refactoring && bug fixes

app/main/reports/parse_file/parse_file.py

@@ -1,13 +1,19 @@
+from app.main.reports.docx_uploader import DocxUploader
+import re
+
+
 def parse_headers_and_pages(chapters, docx):
     text_on_page = docx.pdf_file.get_text_on_page()
-    keys = list(text_on_page.keys())
-    values = list(text_on_page.values())
-    for page_text in text_on_page.values():
+
+    for page, text in text_on_page.items():
+        text = re.sub(r"(-\n)", "", text)
+        text = re.sub(r"\s\n", " ", text)
+        if "СОДЕРЖАНИЕ" in text:
+            continue
         for chapter in chapters:
-            if chapter["header"] in page_text:
-                pos = values.index(page_text)
-                chapter["start_page"] = keys[pos]
-    return chapters
+            if chapter["header"] in text:
+                chapter["start_page"] = page
+    return chapters  # 1.3, 1.4, 3.4.2
 
 
 def parse_chapters(docx):
@@ -20,5 +26,18 @@ def parse_chapters(docx):
             temp_text = ""
             for i in range(len(chapter["child"])):
                 temp_text += chapter["child"][i]["styled_text"]["text"]
-                chapters.append({"header": head, "start_page": 0, "text": temp_text})
+            chapters.append({"header": head, "start_page": 0, "text": temp_text})
     return chapters
+
+
+if __name__ == "__main__":
+    file = "/home/vilka/Downloads/petrov.docx"
+    parsed_file = DocxUploader()
+    parsed_file.upload(file)
+    parsed_file.parse()
+    parsed_file.make_chapters("VKR")
+    parsed_file.make_headers("VKR")
+    chapters = parse_chapters(parsed_file)
+    chapters_with_headers = parse_headers_and_pages(chapters, parsed_file)
+    for i in range(len(chapters_with_headers) // 2):
+        print(chapters_with_headers[i])