matthewwithanm__python-markdownify-202

{
  "status": "ok",
  "stdout": "markdownify/main.py:47:                        help=\"Defines the style of <br> conversions: two spaces \"\nmarkdownify/main.py:48:                        \"or backslash at the and of the line thet should break.\")\nmarkdownify/__init__.py:444:    def convert_br(self, el, text, parent_tags):\nmarkdownify/__init__.py:625:            # from <br> tags.  Newlines in the input have already been\nmarkdownify/__init__.py:636:                                break_long_words=False,\nmarkdownify/__init__.py:637:                                break_on_hyphens=False)\n",
  "stderr": "",
  "exit_code": 0
}

{
  "status": "ok",
  "filepath": "markdownify/__init__.py",
  "content": "        text = (text or '').strip(' \\t\\r\\n')\n        if '_inline' in parent_tags:\n            return ' ' + text + ' '\n        if not text:\n            return \"\\n\"\n\n        # indent lines with blockquote marker\n        def _indent_for_blockquote(match):\n            line_content = match.group(1)\n            return '> ' + line_content if line_content else '>'\n        text = re_line_with_content.sub(_indent_for_blockquote, text)\n\n        return '\\n' + text + '\\n\\n'\n\n    def convert_br(self, el, text, parent_tags):\n        if '_inline' in parent_tags:\n            return \"\"\n\n        if self.options['newline_style'].lower() == BACKSLASH:\n            return '\\\\\\n'\n        else:\n            return '  \\n'\n\n    def convert_code(self, el, text, parent_tags):\n        if 'pre' in parent_tags:\n            return text\n        converter = abstract_inline_conversion(lambda self: '`')\n        return converter(self, el, text, parent_tags)\n\n    convert_del = abstract_inline_conversion(lambda self: '~~')\n",
  "start_line": 430,
  "end_line": 460,
  "total_lines": 736,
  "is_truncated": false
}

{
  "status": "ok",
  "stdout": "H1 test: '# foobar'\nTD test: 'bar'\n",
  "stderr": "",
  "exit_code": 0
}

{
  "status": "ok",
  "stdout": "H1 test: '# foobar'\nTD test: ' foobar |'\n",
  "stderr": "",
  "exit_code": 0
}

