From 2efbc08854fe5a468b6bbda10bf038d06a8aac00 Mon Sep 17 00:00:00 2001
From: Erez Shinan <erezshin+git@gmail.com>
Date: Thu, 16 Nov 2017 09:47:46 +0200
Subject: [PATCH] Support for multiple flags

---
 examples/python2.g   | 12 ++++++------
 examples/python3.g   | 16 ++++++++--------
 lark/common.py       | 10 ++++------
 lark/load_grammar.py | 25 ++++++++++++++++---------
 4 files changed, 34 insertions(+), 29 deletions(-)

diff --git a/examples/python2.g b/examples/python2.g
index a429512..aa5dd9e 100644
--- a/examples/python2.g
+++ b/examples/python2.g
@@ -149,16 +149,16 @@ COMMENT: /#[^\n]*/
 _NEWLINE: ( /\r?\n[\t ]*/ | COMMENT )+
 
 %ignore /[\t \f]+/  // WS
-%ignore /\\[\t \f]*\r?\n/   // LINE_CONT
+%ignore /\\[\t \f]*\r?\n/   // LINE_CONT 
 %ignore COMMENT
 
 
-STRING : /(?i)[ub]?r?("(?!"").*?(?<!\\\\)(\\\\\\\\)*?"|'(?!'').*?(?<!\\\\)(\\\\\\\\)*?')/
-LONG_STRING: /(?i)(?s)[ub]?r?(""".*?(?<!\\\\)(\\\\\\\\)*?"""|'''.*?(?<!\\\\)(\\\\\\\\)*?''')/
+STRING : /[ub]?r?("(?!"").*?(?<!\\\\)(\\\\\\\\)*?"|'(?!'').*?(?<!\\\\)(\\\\\\\\)*?')/i
+LONG_STRING.2: /[ub]?r?(""".*?(?<!\\\\)(\\\\\\\\)*?"""|'''.*?(?<!\\\\)(\\\\\\\\)*?''')/is
 
-DEC_NUMBER: /(?i)[1-9]\d*l?/
-HEX_NUMBER: /(?i)0x[\da-f]*l?/
-OCT_NUMBER: /(?i)0o?[0-7]*l?/
+DEC_NUMBER: /[1-9]\d*l?/i
+HEX_NUMBER: /0x[\da-f]*l?/i
+OCT_NUMBER: /0o?[0-7]*l?/i
 %import common.FLOAT -> FLOAT
 %import common.INT -> _INT
 %import common.CNAME -> NAME
diff --git a/examples/python3.g b/examples/python3.g
index c27b7ec..27b0ab4 100644
--- a/examples/python3.g
+++ b/examples/python3.g
@@ -177,14 +177,14 @@ _NEWLINE: ( /\r?\n[\t ]*/ | COMMENT )+
 
 // STRING : /[ub]?r?("(?!"").*?(?<!\\)(\\\\)*?"|'(?!'').*?(?<!\\)(\\\\)*?')/
 // LONG_STRING: /(?s)[ub]?r?(""".*?(?<!\\)(\\\\)*?"""|'''.*?(?<!\\)(\\\\)*?''')/
-STRING : /(?i)[ubf]?r?("(?!"").*?(?<!\\\\)(\\\\\\\\)*?"|'(?!'').*?(?<!\\\\)(\\\\\\\\)*?')/
-LONG_STRING: /(?i)(?s)[ubf]?r?(""".*?(?<!\\\\)(\\\\\\\\)*?"""|'''.*?(?<!\\\\)(\\\\\\\\)*?''')/
-
-DEC_NUMBER: /(?i)[1-9]\d*l?/
-HEX_NUMBER: /(?i)0x[\da-f]*l?/
-OCT_NUMBER: /(?i)0o?[0-7]*l?/
-FLOAT_NUMBER: /(?i)((\d+\.\d*|\.\d+)(e[-+]?\d+)?|\d+(e[-+]?\d+))/
-IMAG_NUMBER: /(?i)\d+j|${FLOAT_NUMBER}j/
+STRING : /[ubf]?r?("(?!"").*?(?<!\\\\)(\\\\\\\\)*?"|'(?!'').*?(?<!\\\\)(\\\\\\\\)*?')/i
+LONG_STRING: /[ubf]?r?(""".*?(?<!\\\\)(\\\\\\\\)*?"""|'''.*?(?<!\\\\)(\\\\\\\\)*?''')/is
+
+DEC_NUMBER: /[1-9]\d*l?/i
+HEX_NUMBER: /0x[\da-f]*l?/i
+OCT_NUMBER: /0o?[0-7]*l?/i
+FLOAT_NUMBER: /((\d+\.\d*|\.\d+)(e[-+]?\d+)?|\d+(e[-+]?\d+))/i
+IMAG_NUMBER: /\d+j|${FLOAT_NUMBER}j/i
 
