diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-07 19:33:14 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-07 19:33:14 +0000 |
commit | 36d22d82aa202bb199967e9512281e9a53db42c9 (patch) | |
tree | 105e8c98ddea1c1e4784a60a5a6410fa416be2de /third_party/python/ply/example/ansic/clex.py | |
parent | Initial commit. (diff) | |
download | firefox-esr-36d22d82aa202bb199967e9512281e9a53db42c9.tar.xz firefox-esr-36d22d82aa202bb199967e9512281e9a53db42c9.zip |
Adding upstream version 115.7.0esr.upstream/115.7.0esr
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'third_party/python/ply/example/ansic/clex.py')
-rw-r--r-- | third_party/python/ply/example/ansic/clex.py | 168 |
1 files changed, 168 insertions, 0 deletions
diff --git a/third_party/python/ply/example/ansic/clex.py b/third_party/python/ply/example/ansic/clex.py new file mode 100644 index 0000000000..4bde1d730b --- /dev/null +++ b/third_party/python/ply/example/ansic/clex.py @@ -0,0 +1,168 @@ +# ---------------------------------------------------------------------- +# clex.py +# +# A lexer for ANSI C. +# ---------------------------------------------------------------------- + +import sys +sys.path.insert(0, "../..") + +import ply.lex as lex + +# Reserved words +reserved = ( + 'AUTO', 'BREAK', 'CASE', 'CHAR', 'CONST', 'CONTINUE', 'DEFAULT', 'DO', 'DOUBLE', + 'ELSE', 'ENUM', 'EXTERN', 'FLOAT', 'FOR', 'GOTO', 'IF', 'INT', 'LONG', 'REGISTER', + 'RETURN', 'SHORT', 'SIGNED', 'SIZEOF', 'STATIC', 'STRUCT', 'SWITCH', 'TYPEDEF', + 'UNION', 'UNSIGNED', 'VOID', 'VOLATILE', 'WHILE', +) + +tokens = reserved + ( + # Literals (identifier, integer constant, float constant, string constant, + # char const) + 'ID', 'TYPEID', 'ICONST', 'FCONST', 'SCONST', 'CCONST', + + # Operators (+,-,*,/,%,|,&,~,^,<<,>>, ||, &&, !, <, <=, >, >=, ==, !=) + 'PLUS', 'MINUS', 'TIMES', 'DIVIDE', 'MOD', + 'OR', 'AND', 'NOT', 'XOR', 'LSHIFT', 'RSHIFT', + 'LOR', 'LAND', 'LNOT', + 'LT', 'LE', 'GT', 'GE', 'EQ', 'NE', + + # Assignment (=, *=, /=, %=, +=, -=, <<=, >>=, &=, ^=, |=) + 'EQUALS', 'TIMESEQUAL', 'DIVEQUAL', 'MODEQUAL', 'PLUSEQUAL', 'MINUSEQUAL', + 'LSHIFTEQUAL', 'RSHIFTEQUAL', 'ANDEQUAL', 'XOREQUAL', 'OREQUAL', + + # Increment/decrement (++,--) + 'PLUSPLUS', 'MINUSMINUS', + + # Structure dereference (->) + 'ARROW', + + # Conditional operator (?) + 'CONDOP', + + # Delimeters ( ) [ ] { } , . ; : + 'LPAREN', 'RPAREN', + 'LBRACKET', 'RBRACKET', + 'LBRACE', 'RBRACE', + 'COMMA', 'PERIOD', 'SEMI', 'COLON', + + # Ellipsis (...) + 'ELLIPSIS', +) + +# Completely ignored characters +t_ignore = ' \t\x0c' + +# Newlines + + +def t_NEWLINE(t): + r'\n+' + t.lexer.lineno += t.value.count("\n") + +# Operators +t_PLUS = r'\+' +t_MINUS = r'-' +t_TIMES = r'\*' +t_DIVIDE = r'/' +t_MOD = r'%' +t_OR = r'\|' +t_AND = r'&' +t_NOT = r'~' +t_XOR = r'\^' +t_LSHIFT = r'<<' +t_RSHIFT = r'>>' +t_LOR = r'\|\|' +t_LAND = r'&&' +t_LNOT = r'!' +t_LT = r'<' +t_GT = r'>' +t_LE = r'<=' +t_GE = r'>=' +t_EQ = r'==' +t_NE = r'!=' + +# Assignment operators + +t_EQUALS = r'=' +t_TIMESEQUAL = r'\*=' +t_DIVEQUAL = r'/=' +t_MODEQUAL = r'%=' +t_PLUSEQUAL = r'\+=' +t_MINUSEQUAL = r'-=' +t_LSHIFTEQUAL = r'<<=' +t_RSHIFTEQUAL = r'>>=' +t_ANDEQUAL = r'&=' +t_OREQUAL = r'\|=' +t_XOREQUAL = r'\^=' + +# Increment/decrement +t_PLUSPLUS = r'\+\+' +t_MINUSMINUS = r'--' + +# -> +t_ARROW = r'->' + +# ? +t_CONDOP = r'\?' + +# Delimeters +t_LPAREN = r'\(' +t_RPAREN = r'\)' +t_LBRACKET = r'\[' +t_RBRACKET = r'\]' +t_LBRACE = r'\{' +t_RBRACE = r'\}' +t_COMMA = r',' +t_PERIOD = r'\.' +t_SEMI = r';' +t_COLON = r':' +t_ELLIPSIS = r'\.\.\.' + +# Identifiers and reserved words + +reserved_map = {} +for r in reserved: + reserved_map[r.lower()] = r + + +def t_ID(t): + r'[A-Za-z_][\w_]*' + t.type = reserved_map.get(t.value, "ID") + return t + +# Integer literal +t_ICONST = r'\d+([uU]|[lL]|[uU][lL]|[lL][uU])?' + +# Floating literal +t_FCONST = r'((\d+)(\.\d+)(e(\+|-)?(\d+))? | (\d+)e(\+|-)?(\d+))([lL]|[fF])?' + +# String literal +t_SCONST = r'\"([^\\\n]|(\\.))*?\"' + +# Character constant 'c' or L'c' +t_CCONST = r'(L)?\'([^\\\n]|(\\.))*?\'' + +# Comments + + +def t_comment(t): + r'/\*(.|\n)*?\*/' + t.lexer.lineno += t.value.count('\n') + +# Preprocessor directive (ignored) + + +def t_preprocessor(t): + r'\#(.)*?\n' + t.lexer.lineno += 1 + + +def t_error(t): + print("Illegal character %s" % repr(t.value[0])) + t.lexer.skip(1) + +lexer = lex.lex() +if __name__ == "__main__": + lex.runmain(lexer) |