403784),i=v(i,a,c,f,n[h+7],14,1735328473),c=g(c,f=v(f,i,a,c,n[h+12],20,-1926607734),i,a,n[h+5],4,-378558),a=g(a,c,f,i,n[h+8],11,-2022574463),i=g(i,a,c,f,n[h+11],16,1839030562),f=g(f,i,a,c,n[h+14],23,-35309556),c=g(c,f,i,a,n[h+1],4,-1530992060),a=g(a,c,f,i,n[h+4],11,1272893353),i=g(i,a,c,f,n[h+7],16,-155497632),f=g(f,i,a,c,n[h+10],23,-1094730640),c=g(c,f,i,a,n[h+13],4,681279174),a=g(a,c,f,i,n[h],11,-358537222),i=g(i,a,c,f,n[h+3],16,-722521979),f=g(f,i,a,c,n[h+6],23,76029189),c=g(c,f,i,a,n[h+9],4,-640364487),a=g(a,c,f,i,n[h+12],11,-421815835),i=g(i,a,c,f,n[h+15],16,530742520),c=m(c,f=g(f,i,a,c,n[h+2],23,-995338651),i,a,n[h],6,-198630844),a=m(a,c,f,i,n[h+7],10,1126891415),i=m(i,a,c,f,n[h+14],15,-1416354905),f=m(f,i,a,c,n[h+5],21,-57434055),c=m(c,f,i,a,n[h+12],6,1700485571),a=m(a,c,f,i,n[h+3],10,-1894986606),i=m(i,a,c,f,n[h+10],15,-1051523),f=m(f,i,a,c,n[h+1],21,-2054922799),c=m(c,f,i,a,n[h+8],6,1873313359),a=m(a,c,f,i,n[h+15],10,-30611744),i=m(i,a,c,f,n[h+6],15,-1560198380),f=m(f,i,a,c,n[h+13],21,1309151649),c=m(c,f,i,a,n[h+4],6,-145523070),a=m(a,c,f,i,n[h+11],10,-1120210379),i=m(i,a,c,f,n[h+2],15,718787259),f=m(f,i,a,c,n[h+9],21,-343485551),c=d(c,r),f=d(f,e),i=d(i,o),a=d(a,u);return[c,f,i,a]}function a(n){for(var t="",r=32*n.length,e=0;e<r;e+=8)t+=String.fromCharCode(n[e>>5]>>>e%32&255);return t}function h(n){var t=[];for(t[(n.length>>2)-1]=void 0,e=0;e<t.length;e+=1)t[e]=0;for(var r=8*n.length,e=0;e<r;e+=8)t[e>>5]|=(255&n.charCodeAt(e/8))<<e%32;return t}function e(n){for(var t,r="0123456789abcdef",e="",o=0;o<n.length;o+=1)t=n.charCodeAt(o),e+=r.charAt(t>>>4&15)+r.charAt(15&t);return e}function r(n){return unescape(encodeURIComponent(n))}function o(n){return a(i(h(t=r(n)),8*t.length));var t}function u(n,t){return function(n,t){var r,e,o=h(n),u=[],c=[];for(u[15]=c[15]=void 0,16<o.length&&(o=i(o,8*n.length)),r=0;r<16;r+=1)u[r]=909522486^o[r],c[r]=1549556828^o[r];return e=i(u.concat(h(t)),512+8*t.length),a(i(c.concat(e),640))}(r(n),r(t))}function t(n,t,r){return t?r?u(t,n):e(u(t,n)):r?o(n):e(o(n))}"function"==typeof define&&define.amd?define(function(){return t}):"object"==typeof module&&module.exports?module.exports=t:n.md5=t}(this);

View File

@@ -22,7 +22,7 @@ function gifOver(thumbnail, hit) {
thumbnail.addEventListener("mouseout", function () {
//Reset timer
thumbnail.mouseStayedOver = false;
thumbnail.setAttribute("src", `t/${hit["_source"]["index"]}/${hit["_id"]}`);
thumbnail.setAttribute("src", `t/${hit["_source"]["index"]}/${hit["_path_md5"]}`);
})
}
@@ -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
$("audio").each(function () {
if (this !== audio) {
this.pause();
}
});
});
docCard.appendChild(audio)
}
@@ -419,7 +452,7 @@ function makeThumbnail(mimeCategory, hit, imgWrapper, small) {
thumbnail.setAttribute("class", "card-img-top fit");
}
}
thumbnail.setAttribute("src", `t/${hit["_source"]["index"]}/${hit["_id"]}`);
thumbnail.setAttribute("src", `t/${hit["_source"]["index"]}/${hit["_path_md5"]}`);
if (shouldDisplayRawImage(hit)) {
thumbnail.addEventListener("click", () => {

