Zoom and rotate features from forked gradio_annotation package. Fixed csv/xlsx redaction. Updated guide on creating exe.

DocRedactApp_0.2.spec → DocRedactApp_0.2.0.spec

@@ -1,17 +1,31 @@
 # -*- mode: python ; coding: utf-8 -*-
 from PyInstaller.utils.hooks import collect_data_files
+from PyInstaller.utils.hooks import collect_all
 
 datas = [('tesseract/', 'tesseract/'), ('poppler/poppler-24.02.0/', 'poppler/poppler-24.02.0/')]
+binaries = []
+hiddenimports = ['gradio_image_annotation', 'pyarrow.vendored.version', 'pydicom.encoders', 'safehttpx', 'presidio_analyzer', 'presidio_anonymizer', 'presidio_image_redactor']
 datas += collect_data_files('gradio_client')
 datas += collect_data_files('gradio')
+datas += collect_data_files('gradio_image_annotation')
+tmp_ret = collect_all('gradio_image_annotation')
+datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
+tmp_ret = collect_all('safehttpx')
+datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
+tmp_ret = collect_all('presidio_analyzer')
+datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
+tmp_ret = collect_all('presidio_anonymizer')
+datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
+tmp_ret = collect_all('presidio_image_redactor')
+datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
 
 
 a = Analysis(
     ['app.py'],
     pathex=[],
-    binaries=[],
+    binaries=binaries,
     datas=datas,
-    hiddenimports=['pyarrow.vendored.version', 'pydicom.encoders'],
+    hiddenimports=hiddenimports,
     hookspath=['build_deps'],
     hooksconfig={},
     runtime_hooks=[],
@@ -29,7 +43,7 @@ exe = EXE(
     a.scripts,
     [],
     exclude_binaries=True,
-    name='DocRedactApp_0.2',
+    name='DocRedactApp_0.2.0',
     debug=False,
     bootloader_ignore_signals=False,
     strip=False,
@@ -48,5 +62,5 @@ coll = COLLECT(
     strip=False,
     upx=True,
     upx_exclude=[],
-    name='DocRedactApp_0.2',
+    name='DocRedactApp_0.2.0',
 )

app.py

@@ -453,7 +453,7 @@ with app:
     # TABULAR DATA REDACTION
     ###            
     in_data_files.upload(fn=put_columns_in_df, inputs=[in_data_files], outputs=[in_colnames, in_excel_sheets]).\
-                  then(fn=get_input_file_names, inputs=[in_data_files], outputs=[data_full_file_name_textbox, data_file_name_no_extension_textbox, data_file_name_with_extension_textbox, data_full_file_name_textbox, data_file_name_textbox_list])
+                  then(fn=get_input_file_names, inputs=[in_data_files], outputs=[data_file_name_no_extension_textbox, data_file_name_with_extension_textbox, data_full_file_name_textbox, data_file_name_textbox_list])
 
     tabular_data_redact_btn.click(fn=anonymise_data_files, inputs=[in_data_files, in_text, anon_strat, in_colnames, in_redact_language, in_redact_entities, in_allow_list, text_tabular_files_done, text_output_summary, text_output_file_list_state, log_files_output_list_state, in_excel_sheets, first_loop_state], outputs=[text_output_summary, text_output_file, text_output_file_list_state, text_tabular_files_done, log_files_output, log_files_output_list_state], api_name="redact_data")
 

how_to_create_exe_dist.txt

@@ -12,9 +12,9 @@ NOTE: for ensuring that spaCy models are loaded into the program correctly in re
 
 8. In command line, cd to the folder that contains app.py. 
 
-9.Run the following, assuming you want to make one single .exe file (This helped me: https://github.com/pyinstaller/pyinstaller/issues/8108):
+9.Run the following (This helped me: https://github.com/pyinstaller/pyinstaller/issues/8108):
 
-a) In command line: pyi-makespec --additional-hooks-dir="build_deps" --add-data "tesseract/:tesseract/" --add-data "poppler/poppler-24.02.0/:poppler/poppler-24.02.0/" --collect-data=gradio_client  --collect-data=gradio  --hidden-import pyarrow.vendored.version --hidden-import pydicom.encoders  --name DocRedactApp_0.2 app.py 
+a) In command line: pyi-makespec --additional-hooks-dir="build_deps" --add-data "tesseract/:tesseract/" --add-data "poppler/poppler-24.02.0/:poppler/poppler-24.02.0/" --collect-data=gradio_client  --collect-data=gradio --hidden-import=gradio_image_annotation --collect-data=gradio_image_annotation --collect-all=gradio_image_annotation --hidden-import pyarrow.vendored.version --hidden-import pydicom.encoders --hidden-import=safehttpx --collect-all=safehttpx --hidden-import=presidio_analyzer --collect-all=presidio_analyzer --hidden-import=presidio_anonymizer --collect-all=presidio_anonymizer --hidden-import=presidio_image_redactor --collect-all=presidio_image_redactor --name DocRedactApp_0.2.0 app.py
 
 # Add --onefile  to the above if you would like everything packaged as a single exe, although this will need to be extracted upon starting the app, slowing down initialisation time significantly.
 
