TLDR-538 added low quality imgs; fixed after review

ispras · Dec 25, 2023 · 3a2dca8 · 3a2dca8
1 parent aa5f2c7
commit 3a2dca8
Show file tree

Hide file tree

Showing 4 changed files with 549 additions and 72 deletions.
diff --git a/dedoc/scripts/calc_tesseract_benchmarks.py b/dedoc/scripts/calc_tesseract_benchmarks.py
@@ -14,11 +14,11 @@
 from dedoc.scripts.language_tool_correction import LanguageToolCorrector
 from dedoc.scripts.ocr_correction import init_correction_step, correction
 
-WITHOUT_CORRECTION = 0
-SAGE_CORRECTION = 1
-LANGUAGE_TOOL_CORRECTION = 2
+WITHOUT_CORRECTION = ""
+SAGE_CORRECTION = "_sage-correction"
+LANGUAGE_TOOL_CORRECTION = "_languagetool-correction"
 
-USE_CORRECTION_OCR = LANGUAGE_TOOL_CORRECTION
+USE_CORRECTION_OCR = SAGE_CORRECTION
 
 
 def _call_tesseract(image: np.ndarray, language: str, psm: int = 3) -> str:
@@ -287,7 +287,7 @@ def __calculate_ocr_reports(cache_dir_accuracy: str, benchmark_data_path: str, c
 
     benchmark_data_path = os.path.join(cache_dir, f"{base_zip}.zip")
     if not os.path.isfile(benchmark_data_path):
-        wget.download("https://at.ispras.ru/owncloud/index.php/s/HqKt53BWmR8nCVG/download", benchmark_data_path)
+        wget.download("https://at.ispras.ru/owncloud/index.php/s/wMyKioKInYITpYT", benchmark_data_path)
         print(f"Benchmark data downloaded to {benchmark_data_path}")
     else:
         print(f"Use cached benchmark data from {benchmark_data_path}")
@@ -297,7 +297,7 @@ def __calculate_ocr_reports(cache_dir_accuracy: str, benchmark_data_path: str, c
 
     table_errors = __get_summary_symbol_error(path_reports=cache_dir_accuracy)
 
-    with open(os.path.join(output_dir, "tesseract_benchmark.txt"), "w") as res_file:
+    with open(os.path.join(output_dir, f"tesseract_benchmark{USE_CORRECTION_OCR}.txt"), "w") as res_file:
         res_file.write(f"Tesseract version is {pytesseract.get_tesseract_version()}\n")
         res_file.write(f"Correction step: {USE_CORRECTION_OCR}\n")
         res_file.write(f"\nTable 1 - Accuracy for each file\n")

diff --git a/dedoc/scripts/language_tool_correction.py b/dedoc/scripts/language_tool_correction.py
@@ -1,5 +1,9 @@
 import language_tool_python
 
+"""
+pip install language-tool-python==2.7.1
+"""
+
 
 class LanguageToolCorrector:
     def __init__(self):