View File

@@ -165,16 +165,19 @@ window.onload = () => {
}
}
});
initTagTree();
updateTagTree();
};
function saveTag(tag, hit) {
const relPath = hit["_source"]["path"] + "/" + hit["_source"]["name"] + ext(hit);
const relPath = hit["_source"]["path"] + (hit["_source"]["path"] ? "/" : "") + hit["_source"]["name"] + ext(hit);
return $.jsonPost("/tag/" + hit["_source"]["index"], {
delete: false,
name: tag,
doc_id: hit["_id"],
relpath: relPath
path_md5: md5(relPath)
}).then(() => {
tagBar.blur();
$("#tagModal").modal("hide");
@@ -188,6 +191,8 @@ function saveTag(tag, hit) {
hideAfter: 3000,
loaderBg: "#08c7e8",
});
window.setTimeout(updateTagTree, 2000);
})
}
@@ -198,7 +203,7 @@ function deleteTag(tag, hit) {
delete: true,
name: tag,
doc_id: hit["_id"],
relpath: relPath
path_md5: md5(relPath)
}).then(() => {
$.toast({
heading: "Tag deleted",
@@ -210,6 +215,8 @@ function deleteTag(tag, hit) {
hideAfter: 3000,
loaderBg: "#08c7e8",
});
window.setTimeout(updateTagTree, 2000);
})
}
@@ -313,25 +320,8 @@ $.jsonPost("es", {
mimeTree.node("any").select();
});
// Tags tree
$.jsonPost("es", {
aggs: {
tags: {
terms: {
field: "tag",
size: 10000
}
}
},
size: 0,
}).then(resp => {
resp["aggregations"]["tags"]["buckets"]
.sort((a, b) => a["key"].localeCompare(b["key"]))
.forEach(bucket => {
addTag(tagMap, bucket["key"], bucket["key"], bucket["doc_count"])
});
tagMap.push({"text": "All", "id": "any"});
function initTagTree() {
tagMap = [{text: "All", id: "any"}];
tagTree = new InspireTree({
selection: {
mode: 'checkbox'
@@ -346,8 +336,34 @@ $.jsonPost("es", {
});
tagTree.on("node.state.changed", handleTreeClick(tagTree));
tagTree.node("any").select();
searchBusy = false;
});
}
function updateTagTree() {
$.jsonPost("es", {
aggs: {
tags: {
terms: {
field: "tag",
size: 10000
}
}
},
size: 0,
}).then(resp => {
tagMap = [];
resp["aggregations"]["tags"]["buckets"]
.sort((a, b) => a["key"].localeCompare(b["key"]))
.forEach(bucket => {
addTag(tagMap, bucket["key"], bucket["key"], bucket["doc_count"])
});
tagTree.removeAll();
tagMap.push({text: "All", id: "any"})
tagTree.addNodes(tagMap);
searchBusy = false;
});
}
function addTag(map, tag, id, count) {
// let tags = tag.split("#")[0].split(".");
@@ -495,8 +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}}},
@@ -545,19 +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
}
},
@@ -595,7 +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];
@@ -604,6 +635,7 @@ function search(after = null) {
hits.forEach(hit => {
hit["_source"]["name"] = strUnescape(hit["_source"]["name"]);
hit["_source"]["path"] = strUnescape(hit["_source"]["path"]);
hit["_path_md5"] = md5(hit["_source"]["path"] + (hit["_source"]["path"] ? "/" : "") + hit["_source"]["name"] + ext(hit));
});
if (!after) {
@@ -628,7 +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

