Python pygments.formatters.HtmlFormatter() Examples

def _wiki_code(content):
    """
    >>> u = _wiki_code('<code class="python">my_code()</code>')
    >>> expected = '<div class="highlight"><pre><span class="n">my_code</span><span class="p">()</span>\\n</pre></div>\\n'
    >>> expected in u
    True

    """
    css_class = "python"
    if css_class:
        content = content.replace('<code>', '<code class=\"%s\">' % css_class);

    #syntax_css = u"<style>%s</style>" % HtmlFormatter().get_style_defs('.highlight')
    #content = syntax_css + content

    return re.sub(r'\<code\s+class\s*\=\s*\"([^\"]+)\"\>(.*?)\<\/code>',
                  _wiki_code_callback, content, flags=re.I | re.S) 

def stacktraces():
    code = []
    for threadId, stack in sys._current_frames().items():
        code.append("\n# ThreadID: %s" % threadId)
        for filename, lineno, name, line in traceback.extract_stack(stack):
            code.append('File: "%s", line %d, in %s' % (filename, lineno, name))
            if line:
                code.append("  %s" % (line.strip()))
 
    return highlight("\n".join(code), PythonLexer(), HtmlFormatter(
      full=False,
      # style="native",
      noclasses=True,
    ))


# This part was made by nagylzs 

def code(self, session=None):
        all_errors = ""

        try:
            dag_id = request.args.get('dag_id')
            dag_orm = DagModel.get_dagmodel(dag_id, session=session)
            code = DagCode.get_code_by_fileloc(dag_orm.fileloc)
            html_code = Markup(highlight(
                code, lexers.PythonLexer(), HtmlFormatter(linenos=True)))

        except Exception as e:
            all_errors += (
                "Exception encountered during " +
                "dag_id retrieval/dag retrieval fallback/code highlighting:\n\n{}\n".format(e)
            )
            html_code = Markup('<p>Failed to load file.</p><p>Details: {}</p>').format(
                escape(all_errors))

        return self.render_template(
            'airflow/dag_code.html', html_code=html_code, dag=dag_orm, title=dag_id,
            root=request.args.get('root'),
            demo_mode=conf.getboolean('webserver', 'demo_mode'),
            wrapped=conf.getboolean('webserver', 'default_wrap')) 

def test_external_css():
    # test correct behavior
    # CSS should be in /tmp directory
    fmt1 = HtmlFormatter(full=True, cssfile='fmt1.css', outencoding='utf-8')
    # CSS should be in TESTDIR (TESTDIR is absolute)
    fmt2 = HtmlFormatter(full=True, cssfile=path.join(TESTDIR, 'fmt2.css'),
                         outencoding='utf-8')
    tfile = tempfile.NamedTemporaryFile(suffix='.html')
    fmt1.format(tokensource, tfile)
    try:
        fmt2.format(tokensource, tfile)
        assert path.isfile(path.join(TESTDIR, 'fmt2.css'))
    except IOError:
        # test directory not writable
        pass
    tfile.close()

    assert path.isfile(path.join(path.dirname(tfile.name), 'fmt1.css'))
    os.unlink(path.join(path.dirname(tfile.name), 'fmt1.css'))
    try:
        os.unlink(path.join(TESTDIR, 'fmt2.css'))
    except OSError:
        pass 

def show_pseudo(self, item, primary):
    cur = self.db_cursor()
    if primary:
      db = "main"
    else:
      db = "diff"
    ea = str(int(item[1], 16))
    sql = "select prototype, pseudocode, name from %s.functions where address = ?"
    sql = sql % db
    cur.execute(sql, (str(ea), ))
    row = cur.fetchone()
    if row is None or row["prototype"] is None or row["pseudocode"] is None:
      Warning("Sorry, there is no pseudo-code available for the selected function.")
    else:
      fmt = HtmlFormatter()
      fmt.noclasses = True
      fmt.linenos = True
      func = "%s\n%s" % (row["prototype"], row["pseudocode"])
      src = highlight(func, CppLexer(), fmt)
      title = "Pseudo-code for %s" % row["name"]
      cdiffer = CHtmlViewer()
      cdiffer.Show(src, title)
    cur.close() 

