Mercurial > public > mercurial-scm > hg-stable

comparison mercurial/utils/stringutil.py @ 47200:b0e92313107e

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
parselist: move the function from config to stringutil We move the function in a lower level module to avoid cycle. It moves next to `parsebool` who had to migrate for the same reasons. Differential Revision: https://phab.mercurial-scm.org/D10449
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Fri, 16 Apr 2021 01:18:28 +0200
parents d4ba4d51f85f
children dcdecec401ca
comparison
equal deleted inserted replaced
47199:353718f741a8 47200:b0e92313107e
866 If s is not a valid boolean, returns None. 866 If s is not a valid boolean, returns None.
867 """ 867 """
868 return _booleans.get(s.lower(), None) 868 return _booleans.get(s.lower(), None)
869 869
870 870
871 def parselist(value):
872 """parse a configuration value as a list of comma/space separated strings
873
874 >>> parselist(b'this,is "a small" ,test')
875 ['this', 'is', 'a small', 'test']
876 """
877
878 def _parse_plain(parts, s, offset):
879 whitespace = False
880 while offset < len(s) and (
881 s[offset : offset + 1].isspace() or s[offset : offset + 1] == b','
882 ):
883 whitespace = True
884 offset += 1
885 if offset >= len(s):
886 return None, parts, offset
887 if whitespace:
888 parts.append(b'')
889 if s[offset : offset + 1] == b'"' and not parts[-1]:
890 return _parse_quote, parts, offset + 1
891 elif s[offset : offset + 1] == b'"' and parts[-1][-1:] == b'\\':
892 parts[-1] = parts[-1][:-1] + s[offset : offset + 1]
893 return _parse_plain, parts, offset + 1
894 parts[-1] += s[offset : offset + 1]
895 return _parse_plain, parts, offset + 1
896
897 def _parse_quote(parts, s, offset):
898 if offset < len(s) and s[offset : offset + 1] == b'"': # ""
899 parts.append(b'')
900 offset += 1
901 while offset < len(s) and (
902 s[offset : offset + 1].isspace()
903 or s[offset : offset + 1] == b','
904 ):
905 offset += 1
906 return _parse_plain, parts, offset
907
908 while offset < len(s) and s[offset : offset + 1] != b'"':
909 if (
910 s[offset : offset + 1] == b'\\'
911 and offset + 1 < len(s)
912 and s[offset + 1 : offset + 2] == b'"'
913 ):
914 offset += 1
915 parts[-1] += b'"'
916 else:
917 parts[-1] += s[offset : offset + 1]
918 offset += 1
919
920 if offset >= len(s):
921 real_parts = _configlist(parts[-1])
922 if not real_parts:
923 parts[-1] = b'"'
924 else:
925 real_parts[0] = b'"' + real_parts[0]
926 parts = parts[:-1]
927 parts.extend(real_parts)
928 return None, parts, offset
929
930 offset += 1
931 while offset < len(s) and s[offset : offset + 1] in [b' ', b',']:
932 offset += 1
933
934 if offset < len(s):
935 if offset + 1 == len(s) and s[offset : offset + 1] == b'"':
936 parts[-1] += b'"'
937 offset += 1
938 else:
939 parts.append(b'')
940 else:
941 return None, parts, offset
942
943 return _parse_plain, parts, offset
944
945 def _configlist(s):
946 s = s.rstrip(b' ,')
947 if not s:
948 return []
949 parser, parts, offset = _parse_plain, [b''], 0
950 while parser:
951 parser, parts, offset = parser(parts, s, offset)
952 return parts
953
954 if value is not None and isinstance(value, bytes):
955 result = _configlist(value.lstrip(b' ,\n'))
956 else:
957 result = value
958 return result or []
959
960
871 def evalpythonliteral(s): 961 def evalpythonliteral(s):
872 """Evaluate a string containing a Python literal expression""" 962 """Evaluate a string containing a Python literal expression"""
873 # We could backport our tokenizer hack to rewrite '' to u'' if we want 963 # We could backport our tokenizer hack to rewrite '' to u'' if we want
874 if pycompat.ispy3: 964 if pycompat.ispy3:
875 return ast.literal_eval(s.decode('latin1')) 965 return ast.literal_eval(s.decode('latin1'))