@@ -12,9 +12,9 @@
<nav class="navbar navbar-expand-lg">
<a class="navbar-brand" href="/">sist2</a>
<span class="badge badge-pill version">2.8.3</span>
<span class="badge badge-pill version">2.10.3</span>
<span class="tagline">Lightning-fast file system indexer and search tool </span>
<a class="btn ml-auto" href="/stats">Stats</a>
<a class="btn ml-auto" href="stats">Stats</a>
<button class="btn" type="button" data-toggle="modal" data-target="#settings" onclick="loadSettings()">Settings
</button>
<button class="btn" title="Toggle theme" onclick="toggleTheme()">Theme</button>
@@ -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">2.8.3</span>
<span class="badge badge-pill version">2.10.3</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"
@@ -29,13 +29,13 @@
</div>
<div id="treemap-card" class="stats-card">
<button class="btn stats-btn" onclick="fullScreen('treemap-card')">Enlarge</button>
<button class="btn stats-btn" onclick="fullScreen('treemap-card')" id="treemap-card-enlarge">Enlarge</button>
<button class="btn stats-btn" onclick="exportTreemap()">Export</button>
<svg id="treemap"></svg>
</div>
<div id="graphs-card" class="stats-card">
<button class="btn stats-btn" onclick="fullScreen('graphs-card')">Enlarge</button>
<button class="btn stats-btn" onclick="fullScreen('graphs-card')" id="graphs-card-enlarge">Enlarge</button>
<div class="graph">
<svg id="agg_mime_size"></svg>
</div>
@@ -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>
@@ -727,7 +733,7 @@ function updateStats() {
const indexId = $("#indices").val();
d3.csv(`/s/${indexId}/1`).then(tabularData => {
d3.csv(`./s/${indexId}/1`).then(tabularData => {
tabularData.forEach(row => {
row.taxonomy = row.path.split("/");
row.size = Number(row.size);
@@ -742,16 +748,16 @@ function updateStats() {
}
});
d3.csv(`/s/${indexId}/2`).then(tabularData => {
d3.csv(`./s/${indexId}/2`).then(tabularData => {
mimeBarSize(tabularData.slice(), mimeSvgSize);
mimeBarCount(tabularData.slice(), mimeSvgCount);
});
d3.csv(`/s/${indexId}/3`).then(tabularData => {
d3.csv(`./s/${indexId}/3`).then(tabularData => {
sizeHistogram(tabularData, sizeHistogramSvg);
});
d3.csv(`/s/${indexId}/4`).then(tabularData => {
d3.csv(`./s/${indexId}/4`).then(tabularData => {
dateHistogram(tabularData, dateHistogramSvg);
});
@@ -789,7 +795,15 @@ window.onload = function () {
function fullScreen(selector) {
const card = document.getElementById(selector);
const btn = document.getElementById(selector + "-enlarge");
card.classList.toggle("full-screen");
if (card.classList.contains("full-screen")) {
btn.innerText = "Shrink";
} else {
btn.innerText = "Enlarge";
}
}
function exportTreemap() {

View File

@@ -2,8 +2,6 @@
#include "io/serialize.h"
#include "ctx.h"
#include <glib.h>
static GHashTable *FlatTree;
static GHashTable *BufferTable;
@@ -22,7 +20,7 @@ typedef struct {
long count;
} agg_t;
void fill_tables(cJSON *document, UNUSED(const char uuid_str[UUID_STR_LEN])) {
void fill_tables(cJSON *document, UNUSED(const char index_id[MD5_STR_LENGTH])) {
if (cJSON_GetObjectItem(document, "parent") != NULL) {
return;
@@ -103,8 +101,8 @@ void read_index_into_tables(index_t *index) {
while ((de = readdir(dir)) != NULL) {
if (strncmp(de->d_name, "_index_", sizeof("_index_") - 1) == 0) {
char file_path[PATH_MAX];
snprintf(file_path, PATH_MAX, "%s/%s", index->path, de->d_name);
read_index(file_path, index->desc.uuid, index->desc.type, fill_tables);
snprintf(file_path, PATH_MAX, "%s%s", index->path, de->d_name);
read_index(file_path, index->desc.id, index->desc.type, fill_tables);
}
}
closedir(dir);