def show_asm(self, item, primary):
    cur = self.db_cursor()
    if primary:
      db = "main"
    else:
      db = "diff"
    ea = str(int(item[1], 16))
    sql = "select prototype, assembly, name from %s.functions where address = ?"
    sql = sql % db
    cur.execute(sql, (ea, ))
    row = cur.fetchone()
    if row is None:
      Warning("Sorry, there is no assembly available for the selected function.")
    else:
      fmt = HtmlFormatter()
      fmt.noclasses = True
      fmt.linenos = True
      asm = self.prettify_asm(row["assembly"])
      final_asm = "; %s\n%s proc near\n%s\n%s endp\n"
      final_asm = final_asm % (row["prototype"], row["name"], asm, row["name"])
      src = highlight(final_asm, NasmLexer(), fmt)
      title = "Assembly for %s" % row["name"]
      cdiffer = CHtmlViewer()
      cdiffer.Show(src, title)
    cur.close() 

def test_formatter_encodings():
    from pygments.formatters import HtmlFormatter

    # unicode output
    fmt = HtmlFormatter()
    tokens = [(Text, u"ä")]
    out = format(tokens, fmt)
    assert type(out) is str
    assert u"ä" in out

    # encoding option
    fmt = HtmlFormatter(encoding="latin1")
    tokens = [(Text, u"ä")]
    assert u"ä".encode("latin1") in format(tokens, fmt)

    # encoding and outencoding option
    fmt = HtmlFormatter(encoding="latin1", outencoding="utf8")
    tokens = [(Text, u"ä")]
    assert u"ä".encode("utf8") in format(tokens, fmt) 

def display_source_ipython(self):
        """
        Convenience method to print the loaded source file
        as syntax highlighted HTML within IPython.
        """
        from pygments import highlight
        from pygments.lexers import SLexer

        from pygments.formatters import HtmlFormatter
        import IPython.display as display

        with open(self.source_file) as f:
            code = f.read()

        formatter = HtmlFormatter()
        return display.HTML('<style type="text/css">{}</style>{}'.format(
            formatter.get_style_defs('.highlight'),
            highlight(code, SLexer(), formatter))) 

def _render_asm(self, instr, mnemonic_width, options, fill_char=""):
        formatter = HtmlFormatter()
        formatter.noclasses = True
        formatter.nowrap = True

        oprnds_str = ", ".join([oprnd.to_string(**options) for oprnd in instr.operands])

        asm_str = instr.prefix + " " if instr.prefix else ""
        asm_str += instr.mnemonic + fill_char * (mnemonic_width - len(instr.mnemonic))
        asm_str += " " + oprnds_str if oprnds_str else ""

        # TODO Highlight for ARM too.
        asm_str = highlight(asm_str, NasmLexer(), formatter)
        asm_str = asm_str.replace("span", "font")
        asm_str = asm_str.replace('style="color: ', 'color="')
        asm_str = asm_str.replace('style="border: 1px solid ', 'color="')

        return self.asm_tpl.format(address=instr.address, size=instr.size, assembly=asm_str) 

def test_valid_output():
    # test all available wrappers
    fmt = HtmlFormatter(full=True, linenos=True, noclasses=True,
                        outencoding='utf-8')

    handle, pathname = tempfile.mkstemp('.html')
    with os.fdopen(handle, 'w+b') as tfile:
        fmt.format(tokensource, tfile)
    catname = os.path.join(TESTDIR, 'dtds', 'HTML4.soc')
    try:
        import subprocess
        po = subprocess.Popen(['nsgmls', '-s', '-c', catname, pathname],
                              stdout=subprocess.PIPE)
        ret = po.wait()
        output = po.stdout.read()
        po.stdout.close()
    except OSError:
        # nsgmls not available
        pass
    else:
        if ret:
            print(output)
        assert not ret, 'nsgmls run reported errors'

    os.unlink(pathname) 

def test_get_style_defs_contains_style_specific_line_numbers_styles():
    class TestStyle(Style):
        line_number_color = '#ff0000'
        line_number_background_color = '#0000ff'
        line_number_special_color = '#00ff00'
        line_number_special_background_color = '#ffffff'