@@ -28,11 +28,29 @@ a = Analysis(
     }
 )
 
-c) Back in command line, run this: pyinstaller --clean --noconfirm DocRedactApp_0.2.spec
+hook-presidio-image-redactor.py
 
+c) Back in command line, run this: pyinstaller --clean --noconfirm DocRedactApp_0.2.0.spec
 
-9. A 'dist' folder will be created with the executable inside along with all dependencies('dist\data_text_search'). 
 
-10. In 'dist\data_text_search' try double clicking on the .exe file. After a short delay, the command prompt should inform you about the IP address of the app that is now running. Copy the IP address. **Do not close this window!**
+9. A 'dist' folder will be created with the executable inside along with all dependencies('dist\redaction').
 
-11. In an Internet browser, navigate to the indicated IP address. The app should now be running in your browser window.
+10. go to dist/APP-NAME/gradio/component_meta.py and modify the start of the 'create_or_modify_pyi(...' function to this:
+
+def create_or_modify_pyi(
+    component_class: type, class_name: str, events: list[str | EventListener]
+):
+    source_file = Path(inspect.getfile(component_class))
+
+    try:
+        # Try to read the source file
+        source_code = source_file.read_text(encoding="utf-8")
+    except FileNotFoundError:
+        # If source file not found, skip pyi generation
+        return None 
+
+11. Copy the poppler and tesseract folders into the location where the .exe is
+
+12. In 'dist\redaction' try double clicking on the .exe file. After a short delay, the command prompt should inform you about the IP address of the app that is now running. Copy the IP address. **Do not close this window!**
+
+12. In an Internet browser, navigate to the indicated IP address. The app should now be running in your browser window.

requirements.txt

@@ -12,14 +12,18 @@ scikit-learn==1.5.2
 spacy==3.8.3
 #en_core_web_lg @ https://github.com/explosion/spacy-#models/releases/download/en_core_web_lg-3.8.0/en_core_web_sm-#3.8.0.tar.gz
 en_core_web_sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.8.0/en_core_web_sm-3.8.0.tar.gz
-gradio==5.12.0
-boto3==1.35.83
+gradio==5.15.0
+boto3==1.36.15
 pyarrow==18.1.0
 openpyxl==3.1.2
 Faker==22.2.0
 python-levenshtein==0.26.1
 spaczz==0.6.1
-gradio_image_annotation==0.2.5
+#gradio_image_annotation==0.2.5
+# The following version includes rotation and image zoom options
+git+https://github.com/seanpedrick-case/gradio_image_annotator
+
+rapidfuzz==3.12.1
 numpy==1.26.4
 awslambdaric==3.0.0
 

tools/data_anonymise.py

@@ -389,6 +389,11 @@ def anonymise_data_files(file_paths:List[str], in_text:str, anon_strat:str, chos
     if isinstance(out_message, str):
         out_message = [out_message]
 
+    print("log_files_output_paths:",log_files_output_paths)
+
+    if isinstance(log_files_output_paths, str):
+        log_files_output_paths = []
+
     if not out_file_paths:
         out_file_paths = []
     
@@ -473,6 +478,7 @@ def anonymise_data_files(file_paths:List[str], in_text:str, anon_strat:str, chos
                 sheet_name = ""
                 anon_df = read_file(anon_file)
                 out_file_part = get_file_name_without_type(anon_file.name)
+
                 out_file_paths, out_message, key_string, log_files_output_paths = anon_wrapper_func(anon_file, anon_df, chosen_cols, out_file_paths, out_file_part, out_message, sheet_name, anon_strat, language, chosen_redact_entities, in_allow_list, file_type, "", log_files_output_paths)
 
         # Increase latest file completed count unless we are at the last file

tools/redaction_review.py

@@ -500,8 +500,8 @@ def create_xfdf(df, pdf_path, pymupdf_doc, image_paths):
         redact_annot.set('interior-color', colour_str)
         #redact_annot.set('fill-color', colour_str)
         #redact_annot.set('outline-color', colour_str)
-        redact_annot.set('overlay-color', colour_str)
-        redact_annot.set('overlay-text', row['label'])
+        #redact_annot.set('overlay-color', colour_str)
+        #redact_annot.set('overlay-text', row['label'])
         redact_annot.set('opacity', "0.5")
 
         # Add appearance dictionary