myocr-lib 0.1.1__py3-none-any.whl → 0.1.3__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (7) hide show
  1. {myocr_lib-0.1.1.dist-info → myocr_lib-0.1.3.dist-info}/METADATA +1 -1
  2. myocr_lib-0.1.3.dist-info/RECORD +8 -0
  3. ocr_img/main_code.py +1 -1
  4. ocr_pdf/main_code.py +5 -3
  5. myocr_lib-0.1.1.dist-info/RECORD +0 -8
  6. {myocr_lib-0.1.1.dist-info → myocr_lib-0.1.3.dist-info}/WHEEL +0 -0
  7. {myocr_lib-0.1.1.dist-info → myocr_lib-0.1.3.dist-info}/top_level.txt +0 -0
{myocr_lib-0.1.1.dist-info → myocr_lib-0.1.3.dist-info}/METADATA RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: myocr_lib
3
- Version: 0.1.1
3
+ Version: 0.1.3
4
4
  Summary: To be available soon
5
5
  Keywords: utility,library,functions,ocr,image-processing
6
6
  Classifier: Development Status :: 3 - Alpha
myocr_lib-0.1.3.dist-info/RECORD ADDED
@@ -0,0 +1,8 @@
1
+ ocr_img/__init__.py,sha256=A0HMZNNgwObl6qZHeGKXQSf-VhPlkQt3YKEcA_VXHLw,80
2
+ ocr_img/main_code.py,sha256=738bf1zZTr1FRncvPfUik4SSS2nSMkPqrCFRtnQeGmM,1300
3
+ ocr_pdf/__init__.py,sha256=t4SYasAJ1pjnd7sZBnPe1PqMbR18-4onsHXu93zw1LE,96
4
+ ocr_pdf/main_code.py,sha256=Rz9PtpA79XPbX2VsmeNaQabnY_ZoRkYylTUeNZPc2cE,5175
5
+ myocr_lib-0.1.3.dist-info/METADATA,sha256=s-8a8rie6ytZfIIF4vplbuot2_gHccJ8gUF9vHslcwY,677
6
+ myocr_lib-0.1.3.dist-info/WHEEL,sha256=iAkIy5fosb7FzIOwONchHf19Qu7_1wCWyFNR5gu9nU0,91
7
+ myocr_lib-0.1.3.dist-info/top_level.txt,sha256=m22oM9I_3SovUyKNzGQIpqgCp7GTXua0G7cEYqMx654,16
8
+ myocr_lib-0.1.3.dist-info/RECORD,,
ocr_img/main_code.py CHANGED
@@ -42,7 +42,7 @@ class ImageOCR:
42
42
  # apply the ocr
43
43
  text = self._apply_ocr(img)
44
44
 
45
- print(text)
45
+ # print(text)
46
46
 
47
47
  # temporary save to file for demo
48
48
  # get the extension
ocr_pdf/main_code.py CHANGED
@@ -28,7 +28,7 @@ class OCRDataExtractor:
28
28
  result = subprocess.run(command, capture_output=True, text=True)
29
29
 
30
30
  if result.returncode == 0:
31
- print("PDF Was converted to Selectable Successfully.")
31
+ print("OCR on PDF Was successfully.")
32
32
 
33
33
  return True
34
34
 
@@ -110,13 +110,15 @@ class OCRDataExtractor:
110
110
  # apply the whole pdf ocr if all the pages are extractable
111
111
  if self._is_whole_pdf_ocr():
112
112
  print("Applying whole Pdf ocr...")
113
+ # empty the pages
114
+ self.pages_to_ocr = []
113
115
 
114
116
  results = self._apply_whole_pdf_ocr()
115
117
 
116
118
  # apply the extraction for the whole pdf through fitz
117
119
  text = self._extract_text_whole_pdf() if results else None
118
120
 
119
- print(text)
121
+ # print(text)
120
122
 
121
123
  # temporary store the text
122
124
  # ext = self.input_pdf_path.split('.')[-1]
@@ -139,7 +141,7 @@ class OCRDataExtractor:
139
141
  # do the extraction for specific pages only throug fitz
140
142
  text = self._extract_text_page_by_page() if results else None
141
143
 
142
- print(text)
144
+ # print(text)
143
145
 
144
146
  # delete the output file
145
147
  self.delete_file(self.output_file_path)
myocr_lib-0.1.1.dist-info/RECORD DELETED
@@ -1,8 +0,0 @@
1
- ocr_img/__init__.py,sha256=A0HMZNNgwObl6qZHeGKXQSf-VhPlkQt3YKEcA_VXHLw,80
2
- ocr_img/main_code.py,sha256=aqE-NGFDCJ_nqpMt7GujRvEin6dB4kCK9DEQiADnMRs,1298
3
- ocr_pdf/__init__.py,sha256=t4SYasAJ1pjnd7sZBnPe1PqMbR18-4onsHXu93zw1LE,96
4
- ocr_pdf/main_code.py,sha256=1_SDZu-Ry9HZJE39KjgH4my5S7fXpE7MYIjkemxpmT8,5121
5
- myocr_lib-0.1.1.dist-info/METADATA,sha256=3FUPOov0OXejJhMzSrbUc2LssNAJRT9yjHtGQ3G8LLw,677
6
- myocr_lib-0.1.1.dist-info/WHEEL,sha256=iAkIy5fosb7FzIOwONchHf19Qu7_1wCWyFNR5gu9nU0,91
7
- myocr_lib-0.1.1.dist-info/top_level.txt,sha256=m22oM9I_3SovUyKNzGQIpqgCp7GTXua0G7cEYqMx654,16
8
- myocr_lib-0.1.1.dist-info/RECORD,,