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);
@@ -27,6 +27,7 @@ typedef struct tpool {
int thread_cnt;
int work_cnt;
int done_cnt;
int busy_cnt;
int free_arg;
int stop;
@@ -52,6 +53,14 @@ 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->busy_cnt = %d", pool->busy_cnt)
LOG_DEBUGF("tpool.c", "pool->stop = %d", pool->stop)
}
/**
* Pop work object from thread pool
*/
@@ -83,7 +92,7 @@ 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));
@@ -120,6 +129,10 @@ static void *tpool_worker(void *arg) {
}
tpool_work_t *work = tpool_work_get(pool);
if (work != NULL) {
pool->busy_cnt += 1;
}
pthread_mutex_unlock(&(pool->work_mutex));
if (work != NULL) {
@@ -136,6 +149,7 @@ static void *tpool_worker(void *arg) {
pthread_mutex_lock(&(pool->work_mutex));
if (work != NULL) {
pool->busy_cnt -= 1;
pool->done_cnt++;
}
@@ -150,6 +164,7 @@ 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));
@@ -160,14 +175,14 @@ static void *tpool_worker(void *arg) {
void tpool_wait(tpool_t *pool) {
LOG_INFO("tpool.c", "Waiting for worker threads to finish")
pthread_mutex_lock(&(pool->work_mutex));
while (1) {
while (TRUE) {
if (pool->done_cnt < pool->work_cnt) {
pthread_cond_wait(&(pool->working_cond), &(pool->work_mutex));
} else {
usleep(500000);
if (pool->done_cnt == pool->work_cnt) {
pool->stop = 1;
usleep(1000000);
LOG_INFOF("tpool.c", "Received head=NULL signal, busy_cnt=%d", pool->busy_cnt);
if (pool->done_cnt == pool->work_cnt && pool->busy_cnt == 0) {
pool->stop = TRUE;
break;
}
}
@@ -187,12 +202,16 @@ void tpool_destroy(tpool_t *pool) {
pthread_mutex_lock(&(pool->work_mutex));
tpool_work_t *work = pool->work_head;
int count = 0;
while (work != NULL) {
tpool_work_t *tmp = work->next;
free(work);
work = tmp;
count += 1;
}
LOG_DEBUGF("tpool.c", "Destroyed %d jobs", count);
pthread_cond_broadcast(&(pool->has_work_cond));
pthread_mutex_unlock(&(pool->work_mutex));
@@ -218,13 +237,14 @@ void tpool_destroy(tpool_t *pool) {
* Create a thread pool
* @param thread_cnt Worker threads count
*/
tpool_t *tpool_create(size_t thread_cnt, void cleanup_func(), int free_arg) {
tpool_t *tpool_create(int thread_cnt, void cleanup_func(), int free_arg) {
tpool_t *pool = malloc(sizeof(tpool_t));
pool->thread_cnt = thread_cnt;
pool->work_cnt = 0;
pool->done_cnt = 0;
pool->stop = 0;
pool->busy_cnt = 0;
pool->stop = FALSE;
pool->free_arg = free_arg;
pool->cleanup_func = cleanup_func;
pool->threads = calloc(sizeof(pthread_t), thread_cnt);

View File

@@ -8,12 +8,14 @@ typedef struct tpool tpool_t;
typedef void (*thread_func_t)(void *arg);
tpool_t *tpool_create(size_t num, void (*cleanup_func)(), int free_arg);
tpool_t *tpool_create(int 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

@@ -6,7 +6,7 @@
#define INDEX_VERSION_EXTERNAL "_external_v1"
typedef struct index_descriptor {
char uuid[UUID_STR_LEN];
char id[MD5_STR_LENGTH];
char version[64];
long timestamp;
char root[PATH_MAX];
@@ -20,6 +20,7 @@ typedef struct index_t {
struct index_descriptor desc;
struct store_t *store;
struct store_t *tag_store;
struct store_t *meta_store;
char path[PATH_MAX];
} index_t;

View File

@@ -2,7 +2,6 @@
#include "src/ctx.h"
#include <wordexp.h>
#include <glib.h>
#define PBSTR "========================================"
#define PBWIDTH 40
@@ -125,7 +124,7 @@ void progress_bar_print(double percentage, size_t tn_size, size_t index_size) {
}
GHashTable *incremental_get_table() {
GHashTable *file_table = g_hash_table_new(g_direct_hash, g_direct_equal);
GHashTable *file_table = g_hash_table_new_full(g_str_hash, g_str_equal, free, NULL);
return file_table;
}

