From 7cf90b25f7e612494c672381b9055aa8c0136e47 Mon Sep 17 00:00:00 2001
From: Kiryl <you@example.com>
Date: Wed, 29 Sep 2021 19:35:07 +0300
Subject: [PATCH] put limits on styles

---
 src/css_reader.py     | 18 +++++++-----------
 src/epub_converter.py |  2 +-
 2 files changed, 8 insertions(+), 12 deletions(-)

diff --git a/src/css_reader.py b/src/css_reader.py
index 6cad7eb..4ea7514 100644
--- a/src/css_reader.py
+++ b/src/css_reader.py
@@ -58,7 +58,7 @@ def convert_font_size(value):
 
 def convert_indents(value):
         # 30px = 3.2% = 1.25em = 23pt
-    text_indent_regexp = re.compile(r'(-*\w+%)|((-*\w*).*em)|(\w+px)|(-*\w+pt)')
+    text_indent_regexp = re.compile(r'(-*\w+%)|((-*\w*).*em)|(-*\w+pt)')
     has_style_attrs = re.search(text_indent_regexp, value)
     if has_style_attrs:
         if has_style_attrs.group(1):
@@ -72,10 +72,7 @@ def convert_indents(value):
                                 'px')
 
         elif has_style_attrs.group(4):
-            value = value.replace(has_style_attrs.group(4), '30px')
-
-        elif has_style_attrs.group(5):
-            value = value.replace(has_style_attrs.group(5),
+            value = value.replace(has_style_attrs.group(4),
                                   str(abs(int("".join(filter(str.isdigit, str(has_style_attrs.group(5))))))) + 'px')
     return value
 """ 
@@ -252,7 +249,8 @@ class TagStyleConverter:
         clean_style = ''
         for item in split_style:
             item = item.split(':')
-            item[1] = convert_indents(item[1])
+            if item[0] in ['text-indent', 'margin-left']:
+                item[1] = convert_indents(item[1])
             clean_style += item[0] + ': ' + item[1] + '; '
             
         margin_left_regexp = re.compile(
@@ -264,9 +262,7 @@ class TagStyleConverter:
         has_text_indent = re.search(text_indent_regexp, clean_style)
         #formula_of_indent: indent = abs(margin_left - text_indent)
         if has_margin_left:
-            num_ml = 0
-            if has_margin_left.group(1):
-                num_ml = abs(int("".join(
+            num_ml = abs(int("".join(
                     filter(str.isdigit, str(has_margin_left.group(2))))))
 
             if has_text_indent:
@@ -369,8 +365,8 @@ class TagStyleConverter:
                 p_tag = BeautifulSoup(features='lxml').new_tag('p')
                 span_style = tag.attrs['style']
                 p_style = ''
-                for i in range(span_style.count(';')):
-                    possible_p_attrs_regexp = re.compile(r'(text-align:( *\w+);*)|(text-indent:( *\w+);*)')
+                possible_p_attrs_regexp = re.compile(r'(text-align:( *\w+);*)|(text-indent:( *\w+);*)')
+                for i in range(span_style.count(';') + 1):
                     has_p_style_attrs = re.search(possible_p_attrs_regexp, span_style)
                     if has_p_style_attrs:
                         if has_p_style_attrs.group(1):
diff --git a/src/epub_converter.py b/src/epub_converter.py
index 4ac4ae1..baafcf0 100644
--- a/src/epub_converter.py
+++ b/src/epub_converter.py
@@ -455,7 +455,7 @@ if __name__ == "__main__":
 
     logger_object = BookLogger(name=f'epub', main_logger=logger, book_id=0)
 
-    json_converter = EpubConverter('../epub/9781641050692.epub',
+    json_converter = EpubConverter('../epub/Cook.epub',
                                    logger=logger_object)
     tmp = json_converter.convert_to_dict()