{
  "status": "ok",
  "filepath": "markdownify/__init__.py",
  "content": "        return text\n\n    def underline(self, text, pad_char):\n        text = (text or '').rstrip()\n        return '\\n\\n%s\\n%s\\n\\n' % (text, pad_char * len(text)) if text else ''\n\n    def convert_a(self, el, text, parent_tags):\n        if '_noformat' in parent_tags:\n            return text\n        prefix, suffix, text = chomp(text)\n        if not text:\n            return ''\n        href = el.get('href')\n        title = el.get('title')\n        # For the replacement see #29: text nodes underscores are escaped\n        if (self.options['autolinks']\n                and text.replace(r'\\_', '_') == href\n                and not title\n                and not self.options['default_title']):\n            # Shortcut syntax\n            return '<%s>' % href\n        if self.options['default_title'] and not title:\n            title = href\n        title_part = ' \"%s\"' % title.replace('\"', r'\\\"') if title else ''\n        return '%s[%s](%s%s)%s' % (prefix, text, href, title_part, suffix) if href else text\n\n    convert_b = abstract_inline_conversion(lambda self: 2 * self.options['strong_em_symbol'])\n\n    def convert_blockquote(self, el, text, parent_tags):\n        # handle some early-exit scenarios\n        text = (text or '').strip(' \\t\\r\\n')\n        if '_inline' in parent_tags:\n            return ' ' + text + ' '\n        if not text:\n            return \"\\n\"\n\n        # indent lines with blockquote marker\n        def _indent_for_blockquote(match):\n            line_content = match.group(1)\n            return '> ' + line_content if line_content else '>'\n        text = re_line_with_content.sub(_indent_for_blockquote, text)\n\n        return '\\n' + text + '\\n\\n'\n\n    def convert_br(self, el, text, parent_tags):\n        if '_inline' in parent_tags:\n            return \"\"\n\n        if self.options['newline_style'].lower() == BACKSLASH:\n            return '\\\\\\n'\n        else:\n            return '  \\n'\n\n    def convert_code(self, el, text, parent_tags):\n        if 'pre' in parent_tags:\n            return text\n        converter = abstract_inline_conversion(lambda self: '`')\n        return converter(self, el, text, parent_tags)\n\n    convert_del = abstract_inline_conversion(lambda self: '~~')\n\n    def convert_div(self, el, text, parent_tags):\n        if '_inline' in parent_tags:\n            return ' ' + text.strip() + ' '\n        text = text.strip()\n        return '\\n\\n%s\\n\\n' % text if text else ''\n\n    convert_article = convert_div\n\n    convert_section = convert_div\n\n    convert_em = abstract_inline_conversion(lambda self: self.options['strong_em_symbol'])\n\n    convert_kbd = convert_code\n\n    def convert_dd(self, el, text, parent_tags):\n        text = (text or '').strip()\n        if '_inline' in parent_tags:\n            return ' ' + text + ' '\n        if not text:\n            return '\\n'\n\n        # indent definition content lines by four spaces\n        def _indent_for_dd(match):\n            line_content = match.group(1)\n            return '    ' + line_content if line_content else ''\n        text = re_line_with_content.sub(_indent_for_dd, text)\n\n        # insert definition marker into first-line indent whitespace\n        text = ':' + text[1:]\n\n        return '%s\\n' % text\n\n    # definition lists are formatted as follows:\n    #   https://pandoc.org/MANUAL.html#definition-lists\n    #   https://michelf.ca/projects/php-markdown/extra/#def-list\n    convert_dl = convert_div\n\n    def convert_dt(self, el, text, parent_tags):\n        # remove newlines from term text\n        text = (text or '').strip()\n        text = re_all_whitespace.sub(' ', text)\n        if '_inline' in parent_tags:\n            return ' ' + text + ' '\n        if not text:\n            return '\\n'\n\n        # TODO - format consecutive <dt> elements as directly adjacent lines):\n        #   https://michelf.ca/projects/php-markdown/extra/#def-list\n\n        return '\\n\\n%s\\n' % text\n\n    def _convert_hn(self, n, el, text, parent_tags):\n        \"\"\" Method name prefixed with _ to prevent <hn> to call this \"\"\"\n        if '_inline' in parent_tags:\n            return text\n\n        # prevent MemoryErrors in case of very large n\n        n = max(1, min(6, n))\n\n        style = self.options['heading_style'].lower()\n        text = text.strip()\n        if style == UNDERLINED and n <= 2:\n            line = '=' if n == 1 else '-'\n            return self.underline(text, line)\n        text = re_all_whitespace.sub(' ', text)\n        hashes = '#' * n\n        if style == ATX_CLOSED:\n            return '\\n\\n%s %s %s\\n\\n' % (hashes, text, hashes)\n        return '\\n\\n%s %s\\n\\n' % (hashes, text)\n\n    def convert_hr(self, el, text, parent_tags):\n        return '\\n\\n---\\n\\n'\n\n    convert_i = convert_em\n\n    def convert_img(self, el, text, parent_tags):\n        alt = el.attrs.get('alt', None) or ''\n        src = el.attrs.get('src', None) or ''\n        title = el.attrs.get('title', None) or ''\n        title_part = ' \"%s\"' % title.replace('\"', r'\\\"') if title else ''\n        if ('_inline' in parent_tags\n                and el.parent.name not in self.options['keep_inline_images_in']):\n            return alt\n\n        return '![%s](%s%s)' % (alt, src, title_part)\n\n    def convert_video(self, el, text, parent_tags):\n        if ('_inline' in parent_tags\n                and el.parent.name not in self.options['keep_inline_images_in']):",
  "start_line": 400,
  "end_line": 549,
  "total_lines": 736,
  "is_truncated": true
}

{
  "status": "error",
  "error_type": "CommandError",
  "error_message": "",
  "details": {
    "stdout": "",
    "stderr": "",
    "exit_code": 1
  }
}