View File

@@ -10,6 +10,8 @@
#include "third-party/utf8.h/utf8.h"
#include "libscan/scan.h"
#define MD5_STR_LENGTH 33
char *abspath(const char *path);
@@ -21,25 +23,6 @@ void progress_bar_print(double percentage, size_t tn_size, size_t index_size);
GHashTable *incremental_get_table();
__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) {
return g_hash_table_insert(table, GINT_TO_POINTER(inode_no), GINT_TO_POINTER(1));
}
const char *find_file_in_paths(const char **paths, const char *filename);
@@ -48,4 +31,95 @@ void str_escape(char *dst, const char *str);
void str_unescape(char *dst, const char *str);
static int hex2buf(const char *str, int len, unsigned char *bytes) {
static const uint8_t hashmap[] = {
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
0x08, 0x09, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
};
for (int pos = 0; pos < len; pos += 2) {
int idx0 = (uint8_t) str[pos + 0];
int idx1 = (uint8_t) str[pos + 1];
bytes[pos / 2] = (uint8_t) (hashmap[idx0] << 4) | hashmap[idx1];
}
return TRUE;
}
__always_inline
static void buf2hex(const unsigned char *buf, size_t buflen, char *hex_string) {
static const char hexdig[] = "0123456789abcdef";
const unsigned char *p;
size_t i;
char *s = hex_string;
for (i = 0, p = buf; i < buflen; i++, p++) {
*s++ = hexdig[(*p >> 4) & 0x0f];
*s++ = hexdig[*p & 0x0f];
}
*s = '\0';
}
__always_inline
static int md5_digest_is_null(const unsigned char digest[MD5_DIGEST_LENGTH]) {
return (*(int64_t *) digest) == 0 && (*((int64_t *) digest + 1)) == 0;
}
__always_inline
static void incremental_put(GHashTable *table, unsigned char path_md5[MD5_DIGEST_LENGTH], int mtime) {
char *ptr = malloc(MD5_STR_LENGTH);
buf2hex(path_md5, MD5_DIGEST_LENGTH, ptr);
g_hash_table_insert(table, ptr, GINT_TO_POINTER(mtime));
}
__always_inline
static int incremental_get(GHashTable *table, unsigned char path_md5[MD5_DIGEST_LENGTH]) {
if (table != NULL) {
char md5_str[MD5_STR_LENGTH];
buf2hex(path_md5, MD5_DIGEST_LENGTH, md5_str);
return GPOINTER_TO_INT(g_hash_table_lookup(table, md5_str));
} else {
return 0;
}
}
__always_inline
static int incremental_mark_file_for_copy(GHashTable *table, unsigned char path_md5[MD5_DIGEST_LENGTH]) {
char *ptr = malloc(MD5_STR_LENGTH);
buf2hex(path_md5, MD5_DIGEST_LENGTH, ptr);
return g_hash_table_insert(table, ptr, GINT_TO_POINTER(1));
}
#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"
@@ -36,7 +26,7 @@ static void send_response_line(struct mg_connection *nc, int status_code, int le
index_t *get_index_by_id(const char *index_id) {
for (int i = WebCtx.index_count; i >= 0; i--) {
if (strcmp(index_id, WebCtx.indices[i].desc.uuid) == 0) {
if (strncmp(index_id, WebCtx.indices[i].desc.id, MD5_STR_LENGTH) == 0) {
return &WebCtx.indices[i];
}
}
@@ -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 != UUID_STR_LEN + 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_uuid[UUID_STR_LEN];
memcpy(arg_uuid, hm->uri.p + 3, UUID_STR_LEN);
*(arg_uuid + UUID_STR_LEN - 1) = '\0';
char arg_md5[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_uuid);
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 + UUID_STR_LEN)) {
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));
@@ -173,71 +144,62 @@ 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 != UUID_STR_LEN * 2 + 2) {
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_uuid[UUID_STR_LEN];
char arg_index[UUID_STR_LEN];
char arg_file_md5[MD5_STR_LENGTH];
char arg_index[MD5_STR_LENGTH];
memcpy(arg_index, hm->uri.p + 3, UUID_STR_LEN);
*(arg_index + UUID_STR_LEN - 1) = '\0';
memcpy(arg_uuid, hm->uri.p + 3 + UUID_STR_LEN, UUID_STR_LEN);
*(arg_uuid + UUID_STR_LEN - 1) = '\0';
memcpy(arg_index, hm->uri.ptr + 3, MD5_STR_LENGTH);
*(arg_index + MD5_STR_LENGTH - 1) = '\0';
memcpy(arg_file_md5, hm->uri.ptr + 3 + MD5_STR_LENGTH, MD5_STR_LENGTH);
*(arg_file_md5 + MD5_STR_LENGTH - 1) = '\0';
uuid_t uuid;
int ret = uuid_parse(arg_uuid, uuid);
if (ret != 0) {
LOG_DEBUGF("serve.c", "Invalid thumbnail UUID: %s", arg_uuid)
mg_http_send_error(nc, 404, NULL);
nc->flags |= MG_F_SEND_AND_CLOSE;
return;
}
unsigned char md5_buf[MD5_DIGEST_LENGTH];
hex2buf(arg_file_md5, MD5_STR_LENGTH - 1, md5_buf);
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;
}
size_t data_len = 0;
char *data = store_read(store, (char *) uuid, sizeof(uuid_t), &data_len);
char *data = store_read(store, (char *) md5_buf, sizeof(md5_buf), &data_len);
if (data_len != 0) {
send_response_line(nc, 200, data_len, "Content-Type: image/jpeg");
mg_send(nc, data, data_len);
free(data);
} else {
mg_http_reply(nc, 404, "Content-Type: text/plain;charset=utf-8\r\n", "Not found");
return;
}
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) {
@@ -259,16 +221,16 @@ 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');
char location_header[8192];
snprintf(location_header, sizeof(location_header), "Location: %s\r\n", encoded.buf);
