From 832448bbea325a63174af3770091a98ab9f63813 Mon Sep 17 00:00:00 2001
From: moculus <none@none>
Date: Fri, 26 Sep 2008 14:22:19 +0000
Subject: [PATCH] more c mode improvements

--HG--
branch : pmacs2
---
 method/introspect.py | 16 ++++++++++++++++
 mode/c.py            | 24 ++++++++++++++++++------
 2 files changed, 34 insertions(+), 6 deletions(-)

diff --git a/method/introspect.py b/method/introspect.py
index 73fe656..94f5bb1 100644
--- a/method/introspect.py
+++ b/method/introspect.py
@@ -73,6 +73,22 @@ class DumpTokens(Method):
         output = "\n".join(lines)
         w.application.data_buffer("token-dump", output, switch_to=True)
 
+class DumpAggregateTokenData(Method):
+    '''Dump all lexical tokens into an aggregated format'''
+    def _execute(self, w, **vargs):
+        name = w.mode.name()
+        lines = []
+        if modename in w.buffer.highlights:
+            tokens = w.buffer.highlights[name].tokens
+            for group in tokens:
+                for token in group:
+                    s1 = token.name
+                    s2 = token.fqname()
+                    n = len(token.string)
+                    lines.append('%-s %-s %3d %-s' % (s1, s2, n, token.string))
+        output = "\n".join(lines)
+        w.application.data_buffer("token-dump", output, switch_to=True)
+
 class GetToken(Method):
     '''View type and data of the "current" token'''
     def _execute(self, w, **vargs):
diff --git a/mode/c.py b/mode/c.py
index 10484ef..b749077 100644
--- a/mode/c.py
+++ b/mode/c.py
@@ -8,10 +8,14 @@ from mode.python import StringGrammar
 # see http://gcc.gnu.org/onlinedocs/gcc-2.95.3/cpp_3.html#SEC44
 class MacroGrammar(Grammar):
     rules = [
+        RegionRule(r'comment', r'/\*', Grammar, r'\*/'),
+        PatternRule(r'comment', r'//.*$'),
+
         PatternRule('name', r'(?:(?<=#define )) *[a-zA-Z_][a-zA-Z0-9_]*'),
         PatternRule(r"unop", r"\+=|-=|\*=|/=|//=|%=|&=|\^=|>>=|<<=|\*\*=|\|="),
         PatternRule(r'binop', r"\+|<>|<<|<=|<|-|>>|>=|>|\*\*|&|\*|\||/|\^|==|//|~|!=|%"),
         PatternRule(r"delimiter", r"->|\.|\(|\)|\[|\]|{|}|@|,|:|`|;|=|\?"),
+        PatternRule(r"identifier", r"[a-zA-Z_][a-zA-Z0-9_]*"),
         PatternRule(r"integer", r"-?(?:0(?![x0-9])|[1-9][0-9]*|0[0-7]+|0[xX][0-9a-fA-F]+)[lL]?"),
         PatternRule(r"float", r"-?(?:[0-9]+\.[0-9]*|\.[0-9]+|(?:[0-9]|[0-9]+\.[0-9]*|\.[0-9]+)[eE][\+-]?[0-9]+)"),
         RegionRule(r'string', '"', StringGrammar, '"'),
@@ -37,7 +41,7 @@ class CGrammar(Grammar):
         PatternRule(r'label', r'[a-zA-Z_][a-zA-Z0-9_]*(?=:)'),
         PatternRule(r'identifier', r"[a-zA-Z_][a-zA-Z0-9_]*(?! *[\(:])"),
 
-        RegionRule(r'macro', r'#(?:assert|cpu|define|elif|else|endif|error|ident|ifdef|ifndef|if|import|include_next|line|machine|pragma|pragma_once|system|unassert|undef|warning)(?!=[a-zA-Z0-9_])', MacroGrammar, r'\n$'),
+        RegionRule(r'macro', r'# *(?:assert|cpu|define|elif|else|endif|error|ident|ifdef|ifndef|if|import|include_next|line|machine|pragma|pragma_once|system|unassert|undef|warning)(?!=[a-zA-Z0-9_])', MacroGrammar, r'\n$'),
 
         RegionRule(r'comment', r'/\*', Grammar, r'\*/'),
         PatternRule(r'comment', r'//.*$'),
@@ -52,8 +56,14 @@ class CGrammar(Grammar):
         RegionRule(r'macrocomment', r'#if +(?:0|NULL|FALSE)', Grammar, r'#endif'),
 
         PatternRule(r'char', r"'.'|'\\.'|'\\[0-7]{3}'"),
-        PatternRule(r'include', r'#include(?!=[a-zA-Z0-9_])'),
-        PatternRule(r'header', r'<[-A-Za-z/0-9_\.]+>|"[-A-Za-z/0-9_\.]+"'),
+
+        PatternGroupRule(r'includegrp', r'macro.start', r'# *include', r'spaces',
+                         r' +', r'header', r'< *[-A-Za-z/0-9_.]+ *>|" *[-A-Za-z/0-9_.]+ *"'),
+        #PatternGroupRule(r'ifndefgrp', r'macro.start', r'# *ifndef', r'spaces',
+        #                 r' +', r'header', r'< *[-A-Za-z/0-9_.]+ *>|" *[-A-Za-z/0-9_.]+ *"'),
+
+        #PatternRule(r'include', r'#include(?!=[a-zA-Z0-9_])'),
+        #PatternRule(r'header', r'<[-A-Za-z/0-9_\.]+>|"[-A-Za-z/0-9_\.]+"'),
         #PatternRule(r'enumname', r'(?<=enum ) *[a-zA-Z_][a-zA-Z0-9_]*'),
         #PatternRule(r'structname', r'(?<=struct ) *[a-zA-Z_][a-zA-Z0-9_]*'),
 
@@ -227,6 +237,8 @@ class C(mode.Fundamental):
         'macro.null':           ('magenta', 'default', 'bold'),
         'macro.continued':      ('red', 'default', 'bold'),
         'macro.delimiter':      ('default', 'default', 'bold'),
+        'macro.identifier':     ('yellow', 'default', 'bold'),
+        'macro.bareword':       ('yellow', 'default', 'bold'),
         'macro.integer':        ('green', 'default', 'bold'),
         'macro.float':          ('green', 'default', 'bold'),
         'macro.char':           ('green', 'default', 'bold'),
@@ -238,9 +250,9 @@ class C(mode.Fundamental):
         'macro.end':            ('magenta', 'default', 'bold'),
         'include':              ('blue', 'default', 'bold'),
         'header':               ('green', 'default', 'bold'),
-        #'structname':           ('yellow', 'default', 'bold'),
-        #'enumname':             ('yellow', 'default', 'bold'),
-        #'c_type':               ('green', 'default', 'bold'),
+        #'structname':          ('yellow', 'default', 'bold'),
+        #'enumname':            ('yellow', 'default', 'bold'),
+        #'c_type':              ('green', 'default', 'bold'),
     }
     config = {
         'c.syntax-cmd':     "gcc -x c -fsyntax-only %(path)s",