{
  "status": "ok",
  "stdout": "tests/test_advanced.py:33:    assert md('First line <code>blah blah<br />blah blah</code> second line') \\\ntests/test_conversions.py:79:def test_br():\ntests/test_conversions.py:80:    assert md('a<br />b<br />c') == 'a  \\nb  \\nc'\ntests/test_conversions.py:81:    assert md('a<br />b<br />c', newline_style=BACKSLASH) == 'a\\\\\\nb\\\\\\nc'\ntests/test_conversions.py:195:    assert md('<h3>A <br>B</h3>', heading_style=ATX) == '\\n\\n### A B\\n\\n'\ntests/test_conversions.py:267:    assert md('<p>12345<br />67890</p>', wrap=True, wrap_width=10, newline_style=BACKSLASH) == '\\n\\n12345\\\\\\n67890\\n\\n'\ntests/test_conversions.py:268:    assert md('<p>12345<br />67890</p>', wrap=True, wrap_width=50, newline_style=BACKSLASH) == '\\n\\n12345\\\\\\n67890\\n\\n'\ntests/test_conversions.py:269:    assert md('<p>12345<br />67890</p>', wrap=True, wrap_width=10, newline_style=SPACES) == '\\n\\n12345  \\n67890\\n\\n'\ntests/test_conversions.py:270:    assert md('<p>12345<br />67890</p>', wrap=True, wrap_width=50, newline_style=SPACES) == '\\n\\n12345  \\n67890\\n\\n'\ntests/test_conversions.py:271:    assert md('<p>12345678901<br />12345</p>', wrap=True, wrap_width=10, newline_style=BACKSLASH) == '\\n\\n12345678901\\\\\\n12345\\n\\n'\ntests/test_conversions.py:272:    assert md('<p>12345678901<br />12345</p>', wrap=True, wrap_width=50, newline_style=BACKSLASH) == '\\n\\n12345678901\\\\\\n12345\\n\\n'\ntests/test_conversions.py:273:    assert md('<p>12345678901<br />12345</p>', wrap=True, wrap_width=10, newline_style=SPACES) == '\\n\\n12345678901  \\n12345\\n\\n'\ntests/test_conversions.py:274:    assert md('<p>12345678901<br />12345</p>', wrap=True, wrap_width=50, newline_style=SPACES) == '\\n\\n12345678901  \\n12345\\n\\n'\ntests/test_conversions.py:275:    assert md('<p>1234 5678 9012<br />67890</p>', wrap=True, wrap_width=10, newline_style=BACKSLASH) == '\\n\\n1234 5678\\n9012\\\\\\n67890\\n\\n'\ntests/test_conversions.py:276:    assert md('<p>1234 5678 9012<br />67890</p>', wrap=True, wrap_width=10, newline_style=SPACES) == '\\n\\n1234 5678\\n9012  \\n67890\\n\\n'\ntests/test_tables.py:60:table_with_linebreaks = \"\"\"<table>\ntests/test_tables.py:275:    assert md(table_with_linebreaks) == '\\n\\n| Firstname | Lastname | Age |\\n| --- | --- | --- |\\n| Jill | Smith Jackson | 50 |\\n| Eve | Jackson Smith | 94 |\\n\\n'\ntests/test_tables.py:292:    assert md(table_with_linebreaks, table_infer_header=True) == '\\n\\n| Firstname | Lastname | Age |\\n| --- | --- | --- |\\n| Jill | Smith Jackson | 50 |\\n| Eve | Jackson Smith | 94 |\\n\\n'\n",
  "stderr": "",
  "exit_code": 0
}

