Browse Source

[mod] checker : replace pycld3 by langdetect

pycld3 requires the native library cld3
langdetect is a pure python package
Alexandre Flament 4 years ago
parent
commit
aa887eb375
3 changed files with 13 additions and 10 deletions
  1. 1 1
      requirements.txt
  2. 10 5
      searx/search/checker/impl.py
  3. 2 4
      utils/searx.sh

+ 1 - 1
requirements.txt

@@ -9,4 +9,4 @@ pygments==2.1.3
 python-dateutil==2.8.1
 pyyaml==5.3.1
 requests[socks]==2.25.1
-pycld3==0.20
+langdetect==1.0.8

+ 10 - 5
searx/search/checker/impl.py

@@ -9,7 +9,8 @@ from time import time
 from urllib.parse import urlparse
 
 import re
-import cld3
+from langdetect import detect_langs
+from langdetect.lang_detect_exception import LangDetectException
 import requests.exceptions
 
 from searx import poolrequests, logger
@@ -181,10 +182,14 @@ class ResultContainerTests:
         self.test_results.add_error(self.test_name, message, *args, '(' + sqstr + ')')
 
     def _add_language(self, text: str) -> typing.Optional[str]:
-        r = cld3.get_language(str(text))  # pylint: disable=E1101
-        if r is not None and r.probability >= 0.98 and r.is_reliable:
-            self.languages.add(r.language)
-            self.test_results.add_language(r.language)
+        try:
+            r = detect_langs(str(text))  # pylint: disable=E1101
+        except LangDetectException:
+            return None
+
+        if len(r) > 0 and r[0].prob > 0.95:
+            self.languages.add(r[0].lang)
+            self.test_results.add_language(r[0].lang)
         return None
 
     def _check_result(self, result):

+ 2 - 4
utils/searx.sh

@@ -46,7 +46,6 @@ SEARX_PACKAGES_debian="\
 python3-dev python3-babel python3-venv
 uwsgi uwsgi-plugin-python3
 git build-essential libxslt-dev zlib1g-dev libffi-dev libssl-dev
-libprotobuf-dev protobuf-compiler
 shellcheck"
 
 BUILD_PACKAGES_debian="\
@@ -59,7 +58,6 @@ SEARX_PACKAGES_arch="\
 python python-pip python-lxml python-babel
 uwsgi uwsgi-plugin-python
 git base-devel libxml2
-protobuf
 shellcheck"
 
 BUILD_PACKAGES_arch="\
@@ -71,7 +69,7 @@ SEARX_PACKAGES_fedora="\
 python python-pip python-lxml python-babel
 uwsgi uwsgi-plugin-python3
 git @development-tools libxml2
-ShellCheck protobuf-compiler protobuf-devel"
+ShellCheck"
 
 BUILD_PACKAGES_fedora="\
 firefox graphviz graphviz-gd ImageMagick librsvg2-tools
@@ -84,7 +82,7 @@ SEARX_PACKAGES_centos="\
 python36 python36-pip python36-lxml python-babel
 uwsgi uwsgi-plugin-python3
 git @development-tools libxml2
-ShellCheck protobuf-compiler protobuf-devel"
+ShellCheck"
 
 BUILD_PACKAGES_centos="\
 firefox graphviz graphviz-gd ImageMagick librsvg2-tools