    style_defs = HtmlFormatter(style=TestStyle).get_style_defs().splitlines()

    assert style_defs[1] == (
        'td.linenos pre '
        '{ color: #ff0000; background-color: #0000ff; padding: 0 5px 0 5px; }'
    )
    assert style_defs[2] == (
        'span.linenos '
        '{ color: #ff0000; background-color: #0000ff; padding: 0 5px 0 5px; }'
    )
    assert style_defs[3] == (
        'td.linenos pre.special '
        '{ color: #00ff00; background-color: #ffffff; padding: 0 5px 0 5px; }'
    )
    assert style_defs[4] == (
        'span.linenos.special '
        '{ color: #00ff00; background-color: #ffffff; padding: 0 5px 0 5px; }'
    ) 

def block_code(text, lang, inlinestyles=False, linenos=False):
    if not lang:
        text = text.strip()
        return u'<pre><code>%s</code></pre>\n' % mistune.escape(text)

    try:
        lexer = get_lexer_by_name(lang, stripall=True)
        formatter = HtmlFormatter(
            noclasses=inlinestyles, linenos=linenos
        )
        code = highlight(text, lexer, formatter)
        if linenos:
            return '<div class="highlight-wrapper">%s</div>\n' % code
        return code
    except:
        return '<pre class="%s"><code>%s</code></pre>\n' % (
            lang, mistune.escape(text)
        ) 

def view_source(context, web_view, filename):
    from base64 import b64encode
    from os.path import join
    from pygments import highlight
    from pygments.formatters import HtmlFormatter
    from pygments.lexers import get_lexer_for_filename

    from java.io import BufferedReader, InputStreamReader

    stream = context.getAssets().open(join(ASSET_SOURCE_DIR, filename))
    reader = BufferedReader(InputStreamReader(stream))
    text = "\n".join(iter(reader.readLine, None))

    formatter = HtmlFormatter()
    body = highlight(text, get_lexer_for_filename(filename), formatter)
    html = ("<html><head><style>{}\n{}</style></head><body>{}</body></html>"
            .format(formatter.get_style_defs(), EXTRA_CSS, body)).encode()
    web_view.loadData(b64encode(html).decode(), "text/html", "base64") 

def get_experiment(path):
    logdir = APP.config['logdir']
    complete_path = os.path.join(logdir, path)
    if os.path.isfile(complete_path):
        file_content = get_file(complete_path)
        if path.endswith(".log"):
            result = ansiconv.to_html(html.escape(file_content))
        elif path.endswith(".ini"):
            lexer = IniLexer()
            formatter = HtmlFormatter(linenos=True)
            result = highlight(file_content, lexer, formatter)
        else:
            result = "Unknown file type: '{}'.".format(complete_path)
    else:
        result = "File '{}' does not exist.".format(complete_path)
    return Response(result, mimetype='text/html', status=200) 

def get_experiment(path):
    logdir = APP.config['logdir']
    complete_path = os.path.join(logdir, path)
    if os.path.isfile(complete_path):
        file_content = get_file(complete_path)
        if path.endswith(".log"):
            result = ansiconv.to_html(html.escape(file_content))
        elif path.endswith(".ini"):
            lexer = IniLexer()
            formatter = HtmlFormatter(linenos=True)
            result = highlight(file_content, lexer, formatter)
        else:
            result = "Unknown file type: '{}'.".format(complete_path)
    else:
        result = "File '{}' does not exist.".format(complete_path)
    return Response(result, mimetype='text/html', status=200) 

def get_experiment(path):
    logdir = APP.config['logdir']
    complete_path = os.path.join(logdir, path)
    if os.path.isfile(complete_path):
        file_content = get_file(complete_path)
        if path.endswith(".log"):
            result = ansiconv.to_html(html.escape(file_content))
        elif path.endswith(".ini"):
            lexer = IniLexer()
            formatter = HtmlFormatter(linenos=True)
            result = highlight(file_content, lexer, formatter)
        else:
            result = "Unknown file type: '{}'.".format(complete_path)
    else:
        result = "File '{}' does not exist.".format(complete_path)
    return Response(result, mimetype='text/html', status=200) 

def column_definition(table_name, col_name):
    """
    Get the source of a column function.

