Update 1.0.2

dfop02 · Feb 20, 2024 · 1e2106e · 1e2106e
1 parent 450db53
commit 1e2106e
Show file tree

Hide file tree

Showing 9 changed files with 148 additions and 42 deletions.
diff --git a/README.md b/README.md
@@ -1,22 +1,74 @@
 # HTML FOR DOCX
 Convert html to docx, this project is a fork from descontinued [pqzx/html2docx](https://github.com/pqzx/html2docx).
 
-### To install
+### How install
 
 `pip install html-for-docx`
 
 ### Usage
 
-The basic is
+The basic usage: Add HTML formatted to an existing Docx
 
 ```python
 from html4docx import HtmlToDocx
 
 parser = HtmlToDocx()
+html_string = '<h1>Hello world</h1>'
 parser.add_html_to_document(html_string, filename_docx)
 ```
 
-Take a look on [pqzx/html2docx](https://github.com/pqzx/html2docx) project to see examples of usage.
+You can use `python-docx` to manipulate the file as well, here an example
+
+```python
+from docx import Document
+from html4docx import HtmlToDocx
+
+document = Document()
+new_parser = HtmlToDocx()
+
+html_string = '<h1>Hello world</h1>'
+new_parser.add_html_to_document(html_string, document)
+
+document.save('your_file_name')
+```
+
+Convert files directly
+
+```python
+from html4docx import HtmlToDocx
+
+new_parser = HtmlToDocx()
+new_parser.parse_html_file(input_html_file_path, output_docx_file_path)
+```
+
+Convert files from a string
+
+```python
+from html4docx import HtmlToDocx
+
+new_parser = HtmlToDocx()
+docx = new_parser.parse_html_string(input_html_file_string)
+```
+
+Change table styles
+
+Tables are not styled by default. Use the `table_style` attribute on the parser to set a table style. The style is used for all tables.
+
+```python
+from html4docx import HtmlToDocx
+
+new_parser = HtmlToDocx()
+new_parser.table_style = 'Light Shading Accent 4'
+```
+
+To add borders to tables, use the `TableGrid` style:
+
+```python
+new_parser.table_style = 'TableGrid'
+```
+
+Default table styles can be found
+here: https://python-docx.readthedocs.io/en/latest/user/styles-understanding.html#table-styles-in-default-template
 
 ### Why
 
@@ -28,17 +80,17 @@ My goal to fork and fix/update this package was to complete my current task at w
 - Handle missing run for leading br tag | [dashingdove](https://github.com/dashingdove) from [PR](https://github.com/pqzx/html2docx/pull/53)
 - Fix base64 images | [djplaner](https://github.com/djplaner) from [Issue](https://github.com/pqzx/html2docx/issues/28#issuecomment-1052736896)
 - Handle img tag without src attribute | [johnjor](https://github.com/johnjor) from [PR](https://github.com/pqzx/html2docx/pull/63)
-- Fix text-align bug when `!important` | [Dfop02](https://github.com/dfop02)
-- Fix background-color always set default color | [Dfop02](https://github.com/dfop02)
+- Fix bug when any style has `!important` | [Dfop02](https://github.com/dfop02)
 - Fix 'style lookup by style_id is deprecated.' | [Dfop02](https://github.com/dfop02)
 
 **New Features**
 - Add Witdh/Height style to images | [maifeeulasad](https://github.com/maifeeulasad) from [PR](https://github.com/pqzx/html2docx/pull/29)
-- Support px, cm and % for style margin-left to paragraphs | [Dfop02](https://github.com/dfop02)
+- Support px, cm, pt and % for style margin-left to paragraphs | [Dfop02](https://github.com/dfop02)
 - Improve performance on large tables | [dashingdove](https://github.com/dashingdove) from [PR](https://github.com/pqzx/html2docx/pull/58)
 - Support for HTML Pagination | [Evilran](https://github.com/Evilran) from [PR](https://github.com/pqzx/html2docx/pull/39)
 - Support Table style | [Evilran](https://github.com/Evilran) from [PR](https://github.com/pqzx/html2docx/pull/39)
 - Support alternative encoding | [HebaElwazzan](https://github.com/HebaElwazzan) from [PR](https://github.com/pqzx/html2docx/pull/59)
+- Refactory Tests to be more consistent and less 'human validation' | [Dfop02](https://github.com/dfop02)
 