 _DEDENT: "<DEDENT>"
 _INDENT: "<INDENT>"
diff --git a/lark/common.py b/lark/common.py
index 45aa0cd..50bea90 100644
--- a/lark/common.py
+++ b/lark/common.py
@@ -68,16 +68,14 @@ class Pattern(object):
     if Py36:
         # Python 3.6 changed syntax for flags in regular expression
         def _get_flags(self, value):
-            if self.flags:
-                assert len(self.flags) == 1
-                return ('(?%s:%s)' % (self.flags[0], value))
+            for f in self.flags or ():
+                value = ('(?%s:%s)' % (f, value))
             return value
 
     else:
         def _get_flags(self, value):
-            if self.flags:
-                assert len(self.flags) == 1
-                return ('(?%s)' % self.flags) + value
+            for f in self.flags or ():
+                value = ('(?%s)' % f) + value
             return value
 
 class PatternStr(Pattern):
diff --git a/lark/load_grammar.py b/lark/load_grammar.py
index 6f2e102..9bf6f95 100644
--- a/lark/load_grammar.py
+++ b/lark/load_grammar.py
@@ -72,7 +72,7 @@ TOKENS = {
     'RULE': '!?[_?]?[a-z][_a-z0-9]*',
     'TOKEN': '_?[A-Z][_A-Z0-9]*',
     'STRING': r'"(\\"|\\\\|[^"\n])*?"i?',
-    'REGEXP': r'/(?!/)(\\/|\\\\|[^/\n])*?/[%s]?' % _RE_FLAGS,
+    'REGEXP': r'/(?!/)(\\/|\\\\|[^/\n])*?/[%s]*' % _RE_FLAGS,
     '_NL': r'(\r?\n)+\s*',
     'WS': r'[ \t]+',
     'COMMENT': r'//[^\n]*',
@@ -287,21 +287,28 @@ class ExtractAnonTokens(InlineTransformer):
         return Token('TOKEN', token_name, -1)
 
 
+def _rfind(s, choices):
+    return max(s.rfind(c) for c in choices)
+
 def _literal_to_pattern(literal):
     v = literal.value
-    if v[-1] in _RE_FLAGS:
-        flags = v[-1]
-        v = v[:-1]
-    else:
-        flags = None
+    flag_start = _rfind(v, '/"')+1
+    assert flag_start > 0
+    flags = v[flag_start:]
+    assert all(f in _RE_FLAGS for f in flags), flags
 
+    v = v[:flag_start]
     assert v[0] == v[-1] and v[0] in '"/'
     x = v[1:-1]
-    x = re.sub(r'(\\[wd/ ]|\\\[|\\\])', r'\\\1', x)
+    x = re.sub(r'(\\[wd/ .]|\\\[|\\\])', r'\\\1', x)
     x = x.replace("'", r"\'")
-    s = literal_eval("u'''%s'''" % x)
+    to_eval = "u'''%s'''" % x
+    try:
+        s = literal_eval(to_eval)
+    except SyntaxError as e:
+        raise ValueError(v, e)
     return { 'STRING': PatternStr,
-             'REGEXP': PatternRE }[literal.type](s, flags)
+             'REGEXP': PatternRE }[literal.type](s, flags or None)
 
 
 class PrepareLiterals(InlineTransformer):