    If a column is a registered Series and not a function then all that is
    returned is {'type': 'series'}.

    If the column is a registered function then the JSON returned has keys
    "type", "filename", "lineno", "text", and "html". "text" is the raw
    text of the function, "html" has been marked up by Pygments.

    """
    col_type = orca.get_table(table_name).column_type(col_name)

    if col_type != 'function':
        return jsonify(type=col_type)

    filename, lineno, source = \
        orca.get_raw_column(table_name, col_name).func_source_data()

    html = highlight(source, PythonLexer(), HtmlFormatter())

    return jsonify(
        type='function', filename=filename, lineno=lineno, text=source,
        html=html) 

def format_data(data):
    formatter = HtmlFormatter(cssclass="codehilite")

    if data is None:
        return data

    if isinstance(data, bool) or isinstance(data, int) or isinstance(data, float):
        return highlight(str(data), TextLexer(), formatter)
    elif isinstance(data, str):
        try:
            data = json.dumps(json.loads(data), indent=4, sort_keys=True)
            lexer = JsonLexer()
        except (ValueError, TypeError):
            lexer = TextLexer()
    elif isinstance(data, dict) or isinstance(data, list):
        data = json.dumps(data, indent=4, sort_keys=True)
        lexer = JsonLexer()
    else:
        lexer = TextLexer()

    lexer.stripall = True
    return highlight(data, lexer, formatter) 

def pygments2xpre(s, language="python"):
    "Return markup suitable for XPreformatted"
    try:
        from pygments import highlight
        from pygments.formatters import HtmlFormatter
    except ImportError:
        return s

    from pygments.lexers import get_lexer_by_name

    l = get_lexer_by_name(language)
    
    h = HtmlFormatter()
    from StringIO import StringIO
    out = StringIO()
    highlight(s,l,h,out)
    styles = [(cls, style.split(';')[0].split(':')[1].strip())
                for cls, (style, ttype, level) in h.class2style.iteritems()
                if cls and style and style.startswith('color:')]
    return _2xpre(out.getvalue(),styles) 

def injectable_definition(inj_name):
    """
    Get the source of an injectable function.

    If an injectable is a registered Python variable and not a function
    then all that is returned is {'type': 'variable'}.

    If the column is a registered function then the JSON returned has keys
    "type", "filename", "lineno", "text", and "html". "text" is the raw
    text of the function, "html" has been marked up by Pygments.

    """
    inj_type = orca.injectable_type(inj_name)

    if inj_type == 'variable':
        return jsonify(type='variable')
    else:
        filename, lineno, source = \
            orca.get_injectable_func_source_data(inj_name)
        html = highlight(source, PythonLexer(), HtmlFormatter())
        return jsonify(
            type='function', filename=filename, lineno=lineno, text=source,
            html=html) 

def table_definition(table_name):
    """
    Get the source of a table function.

    If a table is registered DataFrame and not a function then all that is
    returned is {'type': 'dataframe'}.

    If the table is a registered function then the JSON returned has keys
    "type", "filename", "lineno", "text", and "html". "text" is the raw
    text of the function, "html" has been marked up by Pygments.

    """
    if orca.table_type(table_name) == 'dataframe':
        return jsonify(type='dataframe')

    filename, lineno, source = \
        orca.get_raw_table(table_name).func_source_data()

    html = highlight(source, PythonLexer(), HtmlFormatter())

    return jsonify(
        type='function', filename=filename, lineno=lineno, text=source,
        html=html) 

def block_code(uuid, text, lang, inlinestyles=False, linenos=False):
    """Renders a code block"""
    if is_plant_uml(text, lang):
        fName = Settings().plantUMLCache.getResource(text, uuid)
        if fName is None:
            return '<br/><img src="cdm-image:na50.png"><br/>\n'
        return '<br/><img src="plantuml:' + fName + '"><br/>\n'