{
  "status": "ok",
  "filepath": "markdownify/__init__.py",
  "content": "from bs4 import BeautifulSoup, Comment, Doctype, NavigableString, Tag\nfrom textwrap import fill\nimport re\nimport six\n\n\n# General-purpose regex patterns\nre_convert_heading = re.compile(r'convert_h(\\d+)')\nre_line_with_content = re.compile(r'^(.*)', flags=re.MULTILINE)\nre_whitespace = re.compile(r'[\\t ]+')\nre_all_whitespace = re.compile(r'[\\t \\r\\n]+')\nre_newline_whitespace = re.compile(r'[\\t \\r\\n]*[\\r\\n][\\t \\r\\n]*')\nre_html_heading = re.compile(r'h(\\d+)')\n\n# Pattern for creating convert_<tag> function names from tag names\nre_make_convert_fn_name = re.compile(r'[\\[\\]:-]')\n\n# Extract (leading_nl, content, trailing_nl) from a string\n# (functionally equivalent to r'^(\\n*)(.*?)(\\n*)$', but greedy is faster than reluctant here)\nre_extract_newlines = re.compile(r'^(\\n*)((?:.*[^\\n])?)(\\n*)$', flags=re.DOTALL)\n\n# Escape miscellaneous special Markdown characters\nre_escape_misc_chars = re.compile(r'([]\\\\&<`[>~=+|])')\n\n# Escape sequence of one or more consecutive '-', preceded\n# and followed by whitespace or start/end of fragment, as it\n# might be confused with an underline of a header, or with a\n# list marker\nre_escape_misc_dash_sequences = re.compile(r'(\\s|^)(-+(?:\\s|$))')\n\n# Escape sequence of up to six consecutive '#', preceded\n# and followed by whitespace or start/end of fragment, as\n# it might be confused with an ATX heading\nre_escape_misc_hashes = re.compile(r'(\\s|^)(#{1,6}(?:\\s|$))')\n\n# Escape '.' or ')' preceded by up to nine digits, as it might be\n# confused with a list item\nre_escape_misc_list_items = re.compile(r'((?:\\s|^)[0-9]{1,9})([.)](?:\\s|$))')\n\n# Heading styles\nATX = 'atx'\nATX_CLOSED = 'atx_closed'\nUNDERLINED = 'underlined'\nSETEXT = UNDERLINED\n\n# Newline style\nSPACES = 'spaces'\nBACKSLASH = 'backslash'\n\n# Strong and emphasis style\nASTERISK = '*'\nUNDERSCORE = '_'\n\n# Document strip styles\nLSTRIP = 'lstrip'\nRSTRIP = 'rstrip'\nSTRIP = 'strip'\n\n\ndef chomp(text):\n    \"\"\"\n    If the text in an inline tag like b, a, or em contains a leading or trailing\n    space, strip the string and return a space as suffix of prefix, if needed.\n    This function is used to prevent conversions like\n        <b> foo</b> => ** foo**\n    \"\"\"\n    prefix = ' ' if text and text[0] == ' ' else ''\n    suffix = ' ' if text and text[-1] == ' ' else ''\n    text = text.strip()\n    return (prefix, suffix, text)\n\n\ndef abstract_inline_conversion(markup_fn):\n    \"\"\"\n    This abstracts all simple inline tags like b, em, del, ...\n    Returns a function that wraps the chomped text in a pair of the string\n    that is returned by markup_fn, with '/' inserted in the string used after\n    the text if it looks like an HTML tag. markup_fn is necessary to allow for\n    references to self.strong_em_symbol etc.\n    \"\"\"\n    def implementation(self, el, text, parent_tags):\n        markup_prefix = markup_fn(self)\n        if markup_prefix.startswith('<') and markup_prefix.endswith('>'):\n            markup_suffix = '</' + markup_prefix[1:]\n        else:\n            markup_suffix = markup_prefix\n        if '_noformat' in parent_tags:\n            return text\n        prefix, suffix, text = chomp(text)\n        if not text:\n            return ''\n        return '%s%s%s%s%s' % (prefix, markup_prefix, text, markup_suffix, suffix)\n    return implementation\n\n\ndef _todict(obj):\n    return dict((k, getattr(obj, k)) for k in dir(obj) if not k.startswith('_'))\n\n\ndef should_remove_whitespace_inside(el):",
  "start_line": 1,
  "end_line": 100,
  "total_lines": 736,
  "is_truncated": false
}

{
  "status": "ok",
  "stdout": "677:    def convert_td(self, el, text, parent_tags):\n",
  "stderr": "",
  "exit_code": 0
}

