mathml2docx 0.1.2__tar.gz → 0.1.3__tar.gz

{mathml2docx-0.1.2/mathml2docx.egg-info → mathml2docx-0.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mathml2docx
-Version: 0.1.2
+Version: 0.1.3
 Summary: The fork in https://github.com/pqzx/html2docx converts html (including mathml) to docx
 Author: joongi007
 License: MIT License

{mathml2docx-0.1.2 → mathml2docx-0.1.3}/mathml2docx/__init__.py

@@ -1,4 +1,4 @@
 from .h2d import HtmlToDocx
 from .wrapper import MathmlToDocx
 
-__version__='0.1.0'
+__version__='0.1.3'

{mathml2docx-0.1.2 → mathml2docx-0.1.3}/mathml2docx/h2d.py

@@ -39,6 +39,7 @@ class HtmlToDocx(HTMLParser):
             'tables': True,
             'mathml': True,
             'styles': True,
+            'img_src_base_path':None,
         }
         self.table_row_selectors = [
             'table > tr',
@@ -64,6 +65,7 @@ class HtmlToDocx(HTMLParser):
         self.include_images = self.options['images']
         self.include_mathml = self.options['mathml']
         self.include_styles = self.options['styles']
+        self.img_src_base_path = self.options['img_src_base_path']
         self.paragraph = None
         self.run = None
         self.skip = False
@@ -217,12 +219,22 @@ class HtmlToDocx(HTMLParser):
             except urllib.error.URLError:
                 image = None
         else:
+            
             image = src_attr
+            print(self.img_src_base_path)
             if image and image.startswith('data:image/'):
                 #-- convert to bytes ready to insert to docx
                 image = image.split(',')[1]
                 image = base64.b64decode(image)
                 image = io.BytesIO(image)
+            elif image and self.img_src_base_path:
+                image = os.path.abspath(os.path.join(self.img_src_base_path, image))
+                print(image)
+                if os.path.isfile(image):
+                    with open(image, "rb") as fp:
+                        image = io.BytesIO(fp.read())
+                else:
+                    image = None
             else:
                 image = None
                 
@@ -682,4 +694,4 @@ if __name__=='__main__':
     args = vars(arg_parser.parse_args())
     file_html = args.pop('filename_html')
     html_parser = HtmlToDocx()
-    html_parser.parse_html_file(file_html, **args)
+    html_parser.parse_html_file(file_html, **args)

{mathml2docx-0.1.2 → mathml2docx-0.1.3}/mathml2docx/wrapper.py

@@ -13,10 +13,19 @@ class MathmlToDocx:
                  tables = True, 
                  mathml = True, 
                  styles = True, 
+                 img_src_base_path = None,
                  table_style = DEFAULT_TABLE_STYLE, 
                  paragraph_style = DEFAULT_PARAGRAPH_STYLE):
         self.__h2d = HtmlToDocx()
-        self.__options = MathmlTODocxOption(self.__h2d, fix_html, images, tables, mathml, styles)
+        self.__options = MathmlTODocxOption(
+            self.__h2d, 
+            fix_html, 
+            images, 
+            tables, 
+            mathml, 
+            styles, 
+            img_src_base_path
+        )
         self.__h2d.table_style = table_style
         self.__h2d.paragraph_style = paragraph_style
 
@@ -97,7 +106,7 @@ class MathmlToDocx:
         self.__h2d.add_styles_to_run(style)
 
 class MathmlTODocxOption:
-    def __init__(self, h2d, fix_html, images, tables, mathml, styles):
+    def __init__(self, h2d, fix_html, images, tables, mathml, styles, img_src_base_path):
         # init
         self.__h2d = h2d
         self.__fix_html = fix_html
@@ -105,6 +114,7 @@ class MathmlTODocxOption:
         self.__tables = tables
         self.__mathml = mathml
         self.__styles = styles
+        self.__img_src_base_path = img_src_base_path
 
         # h2d options init
         self.__h2d.options["fix-html"] = self.__fix_html
@@ -112,6 +122,7 @@ class MathmlTODocxOption:
         self.__h2d.options["tables"] = self.__tables
         self.__h2d.options["mathml"] = self.__mathml
         self.__h2d.options["styles"] = self.__styles
+        self.__h2d.options["img_src_base_path"] = self.__img_src_base_path
 
     @property
     def fix_html(self) -> bool:
@@ -163,6 +174,16 @@ class MathmlTODocxOption:
         self.__styles = styles
         self.__h2d.options["styles"] = styles
 
+    @property
+    def img_src_base_path(self) -> Union[str, None]:
+        self.__img_src_base_path = self.__h2d.options["img_src_base_path"]
+        return self.__img_src_base_path
+    
+    @img_src_base_path.setter
+    def img_src_base_path(self, img_src_base_path : Union[str, None]):
+        self.__img_src_base_path = img_src_base_path
+        self.__h2d.options["img_src_base_path"] = img_src_base_path
+
 if __name__=='__main__':
     arg_parser = argparse.ArgumentParser(description='Convert .html file into .docx file with formatting')
     arg_parser.add_argument('filename_html', help='The .html file to be parsed')

{mathml2docx-0.1.2 → mathml2docx-0.1.3/mathml2docx.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mathml2docx
-Version: 0.1.2
+Version: 0.1.3
 Summary: The fork in https://github.com/pqzx/html2docx converts html (including mathml) to docx
 Author: joongi007
 License: MIT License

{mathml2docx-0.1.2 → mathml2docx-0.1.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "mathml2docx"
-version = "0.1.2"
+version = "0.1.3"
 authors = [
   { name="joongi007" },
 ]

{mathml2docx-0.1.2 → mathml2docx-0.1.3}/tests/test_code.py

@@ -1,9 +1,9 @@
 import os
-from .context import HtmlToDocx, test_dir
+from .context import MathmlToDocx, test_dir
 
 # Manual test (requires inspection of result) for converting code and pre blocks.
 
 filename = os.path.join(test_dir, 'dataset', 'code.html')
-d = HtmlToDocx()
+d = MathmlToDocx()
 
 d.parse_html_file(filename)

{mathml2docx-0.1.2 → mathml2docx-0.1.3}/tests/test_tables.py

@@ -1,9 +1,9 @@
 import os
-from .context import HtmlToDocx, test_dir
+from .context import MathmlToDocx, test_dir
 
 # Manual test (requires inspection of result) for converting html with nested tables
 
 filename = os.path.join(test_dir, 'dataset', 'tables2.html')
-d = HtmlToDocx()
+d = MathmlToDocx()
 
 d.parse_html_file(filename)