From b83942c755a78f6d917743b73ed87a8fd9f367de Mon Sep 17 00:00:00 2001 From: Raymond Hettinger Date: Fri, 9 Nov 2018 01:19:33 -0800 Subject: Cleanup and improve the regex tokenizer example. (GH-10426) 1) Convert weird field name "typ" to the more standard "type". 2) For the NUMBER type, convert the value to an int() or float(). 3) Simplify ``group(kind)`` to the shorter and faster ``group()`` call. 4) Simplify logic go a single if-elif chain to make this easier to extend. 5) Reorder the tests to match the order the tokens are specified. This isn't necessary for correctness but does make the example easier to follow. 6) Move the "column" calculation before the if-elif chain so that users have the option of using this value in error messages. --- Doc/library/re.rst | 74 ++++++++++++++++++++++++++++-------------------------- 1 file changed, 38 insertions(+), 36 deletions(-) diff --git a/Doc/library/re.rst b/Doc/library/re.rst index 31fb628..2f82955 100644 --- a/Doc/library/re.rst +++ b/Doc/library/re.rst @@ -1609,38 +1609,40 @@ successive matches:: import collections import re - Token = collections.namedtuple('Token', ['typ', 'value', 'line', 'column']) + Token = collections.namedtuple('Token', ['type', 'value', 'line', 'column']) def tokenize(code): keywords = {'IF', 'THEN', 'ENDIF', 'FOR', 'NEXT', 'GOSUB', 'RETURN'} token_specification = [ - ('NUMBER', r'\d+(\.\d*)?'), # Integer or decimal number - ('ASSIGN', r':='), # Assignment operator - ('END', r';'), # Statement terminator - ('ID', r'[A-Za-z]+'), # Identifiers - ('OP', r'[+\-*/]'), # Arithmetic operators - ('NEWLINE', r'\n'), # Line endings - ('SKIP', r'[ \t]+'), # Skip over spaces and tabs - ('MISMATCH',r'.'), # Any other character + ('NUMBER', r'\d+(\.\d*)?'), # Integer or decimal number + ('ASSIGN', r':='), # Assignment operator + ('END', r';'), # Statement terminator + ('ID', r'[A-Za-z]+'), # Identifiers + ('OP', r'[+\-*/]'), # Arithmetic operators + ('NEWLINE', r'\n'), # Line endings + ('SKIP', r'[ \t]+'), # Skip over spaces and tabs + ('MISMATCH', r'.'), # Any other character ] tok_regex = '|'.join('(?P<%s>%s)' % pair for pair in token_specification) line_num = 1 line_start = 0 for mo in re.finditer(tok_regex, code): kind = mo.lastgroup - value = mo.group(kind) - if kind == 'NEWLINE': + value = mo.group() + column = mo.start() - line_start + if kind == 'NUMBER': + value = float(value) if '.' in value else int(value) + elif kind == 'ID' and value in keywords: + kind = value + elif kind == 'NEWLINE': line_start = mo.end() line_num += 1 + continue elif kind == 'SKIP': - pass + continue elif kind == 'MISMATCH': raise RuntimeError(f'{value!r} unexpected on line {line_num}') - else: - if kind == 'ID' and value in keywords: - kind = value - column = mo.start() - line_start - yield Token(kind, value, line_num, column) + yield Token(kind, value, line_num, column) statements = ''' IF quantity THEN @@ -1654,25 +1656,25 @@ successive matches:: The tokenizer produces the following output:: - Token(typ='IF', value='IF', line=2, column=4) - Token(typ='ID', value='quantity', line=2, column=7) - Token(typ='THEN', value='THEN', line=2, column=16) - Token(typ='ID', value='total', line=3, column=8) - Token(typ='ASSIGN', value=':=', line=3, column=14) - Token(typ='ID', value='total', line=3, column=17) - Token(typ='OP', value='+', line=3, column=23) - Token(typ='ID', value='price', line=3, column=25) - Token(typ='OP', value='*', line=3, column=31) - Token(typ='ID', value='quantity', line=3, column=33) - Token(typ='END', value=';', line=3, column=41) - Token(typ='ID', value='tax', line=4, column=8) - Token(typ='ASSIGN', value=':=', line=4, column=12) - Token(typ='ID', value='price', line=4, column=15) - Token(typ='OP', value='*', line=4, column=21) - Token(typ='NUMBER', value='0.05', line=4, column=23) - Token(typ='END', value=';', line=4, column=27) - Token(typ='ENDIF', value='ENDIF', line=5, column=4) - Token(typ='END', value=';', line=5, column=9) + Token(type='IF', value='IF', line=2, column=4) + Token(type='ID', value='quantity', line=2, column=7) + Token(type='THEN', value='THEN', line=2, column=16) + Token(type='ID', value='total', line=3, column=8) + Token(type='ASSIGN', value=':=', line=3, column=14) + Token(type='ID', value='total', line=3, column=17) + Token(type='OP', value='+', line=3, column=23) + Token(type='ID', value='price', line=3, column=25) + Token(type='OP', value='*', line=3, column=31) + Token(type='ID', value='quantity', line=3, column=33) + Token(type='END', value=';', line=3, column=41) + Token(type='ID', value='tax', line=4, column=8) + Token(type='ASSIGN', value=':=', line=4, column=12) + Token(type='ID', value='price', line=4, column=15) + Token(type='OP', value='*', line=4, column=21) + Token(type='NUMBER', value=0.05, line=4, column=23) + Token(type='END', value=';', line=4, column=27) + Token(type='ENDIF', value='ENDIF', line=5, column=4) + Token(type='END', value=';', line=5, column=9) .. [Frie09] Friedl, Jeffrey. Mastering Regular Expressions. 3rd ed., O'Reilly -- cgit v0.12