with spacy version

.idea/workspace.xml

@@ -4,8 +4,10 @@
     <option name="autoReloadType" value="SELECTIVE" />
   </component>
   <component name="ChangeListManager">
-    <list default="true" id="5e4481c0-7ba2-42e4-bbe6-4c36a0d36baa" name="Changes" comment="change time cost count">
+    <list default="true" id="5e4481c0-7ba2-42e4-bbe6-4c36a0d36baa" name="Changes" comment="local model">
       <change beforePath="$PROJECT_DIR$/.idea/workspace.xml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/workspace.xml" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/logs/app.log" beforeDir="false" afterPath="$PROJECT_DIR$/logs/app.log" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/requirements.txt" beforeDir="false" afterPath="$PROJECT_DIR$/requirements.txt" afterDir="false" />
     </list>
     <option name="SHOW_DIALOG" value="false" />
     <option name="HIGHLIGHT_CONFLICTS" value="true" />
@@ -34,29 +36,29 @@
     <option name="hideEmptyMiddlePackages" value="true" />
     <option name="showLibraryContents" value="true" />
   </component>
-  <component name="PropertiesComponent"><![CDATA[{
-  "keyToString": {
-    "DefaultHtmlFileTemplate": "HTML File",
-    "RunOnceActivity.OpenProjectViewOnStart": "true",
-    "RunOnceActivity.ShowReadmeOnStart": "true",
-    "WebServerToolWindowFactoryState": "false",
-    "last_opened_file_path": "/Users/hika/ANU/2024 s2/8800/Cpp4App_test/CDM/detect_merge",
-    "node.js.detected.package.eslint": "true",
-    "node.js.detected.package.tslint": "true",
-    "node.js.selected.package.eslint": "(autodetect)",
-    "node.js.selected.package.tslint": "(autodetect)",
-    "nodejs_package_manager_path": "npm",
-    "settings.editor.selected.configurable": "vcs.Git",
-    "vue.rearranger.settings.migration": "true"
+  <component name="PropertiesComponent">{
+  &quot;keyToString&quot;: {
+    &quot;DefaultHtmlFileTemplate&quot;: &quot;HTML File&quot;,
+    &quot;RunOnceActivity.OpenProjectViewOnStart&quot;: &quot;true&quot;,
+    &quot;RunOnceActivity.ShowReadmeOnStart&quot;: &quot;true&quot;,
+    &quot;WebServerToolWindowFactoryState&quot;: &quot;false&quot;,
+    &quot;last_opened_file_path&quot;: &quot;/Users/hika/ANU/2024 s2/8800/Cpp4App_test/CDM/detect_merge&quot;,
+    &quot;node.js.detected.package.eslint&quot;: &quot;true&quot;,
+    &quot;node.js.detected.package.tslint&quot;: &quot;true&quot;,
+    &quot;node.js.selected.package.eslint&quot;: &quot;(autodetect)&quot;,
+    &quot;node.js.selected.package.tslint&quot;: &quot;(autodetect)&quot;,
+    &quot;nodejs_package_manager_path&quot;: &quot;npm&quot;,
+    &quot;settings.editor.selected.configurable&quot;: &quot;vcs.Git&quot;,
+    &quot;vue.rearranger.settings.migration&quot;: &quot;true&quot;
   }
-}]]></component>
+}</component>
   <component name="RecentsManager">
     <key name="CopyFile.RECENT_KEYS">
       <recent name="$PROJECT_DIR$/CDM/detect_merge" />
     </key>
     <key name="MoveFile.RECENT_KEYS">
-      <recent name="$PROJECT_DIR$/CDM/detect_merge" />
       <recent name="$PROJECT_DIR$" />
+      <recent name="$PROJECT_DIR$/CDM/detect_merge" />
       <recent name="$PROJECT_DIR$/web_design" />
       <recent name="$PROJECT_DIR$/google_drive_credentials" />
     </key>
@@ -108,20 +110,7 @@
       <workItem from="1731657236263" duration="3838000" />
       <workItem from="1731661095283" duration="476000" />
       <workItem from="1731661576559" duration="73000" />
-    </task>
-    <task id="LOCAL-00016" summary="test auto monitor">
-      <created>1723461444926</created>
-      <option name="number" value="00016" />
-      <option name="presentableId" value="LOCAL-00016" />
-      <option name="project" value="LOCAL" />
-      <updated>1723461444926</updated>
-    </task>
-    <task id="LOCAL-00017" summary="complete log part">
-      <created>1723462386739</created>
-      <option name="number" value="00017" />
-      <option name="presentableId" value="LOCAL-00017" />
-      <option name="project" value="LOCAL" />
-      <updated>1723462386739</updated>
+      <workItem from="1736955054540" duration="1826000" />
     </task>
     <task id="LOCAL-00018" summary="change to html">
       <created>1723480210476</created>
@@ -452,7 +441,21 @@
       <option name="project" value="LOCAL" />
       <updated>1730171925436</updated>
     </task>
-    <option name="localTasksCounter" value="65" />
+    <task id="LOCAL-00065" summary="skip pip check">
+      <created>1736955150675</created>
+      <option name="number" value="00065" />
+      <option name="presentableId" value="LOCAL-00065" />
+      <option name="project" value="LOCAL" />
+      <updated>1736955150676</updated>
+    </task>
+    <task id="LOCAL-00066" summary="local model">
+      <created>1736956205746</created>
+      <option name="number" value="00066" />
+      <option name="presentableId" value="LOCAL-00066" />
+      <option name="project" value="LOCAL" />
+      <updated>1736956205746</updated>
+    </task>
+    <option name="localTasksCounter" value="67" />
     <servers />
   </component>
   <component name="TypeScriptGeneratedFilesManager">
@@ -492,9 +495,12 @@
     <MESSAGE value="batch images" />
     <MESSAGE value="." />
     <MESSAGE value="change time cost count" />
-    <option name="LAST_COMMIT_MESSAGE" value="change time cost count" />
+    <MESSAGE value="skip pip check" />
+    <MESSAGE value="local model" />
+    <option name="LAST_COMMIT_MESSAGE" value="local model" />
   </component>
   <component name="com.intellij.coverage.CoverageDataManagerImpl">
+    <SUITE FILE_PATH="coverage/Cpp4App_test2$app.coverage" NAME="app Coverage Results" MODIFIED="1736956973387" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="true" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
     <SUITE FILE_PATH="coverage/Cpp4App_test$app.coverage" NAME="app Coverage Results" MODIFIED="1731660960877" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="true" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
   </component>
 </project>

requirements.txt

@@ -8,10 +8,10 @@ bs4==0.0.1
 scikit-learn==1.1.2
 scipy==1.9.0
 nltk==3.7
-spacy
+spacy==3.7.2
 pytesseract==0.3.10
 # https://huggingface.co/spacy/en_core_web_sm/resolve/main/en_core_web_sm-any-py3-none-any.whl
-./en_core_web_sm-any-py3-none-any.whl
+# ./en_core_web_sm-any-py3-none-any.whl
 transformers
 openai==0.27.0
 openpyxl