mg_http_reply(nc, 308, location_header, "");
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;
@@ -289,10 +251,10 @@ 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) {
@@ -305,7 +267,7 @@ void index_info(struct mg_connection *nc) {
cJSON *idx_json = cJSON_CreateObject();
cJSON_AddStringToObject(idx_json, "name", idx->desc.name);
cJSON_AddStringToObject(idx_json, "version", idx->desc.version);
cJSON_AddStringToObject(idx_json, "id", idx->desc.uuid);
cJSON_AddStringToObject(idx_json, "id", idx->desc.id);
cJSON_AddNumberToObject(idx_json, "timestamp", (double) idx->desc.timestamp);
cJSON_AddItemToArray(arr, idx_json);
}
@@ -316,40 +278,35 @@ 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 != UUID_STR_LEN + 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_uuid[UUID_STR_LEN];
memcpy(arg_uuid, hm->uri.p + 3, UUID_STR_LEN);
*(arg_uuid + UUID_STR_LEN - 1) = '\0';
char arg_md5[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_uuid);
cJSON *doc = elastic_get_document(arg_md5);
cJSON *source = cJSON_GetObjectItem(doc, "_source");
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;
}
@@ -358,24 +315,21 @@ 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 != UUID_STR_LEN + 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_uuid[UUID_STR_LEN];
memcpy(arg_uuid, hm->uri.p + 3, UUID_STR_LEN);
*(arg_uuid + UUID_STR_LEN - 1) = '\0';
char arg_md5[MD5_STR_LENGTH];
memcpy(arg_md5, hm->uri.ptr + 3, MD5_STR_LENGTH);
*(arg_md5 + MD5_STR_LENGTH - 1) = '\0';
const char *next = arg_uuid;
const char *next = arg_md5;
cJSON *doc = NULL;
cJSON *index_id = NULL;
cJSON *source = NULL;
@@ -386,8 +340,7 @@ 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");
@@ -401,8 +354,7 @@ 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;
}
@@ -423,14 +375,12 @@ void status(struct mg_connection *nc) {
}
free(status);
nc->flags |= MG_F_SEND_AND_CLOSE;
}
typedef struct {
char *name;
int delete;
char *relpath;
char *path_md5_str;
char *doc_id;
} tag_req_t;
@@ -450,8 +400,9 @@ tag_req_t *parse_tag_request(cJSON *json) {
return NULL;
}
cJSON *arg_relpath = cJSON_GetObjectItem(json, "relpath");
if (arg_relpath == NULL || !cJSON_IsString(arg_relpath)) {
cJSON *arg_path_md5 = cJSON_GetObjectItem(json, "path_md5");
if (arg_path_md5 == NULL || !cJSON_IsString(arg_path_md5) ||
strlen(arg_path_md5->valuestring) != MD5_STR_LENGTH - 1) {
return NULL;
}
@@ -463,41 +414,38 @@ tag_req_t *parse_tag_request(cJSON *json) {
tag_req_t *req = malloc(sizeof(tag_req_t));
req->delete = arg_delete->valueint;
req->name = arg_name->valuestring;
req->relpath = arg_relpath->valuestring;
req->path_md5_str = arg_path_md5->valuestring;
req->doc_id = arg_doc_id->valuestring;
return req;
}
void tag(struct mg_connection *nc, struct http_message *hm, struct mg_str *path) {
if (path->len != UUID_STR_LEN + 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[UUID_STR_LEN];
memcpy(arg_index, hm->uri.p + 5, UUID_STR_LEN);
*(arg_index + UUID_STR_LEN - 1) = '\0';
char arg_index[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);
@@ -506,15 +454,14 @@ 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;
}
cJSON *arr = NULL;
size_t data_len = 0;
const char *data = store_read(store, arg_req->relpath, strlen(arg_req->relpath), &data_len);
const char *data = store_read(store, arg_req->path_md5_str, MD5_STR_LENGTH, &data_len);
if (data_len == 0) {
arr = cJSON_CreateArray();
} else {
@@ -535,8 +482,8 @@ void tag(struct mg_connection *nc, struct http_message *hm, struct mg_str *path)
}
}
char buf[8192];
snprintf(buf, sizeof(buf),
char *buf = malloc(sizeof(char) * 8192);
snprintf(buf, 8192,
"{"
" \"script\" : {"
" \"source\": \"if (ctx._source.tag.contains(params.tag)) { ctx._source.tag.remove(ctx._source.tag.indexOf(params.tag)) }\","
@@ -550,13 +497,13 @@ 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));
char buf[8192];
snprintf(buf, sizeof(buf),
char *buf = malloc(sizeof(char) * 8192);
snprintf(buf, 8192,
"{"
" \"script\" : {"
" \"source\": \"if(ctx._source.tag == null) {ctx._source.tag = new ArrayList()} ctx._source.tag.add(params.tag)\","
@@ -570,11 +517,12 @@ 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);
store_write(store, arg_req->relpath, strlen(arg_req->relpath) + 1, json_str, strlen(json_str) + 1);
store_write(store, arg_req->path_md5_str, MD5_STR_LENGTH, json_str, strlen(json_str) + 1);
store_flush(store);
free(arg_req);
free(json_str);
@@ -583,39 +531,22 @@ 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\"\r\n", "");
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)) {
@@ -623,52 +554,48 @@ static void ev_router(struct mg_connection *nc, int ev, void *p) {
}
}
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)) {
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) {
@@ -688,14 +615,14 @@ 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;
}
}
}
@@ -706,15 +633,18 @@ 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

