Table padding option (#130)

Add Table padding option

ChangeLog.rst

@@ -2,6 +2,7 @@ xxxx.x.x
 =========
 ----
 
+* Fix #125: --pad_tables now pads table cells to make them look nice.
 * Fix #114: Break does not interrupt blockquotes
 * Deprecation warnings for URL retreival
 

docs/usage.md

@@ -131,3 +131,4 @@ Command line options
 | `--mark-code`                                          | Mark code with [code]...[/code] blocks
 | `--no-wrap-links`                                      | Do not wrap links during text wrapping. Implies `--reference-links`
 | `--decode-errors`=`HANDLER`                            | What to do in case an error is encountered. `ignore`, `strict`, `replace` etc.
+| `--pad-tables`                                         | Use padding to make tables look good.

html2text/__init__.py

@@ -27,7 +27,8 @@
     list_numbering_start,
     dumb_css_parser,
     escape_md_section,
-    skipwrap
+    skipwrap,
+    pad_tables_in_text
 )
 
 __version__ = (2016, 4, 2)
@@ -77,6 +78,7 @@ def __init__(self, out=None, baseurl='', bodywidth=config.BODY_WIDTH):
         self.hide_strikethrough = False  # covered in cli
         self.mark_code = config.MARK_CODE
         self.wrap_links = config.WRAP_LINKS  # covered in cli
+        self.pad_tables = config.PAD_TABLES  # covered in cli
         self.tag_callback = None
 
         if out is None:  # pragma: no cover
@@ -130,7 +132,11 @@ def feed(self, data):
     def handle(self, data):
         self.feed(data)
         self.feed("")
-        return self.optwrap(self.close())
+        markdown = self.optwrap(self.close())
+        if self.pad_tables:
+            return pad_tables_in_text(markdown)
+        else:
+            return markdown
 
     def outtextf(self, s):
         self.outtextlist.append(s)
@@ -556,8 +562,16 @@ def handle_tag(self, tag, attrs, start):
                         self.o('</{0}>'.format(tag))
 
             else:
-                if tag == "table" and start:
-                    self.table_start = True
+                if tag == "table":
+                    if start:
+                        self.table_start = True
+                        if self.pad_tables:
+                            self.o("<"+config.TABLE_MARKER_FOR_PAD+">")
+                            self.o("  \n")
+                    else:
+                        if self.pad_tables:
+                            self.o("</"+config.TABLE_MARKER_FOR_PAD+">")
+                            self.o("  \n")
                 if tag in ["td", "th"] and start:
                     if self.split_next_td:
                         self.o("| ")

html2text/cli.py

@@ -23,6 +23,13 @@ class bcolors:  # pragma: no cover
         '%prog [(filename|url) [encoding]]',
         version='%prog ' + ".".join(map(str, __version__))
     )
+    p.add_option(
+        "--pad-tables",
+        dest="pad_tables",
+        action="store_true",
+        default=config.PAD_TABLES,
+        help="pad the cells to equal column width in tables"
+    )
     p.add_option(
         "--no-wrap-links",
         dest="wrap_links",
@@ -271,5 +278,6 @@ class bcolors:  # pragma: no cover
     h.links_each_paragraph = options.links_each_paragraph
     h.mark_code = options.mark_code
     h.wrap_links = options.wrap_links
+    h.pad_tables = options.pad_tables
 
     wrapwrite(h.handle(data))

html2text/config.py

@@ -3,6 +3,8 @@
 # Use Unicode characters instead of their ascii psuedo-replacements
 UNICODE_SNOB = 0
 
+# Marker to use for marking tables for padding post processing
+TABLE_MARKER_FOR_PAD = "special_marker_for_table_padding"
 # Escape all special characters.  Output is less readable, but avoids
 # corner case formatting issues.
 ESCAPE_SNOB = 0
@@ -36,6 +38,7 @@
 IGNORE_EMPHASIS = False
 MARK_CODE = False
 DECODE_ERRORS = 'strict'
+PAD_TABLES = False
 