    lexer = get_lexer(text, lang)
    if lexer:
        try:
            formatter = HtmlFormatter(noclasses=inlinestyles, linenos=linenos)
            code = highlight(text, lexer, formatter)
            return ''.join([PRE_WRAP_START, '<pre>',
                            code.replace('125%', '100%'), '</pre>',
                            PRE_WRAP_END, '\n'])
        except:
            pass

    return ''.join([PRE_WRAP_START, '<pre>', mistune.escape(text),
                    '</pre>', PRE_WRAP_END, '\n']) 

def test_normal():
    # test that cmdline gives the same output as library api
    from pygments.lexers import PythonLexer
    from pygments.formatters import HtmlFormatter
    filename = TESTFILE
    with open(filename, 'rb') as fp:
        code = fp.read()

    output = highlight(code, PythonLexer(), HtmlFormatter())

    o = check_success('-lpython', '-fhtml', filename)
    assert o == output 

def test_lineanchors():
    optdict = dict(lineanchors="foo")
    outfile = StringIO()
    fmt = HtmlFormatter(**optdict)
    fmt.format(tokensource, outfile)
    html = outfile.getvalue()
    assert re.search("<pre><span></span><a name=\"foo-1\">", html) 

def test_get_style_defs_contains_default_line_numbers_styles():
    style_defs = HtmlFormatter().get_style_defs().splitlines()

    assert style_defs[1] == (
        'td.linenos pre '
        '{ color: #000000; background-color: #f0f0f0; padding: 0 5px 0 5px; }'
    )
    assert style_defs[2] == (
        'span.linenos '
        '{ color: #000000; background-color: #f0f0f0; padding: 0 5px 0 5px; }'
    ) 

def html_sourcecode(sourcecode):
    from pygments import highlight
    from pygments.lexers import SLexer
    from pygments.formatters import HtmlFormatter
    formatter = HtmlFormatter()
    htmlcode = highlight(sourcecode, SLexer(), formatter)
    d = {'sourcecode': htmlcode,
         'syntax_highlighting': formatter.get_style_defs()}
    html = template_sourcecode.render(d)
    return html 

def test_bare_class_handler():
    from pygments.formatters import HtmlFormatter
    from pygments.lexers import PythonLexer
    try:
        lex('test\n', PythonLexer)
    except TypeError as e:
        assert 'lex() argument must be a lexer instance' in str(e)
    else:
        assert False, 'nothing raised'
    try:
        format([], HtmlFormatter)
    except TypeError as e:
        assert 'format() argument must be a formatter instance' in str(e)
    else:
        assert False, 'nothing raised' 

def test_get_token_style_defs_uses_css_prefix(
    formatter_kwargs, style_defs_args, assert_starts_with, assert_contains
):
    formatter = HtmlFormatter(**formatter_kwargs)

    for line in formatter.get_token_style_defs(*style_defs_args):
        assert line.startswith(assert_starts_with)
        for s in assert_contains:
            assert s in line 

def test_all_options():
    def check(optdict):
        outfile = StringIO()
        fmt = HtmlFormatter(**optdict)
        fmt.format(tokensource, outfile)

    for optdict in [
        dict(nowrap=True),
        dict(linenos=True, full=True),
        dict(linenos=True, linespans='L'),
        dict(hl_lines=[1, 5, 10, 'xxx']),
        dict(hl_lines=[1, 5, 10], noclasses=True),
    ]:
        check(optdict)

    for linenos in [False, 'table', 'inline']:
        for noclasses in [False, True]:
            for linenospecial in [0, 5]:
                for anchorlinenos in [False, True]:
                    optdict = dict(
                        linenos=linenos,
                        noclasses=noclasses,
                        linenospecial=linenospecial,
                        anchorlinenos=anchorlinenos,
                    )
                    check(optdict) 

def test_get_background_style_defs_uses_multiple_css_prefixes():
    formatter = HtmlFormatter()

    lines = formatter.get_background_style_defs([".foo", ".bar"])
    assert lines[0].startswith(".foo .hll, .bar .hll {")
    assert lines[1].startswith(".foo , .bar {")