77
tests/test_scan.py Normal file
View File

@@ -0,0 +1,77 @@
import unittest
import subprocess
import shutil
import json
import os
TEST_FILES = "third-party/libscan/libscan-test-files/test_files"
def copy_files(files):
base = os.path.basename(files)
new_path = os.path.join("/tmp/sist2_test/", base)
shutil.rmtree(new_path, ignore_errors=True)
shutil.copytree(files, new_path)
return new_path
def sist2(*args):
print("./sist2 " + " ".join(args))
return subprocess.check_output(
args=["./sist2", *args],
)
def sist2_index(files, *args):
path = copy_files(files)
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):
path = copy_files(files)
if func:
func(path)
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", "index", "--print", index],
)
for line in res.splitlines():
if line:
yield json.loads(line)
class ScanTest(unittest.TestCase):
def test_incremental1(self):
def remove_files(path):
os.remove(os.path.join(path, "msdoc/test1.doc"))
os.remove(os.path.join(path, "msdoc/test2.doc"))
def add_files(path):
with open(os.path.join(path, "newfile1"), "w"):
pass
with open(os.path.join(path, "newfile2"), "w"):
pass
with open(os.path.join(path, "newfile3"), "w"):
pass
file_count = sum(1 for _ in sist2_index(TEST_FILES))
self.assertEqual(sum(1 for _ in sist2_incremental_index(TEST_FILES, remove_files)), file_count - 2)
self.assertEqual(sum(1 for _ in sist2_incremental_index(TEST_FILES, add_files)), file_count + 3)
if __name__ == "__main__":
unittest.main()