 ## License
 

diff --git a/html4docx/h4d.py b/html4docx/h4d.py
@@ -21,19 +21,17 @@
 from io import BytesIO
 from html.parser import HTMLParser
 
-import docx
-import docx.table
-
-from html4docx import utils
-from html4docx.colors import Color
+from bs4 import BeautifulSoup
 
+import docx
 from docx import Document
 from docx.shared import RGBColor, Pt, Cm, Inches
 from docx.enum.text import WD_ALIGN_PARAGRAPH
 from docx.oxml import OxmlElement
 from docx.oxml.ns import qn
 
-from bs4 import BeautifulSoup
+from html4docx import utils
+from html4docx.colors import Color
 
 # values in inches
 INDENT = 0.25
@@ -65,10 +63,7 @@ def set_initial_attrs(self, document=None):
             'span': [],
             'list': [],
         }
-        if document:
-            self.doc = document
-        else:
-            self.doc = Document()
+        self.doc = document if document else Document()
         self.bs = self.options['fix-html'] # whether or not to clean with BeautifulSoup
         self.document = self.doc
         self.include_tables = True # TODO add this option back in?
@@ -91,7 +86,8 @@ def get_cell_html(self, soup):
 
     def add_styles_to_paragraph(self, style):
         if 'text-align' in style:
-            align = style['text-align']
+            align = re.sub('!important', '', style['text-align'], flags=re.IGNORECASE)
+
             if 'center' in align:
                 self.paragraph.paragraph_format.alignment = WD_ALIGN_PARAGRAPH.CENTER
             elif 'right' in align:
@@ -102,25 +98,28 @@ def add_styles_to_paragraph(self, style):
         if 'margin-left' in style and 'margin-right' in style:
             margin_left = style['margin-left']
             margin_right = style['margin-right']
-            if "auto" in margin_left and "auto" in margin_right:
+            if 'auto' in margin_left and 'auto' in margin_right:
                 self.paragraph.paragraph_format.alignment = WD_ALIGN_PARAGRAPH.CENTER
         elif 'margin-left' in style:
-            margin = style['margin-left']
+            margin = re.sub('!important', '', style['margin-left'], flags=re.IGNORECASE)
             units = re.sub(r'[0-9]+', '', margin)
             margin = int(float(re.sub(r'[a-zA-Z\!]+', '', margin)))
 
             if units == 'px':
                 self.paragraph.paragraph_format.left_indent = Inches(min(margin // 10 * INDENT, MAX_INDENT))
             elif units == 'cm':
                 self.paragraph.paragraph_format.left_indent = Cm(min(margin // 10 * INDENT, MAX_INDENT) * 2.54)
+            elif units == 'pt':
+                self.paragraph.paragraph_format.left_indent = Pt(min(margin // 10 * INDENT, MAX_INDENT) * 72)
             elif units == '%':
                 self.paragraph.paragraph_format.left_indent = MAX_INDENT * (units / 100)
-            # TODO handle more units
+            else:
+                # When unit is not supported
+                self.paragraph.paragraph_format.left_indent = None
 
     def add_styles_to_table(self, style):
         if 'text-align' in style:
-            align = style['text-align']
-            align = re.sub('!important', '', align, flags=re.IGNORECASE)
+            align = re.sub('!important', '', style['text-align'], flags=re.IGNORECASE)
 
             if 'center' in align:
                 self.table.alignment = WD_ALIGN_PARAGRAPH.CENTER
@@ -135,26 +134,30 @@ def add_styles_to_table(self, style):
             if 'auto' in margin_left and 'auto' in margin_right:
                 self.table.alignment = WD_ALIGN_PARAGRAPH.CENTER
         elif 'margin-left' in style:
-            margin = style['margin-left']
+            margin = re.sub('!important', '', style['margin-left'], flags=re.IGNORECASE)
             units = re.sub(r'[0-9]+', '', margin)
             margin = int(float(re.sub(r'[a-zA-Z\!]+', '', margin)))
 
             if units == 'px':
                 self.table.left_indent = Inches(min(margin // 10 * INDENT, MAX_INDENT))
             elif units == 'cm':
                 self.table.left_indent = Cm(min(margin // 10 * INDENT, MAX_INDENT) * 2.54)
+            elif units == 'pt':
+                self.table.left_indent = Pt(min(margin // 10 * INDENT, MAX_INDENT) * 72)
             elif units == '%':
                 self.table.left_indent = MAX_INDENT * (units / 100)
-            # TODO handle more units
+            else:
+                # When unit is not supported
+                self.table.left_indent = None
 
