He said, "'Quoted' words in a larger quote."
+double_quote_sets_re = re.compile(r""""'(?=\w)""") +single_quote_sets_re = re.compile(r"""'"(?=\w)""") + +# Special case for decade abbreviations (the '80s): +decade_abbr_re = re.compile(r"""\b'(?=\d{2}s)""") + +# Get most opening double quotes: +opening_double_quotes_regex = re.compile(r""" + ( + \s | # a whitespace char, or + | # a non-breaking space entity, or + -- | # dashes, or + &[mn]dash; | # named dash entities + %s | # or decimal entities + &\#x201[34]; # or hex + ) + " # the quote + (?=\w) # followed by a word character + """ % (dec_dashes,), re.VERBOSE) + +# Double closing quotes: +closing_double_quotes_regex = re.compile(r""" + #(%s)? # character that indicates the quote should be closing + " + (?=\s) + """ % (close_class,), re.VERBOSE) + +closing_double_quotes_regex_2 = re.compile(r""" + (%s) # character that indicates the quote should be closing + " + """ % (close_class,), re.VERBOSE) + +# Get most opening single quotes: +opening_single_quotes_regex = re.compile(r""" + ( + \s | # a whitespace char, or + | # a non-breaking space entity, or + -- | # dashes, or + &[mn]dash; | # named dash entities + %s | # or decimal entities + &\#x201[34]; # or hex + ) + ' # the quote + (?=\w) # followed by a word character + """ % (dec_dashes,), re.VERBOSE) + +closing_single_quotes_regex = re.compile(r""" + (%s) + ' + (?!\s | s\b | \d) + """ % (close_class,), re.VERBOSE) + +closing_single_quotes_regex_2 = re.compile(r""" + (%s) + ' + (\s | s\b) + """ % (close_class,), re.VERBOSE) + +def educateQuotes(s): + """ + Parameter: String. + + Returns: The string, with "educated" curly quote HTML entities. + + Example input: "Isn't this fun?" + Example output: “Isn’t this fun?” + """ + + # Special case if the very first character is a quote + # followed by punctuation at a non-word-break. Close the quotes by brute force: + s = single_quote_start_re.sub("’", s) + s = double_quote_start_re.sub("”", s) + + # Special case for double sets of quotes, e.g.: + #He said, "'Quoted' words in a larger quote."
+ s = double_quote_sets_re.sub("“‘", s) + s = single_quote_sets_re.sub("‘“", s) + + # Special case for decade abbreviations (the '80s): + s = decade_abbr_re.sub("’", s) + + s = opening_single_quotes_regex.sub(r"\1‘", s) + s = closing_single_quotes_regex.sub(r"\1’", s) + s = closing_single_quotes_regex_2.sub(r"\1’\2", s) + + # Any remaining single quotes should be opening ones: + s = s.replace("'", "‘") + + s = opening_double_quotes_regex.sub(r"\1“", s) + s = closing_double_quotes_regex.sub(r"”", s) + s = closing_double_quotes_regex_2.sub(r"\1”", s) + + # Any remaining quotes should be opening ones. + return s.replace('"', "“") + + +def educateQuotesLatex(s, dquotes=("``", "''")): + """ + Parameter: String. + + Returns: The string, with double quotes corrected to LaTeX quotes. + + Example input: "Isn't this fun?" + Example output: ``Isn't this fun?''; + """ + + # Special case if the very first character is a quote + # followed by punctuation at a non-word-break. Close the quotes by brute force: + s = single_quote_start_re.sub("\x04", s) + s = double_quote_start_re.sub("\x02", s) + + # Special case for double sets of quotes, e.g.: + #He said, "'Quoted' words in a larger quote."
+ s = double_quote_sets_re.sub("\x01\x03", s) + s = single_quote_sets_re.sub("\x03\x01", s) + + # Special case for decade abbreviations (the '80s): + s = decade_abbr_re.sub("\x04", s) + + s = opening_single_quotes_regex.sub("\\1\x03", s) + s = closing_single_quotes_regex.sub("\\1\x04", s) + s = closing_single_quotes_regex_2.sub("\\1\x04\\2", s) + + # Any remaining single quotes should be opening ones: + s = s.replace("'", "\x03") + + s = opening_double_quotes_regex.sub("\\1\x01", s) + s = closing_double_quotes_regex.sub("\x02", s) + s = closing_double_quotes_regex_2.sub("\\1\x02", s) + + # Any remaining quotes should be opening ones. + s = s.replace('"', "\x01") + + # Finally, replace all helpers with quotes. + return s.replace("\x01", dquotes[0]).replace("\x02", dquotes[1]).\ + replace("\x03", "`").replace("\x04", "'") + + +def educateBackticks(s): + """ + Parameter: String. + Returns: The string, with ``backticks'' -style double quotes + translated into HTML curly quote entities. + Example input: ``Isn't this fun?'' + Example output: “Isn't this fun?” + """ + return s.replace("``", "“").replace("''", "”") + + +def educateSingleBackticks(s): + """ + Parameter: String. + Returns: The string, with `backticks' -style single quotes + translated into HTML curly quote entities. + + Example input: `Isn't this fun?' + Example output: ‘Isn’t this fun?’ + """ + return s.replace('`', "‘").replace("'", "’") + + +def educateDashesOldSchool(s): + """ + Parameter: String. + + Returns: The string, with each instance of "--" translated to + an en-dash HTML entity, and each "---" translated to + an em-dash HTML entity. + """ + return s.replace('---', "—").replace('--', "–") + + +def educateDashesOldSchoolInverted(s): + """ + Parameter: String. + + Returns: The string, with each instance of "--" translated to + an em-dash HTML entity, and each "---" translated to + an en-dash HTML entity. Two reasons why: First, unlike the + en- and em-dash syntax supported by + EducateDashesOldSchool(), it's compatible with existing + entries written before SmartyPants 1.1, back when "--" was + only used for em-dashes. Second, em-dashes are more + common than en-dashes, and so it sort of makes sense that + the shortcut should be shorter to type. (Thanks to Aaron + Swartz for the idea.) + """ + return s.replace('---', "–").replace('--', "—") + + + +def educateEllipses(s): + """ + Parameter: String. + Returns: The string, with each instance of "..." translated to + an ellipsis HTML entity. + + Example input: Huh...? + Example output: Huh…? + """ + return s.replace('...', "…").replace('. . .', "…") + + +__author__ = "Chad Miller