 # Convert links with same href and text to <href> format if they are absolute links
 USE_AUTOMATIC_LINKS = True

html2text/utils.py

@@ -244,3 +244,55 @@ def escape_md_section(text, snob=False):
     text = config.RE_MD_DASH_MATCHER.sub(r"\1\\\2", text)
 
     return text
+
+def reformat_table(lines, right_margin):
+    """
+    Given the lines of a table
+    padds the cells and returns the new lines
+    """
+    # find the maximum width of the columns
+    max_width = [len(x.rstrip()) + right_margin for x in lines[0].split('|')]
+    for line in lines:
+        cols = [x.rstrip() for x in line.split('|')]
+        max_width = [max(len(x) + right_margin, old_len)
+                     for x, old_len in zip(cols, max_width)]
+
+    # reformat
+    new_lines = []
+    for line in lines:
+        cols = [x.rstrip() for x in line.split('|')]
+        if set(line.strip()) == set('-|'):
+            filler = '-'
+            new_cols = [x.rstrip() + (filler * (M - len(x.rstrip())))
+                        for x, M in zip(cols, max_width)]
+        else:
+            filler = ' '
+            new_cols = [x.rstrip() + (filler * (M - len(x.rstrip())))
+                        for x, M in zip(cols, max_width)]
+        new_lines.append('|'.join(new_cols))
+    return new_lines
+
+def pad_tables_in_text(text, right_margin=1):
+    """
+    Provide padding for tables in the text
+    """
+    lines = text.split('\n')
+    table_buffer, altered_lines, table_widths, table_started = [], [], [], False
+    new_lines = []
+    for line in lines:
+        # Toogle table started
+        if (config.TABLE_MARKER_FOR_PAD in line):
+            table_started = not table_started
+            if not table_started:
+                table = reformat_table(table_buffer, right_margin)
+                new_lines.extend(table)
+                table_buffer = []
+                new_lines.append('')
+            continue
+        # Process lines
+        if table_started:
+            table_buffer.append(line)
+        else:
+            new_lines.append(line)
+    new_text = '\n'.join(new_lines)
+    return new_text

test/pad_table.html

@@ -0,0 +1,26 @@
+<!DOCTYPE html> <html>
+    <head lang="en"> <meta charset="UTF-8"> <title></title> </head>
+    <body> <h1>This is a test document</h1> With some text, <code>code</code>, <b>bolds</b> and <i>italics</i>.  <h2>This is second header</h2> <p style="display: none">Displaynone text</p> 
+    <table>
+        <tr> <th>Header 1</th> <th>Header 2</th> <th>Header 3</th> </tr>
+        <tr> <td>Content 1</td> <td>2</td> <td><img src="http://lorempixel.com/200/200" alt="200"/> Image!</td> </tr>
+        <tr> <td>Content 1 longer</td> <td>Content 2</td> <td>blah</td> </tr>
+        <tr> <td>Content </td> <td>Content 2</td> <td>blah</td> </tr>
+        <tr> <td>t </td> <td>Content 2</td> <td>blah blah blah</td> </tr>
+    </table>
+
+
+    <table> <tr> <th>H1</th> <th>H2</th> <th>H3</th> </tr>
+        <tr> <td>C1</td> <td>Content 2</td> <td>x</td> </tr>
+        <tr> <td>C123</td> <td>Content 2</td> <td>xyz</td> </tr>
+    </table>
+
+some content between the tables<br>
+
+    <table> <tr> <th>Header 1</th> <th>Header 2</th> <th>Header 3</th> </tr>
+        <tr> <td>Content 1</td> <td>Content 2</td> <td><img src="http://lorempixel.com/200/200" alt="200"/> Image!</td> </tr>
+        <tr> <td>Content 1</td> <td>Content 2 longer</td> <td><img src="http://lorempixel.com/200/200" alt="200"/> Image!</td> </tr>
+    </table>
+
+something else entirely
+</body> </html>

test/pad_table.md

@@ -0,0 +1,28 @@
+# This is a test document
+
+With some text, `code`, **bolds** and _italics_.
+
+## This is second header
+
+Displaynone text
+
+Header 1         | Header 2  | Header 3                                     
+-----------------|-----------|----------------------------------------------
+Content 1        | 2         | ![200](http://lorempixel.com/200/200) Image! 
+Content 1 longer | Content 2 | blah                                         
+Content          | Content 2 | blah                                         
+t                | Content 2 | blah blah blah                               
+
+H1   | H2        | H3  
+-----|-----------|-----
+C1   | Content 2 | x   
+C123 | Content 2 | xyz 
+
+some content between the tables  
+Header 1  | Header 2         | Header 3                                     
+----------|------------------|----------------------------------------------
+Content 1 | Content 2        | ![200](http://lorempixel.com/200/200) Image! 
+Content 1 | Content 2 longer | ![200](http://lorempixel.com/200/200) Image! 
+
+something else entirely
+

test/test_html2text.py

@@ -170,6 +170,10 @@ def test_func(self):
         module_args['mark_code'] = True
         cmdline_args.append('--mark-code')
 
+    if base_fn.startswith('pad_table'):
+        module_args['pad_tables'] = True
+        cmdline_args.append('--pad-tables')
+
     if base_fn not in ['bodywidth_newline.html', 'abbr_tag.html']:
         test_func = None