     def add_styles_to_run(self, style):
         if 'font-size' in style:
-            font_size = style['font-size']
+            font_size = re.sub('!important', '', style['font-size'], flags=re.IGNORECASE)
             units = re.sub(r'[0-9]+', '', font_size)
             font_size = int(float(re.sub(r'[a-zA-Z\!]+', '', font_size)))
 
             if units == 'px':
-                font_size_unit = Inches(font_size)
+                font_size_unit = Inches(utils.px_to_inches(font_size))
             elif units == 'cm':
                 font_size_unit = Cm(font_size)
             elif units == 'pt':
@@ -168,8 +171,7 @@ def add_styles_to_run(self, style):
                     run.font.size = font_size_unit
 
         if 'color' in style:
-            font_color = style['color'].lower()
-            font_color = re.sub('!important', '', font_color, flags=re.IGNORECASE)
+            font_color = re.sub('!important', '', style['color'].lower(), flags=re.IGNORECASE)
 
             if 'rgb' in font_color:
                 color = re.sub(r'[a-z()]+', '', font_color)
@@ -187,7 +189,7 @@ def add_styles_to_run(self, style):
             self.run.font.color.rgb = RGBColor(*colors)
 
         if 'background-color' in style:
-            background_color = style['background-color'].lower()
+            background_color = re.sub('!important', '', style['background-color'].lower(), flags=re.IGNORECASE)
 
             if 'rgb' in background_color:
                 color = re.sub(r'[a-z()]+', '', background_color)
@@ -361,7 +363,7 @@ def handle_table(self, current_attrs):
 
     def handle_div(self, current_attrs):
         # handle page break
-        if 'style' in current_attrs and "page-break-after: always" in current_attrs['style']:
+        if 'style' in current_attrs and 'page-break-after: always' in current_attrs['style']:
             self.doc.add_page_break()
 
     def handle_link(self, href, text):
@@ -435,7 +437,7 @@ def handle_starttag(self, tag, attrs):
         elif tag == 'li':
             self.handle_li()
 
-        elif tag == "hr":
+        elif tag == 'hr':
             # This implementation was taken from:
             # https://github.com/python-openxml/python-docx/issues/105#issuecomment-62806373
             self.paragraph = self.doc.add_paragraph()
@@ -473,7 +475,7 @@ def handle_starttag(self, tag, attrs):
             self.handle_table(current_attrs)
             return
 
-        elif tag == "div":
+        elif tag == 'div':
             self.handle_div(current_attrs)
 
         # set new run reference point in case of leading line breaks

diff --git a/html4docx/utils.py b/html4docx/utils.py
@@ -44,6 +44,9 @@ def is_url(url):
     parts = urlparse(url)
     return all([parts.scheme, parts.netloc, parts.path])
 
+def px_to_inches(px):
+    return px * 0.0104166667
+
 def rgb_to_hex(rgb):
     return '#' + ''.join(f'{i:02X}' for i in rgb)
 

diff --git a/setup.cfg b/setup.cfg
@@ -1,6 +1,6 @@
 [metadata]
 name = html-for-docx
-version = 1.0.1
+version = 1.0.2
 url = https://github.com/dfop02/html4docx
 project_urls =
     Bug Tracker = https://github.com/dfop02/html4docx/issues
@@ -38,6 +38,6 @@ install_requires =
     beautifulsoup4 >= 4.12.2
 
 [flake8]
-exclude = build,.git,tests/,html4docx/__init__.py,setup.py
+exclude = build,.git,html4docx/__init__.py,setup.py
 ignore = W504,W601,W292,E261,E302,E305
 max-line-length = 127
diff --git a/setup.py b/setup.py
@@ -3,7 +3,7 @@
 
 here   = os.path.abspath(os.path.dirname(__file__))
 README = open(os.path.join(here, 'README.md')).read()
-VERSION = '1.0.1'
+VERSION = '1.0.2'
 
 setup(
     name                 = 'html-for-docx',

diff --git a/tests/context.py b/tests/context.py
@@ -1,6 +1,4 @@
 import os
 import sys
 sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
-
-from html4docx import HtmlToDocx
 test_dir = 'tests'