{
  "status": "ok",
  "filepath": "markdownify/__init__.py",
  "content": "\n    def convert_caption(self, el, text, parent_tags):\n        return text.strip() + '\\n\\n'\n\n    def convert_figcaption(self, el, text, parent_tags):\n        return '\\n\\n' + text.strip() + '\\n\\n'\n\n    def convert_td(self, el, text, parent_tags):\n        colspan = 1\n        if 'colspan' in el.attrs and el['colspan'].isdigit():\n            colspan = int(el['colspan'])\n        return ' ' + text.strip().replace(\"\\n\", \" \") + ' |' * colspan\n\n    def convert_th(self, el, text, parent_tags):\n        colspan = 1\n        if 'colspan' in el.attrs and el['colspan'].isdigit():\n            colspan = int(el['colspan'])\n        return ' ' + text.strip().replace(\"\\n\", \" \") + ' |' * colspan\n\n    def convert_tr(self, el, text, parent_tags):\n        cells = el.find_all(['td', 'th'])\n        is_first_row = el.find_previous_sibling() is None\n        is_headrow = (\n            all([cell.name == 'th' for cell in cells])\n            or (el.parent.name == 'thead'\n                # avoid multiple tr in thead\n                and len(el.parent.find_all('tr')) == 1)\n        )\n        is_head_row_missing = (\n            (is_first_row and not el.parent.name == 'tbody')\n            or (is_first_row and el.parent.name == 'tbody' and len(el.parent.parent.find_all(['thead'])) < 1)",
  "start_line": 670,
  "end_line": 700,
  "total_lines": 736,
  "is_truncated": false
}

{
  "status": "ok",
  "stdout": "H1 test: '# foobar'\nTD test: ' foobar |'\n",
  "stderr": "",
  "exit_code": 0
}

{
  "status": "ok",
  "stdout": "H1 test: '# foobar'\nTD test: ' foobar |'\n",
  "stderr": "",
  "exit_code": 0
}

{
  "status": "ok",
  "stdout": "    def convert_br(self, el, text, parent_tags):\n        if '_inline' in parent_tags:\n            return \"\"\n\n",
  "stderr": "",
  "exit_code": 0
}

{
  "status": "ok",
  "filepath": "markdownify/__init__.py",
  "occurrences": 1,
  "strategy": "exact",
  "diff": "--- a/markdownify/__init__.py\n+++ b/markdownify/__init__.py\n@@ -443,7 +443,7 @@\n \n     def convert_br(self, el, text, parent_tags):\n         if '_inline' in parent_tags:\n-            return \"\"\n+            return \" \"\n \n         if self.options['newline_style'].lower() == BACKSLASH:\n             return '\\\\\\n'\n",
  "is_truncated": false
}

{
  "status": "ok",
  "stdout": "H1 test: '# foo bar'\nTD test: ' foo bar |'\n",
  "stderr": "",
  "exit_code": 0
}

{
  "status": "ok",
  "stdout": ".................................................                        [100%]\n49 passed in 0.12s\n",
  "stderr": "",
  "exit_code": 0
}

{
  "status": "ok",
  "stdout": "........                                                                 [100%]\n8 passed in 0.05s\n",
  "stderr": "",
  "exit_code": 0
}

{
  "status": "ok",
  "stdout": " M markdownify/__init__.py\ndiff --git a/markdownify/__init__.py b/markdownify/__init__.py\nindex 69ec328..3b540e0 100644\n--- a/markdownify/__init__.py\n+++ b/markdownify/__init__.py\n@@ -443,7 +443,7 @@ class MarkdownConverter(object):\n \n     def convert_br(self, el, text, parent_tags):\n         if '_inline' in parent_tags:\n-            return \"\"\n+            return \" \"\n \n         if self.options['newline_style'].lower() == BACKSLASH:\n             return '\\\\\\n'\n",
  "stderr": "",
  "exit_code": 0
}

{
  "status": "ok",
  "stdout": "No spaces: '### foo bar'\nWith spaces: '### foo bar'\n",
  "stderr": "",
  "exit_code": 0
}

{
  "status": "ok",
  "patch_size": 436,
  "files_changed": 1
}