Add utils/SummarizeErrors.

- Little script for scanning a compile log and summarizing warnings,
   errors, assertions, and crashes.
 - Is very slow, and stack trace regexs probably only work on Darwin.

llvm-svn: 62013

clang/utils/SummarizeErrors

@@ -0,0 +1,99 @@
+#!/usr/bin/python
+
+import os, sys, re
+
+class multidict:
+    def __init__(self, elts=()):
+        self.data = {}
+        for key,value in elts:
+            self[key] = value
+    
+    def __getitem__(self, item):
+        return self.data[item]
+    def __setitem__(self, key, value):
+        if key in self.data:
+            self.data[key].append(value)
+        else:
+            self.data[key] = [value]
+    def items(self):
+        return self.data.items()
+    def values(self):
+        return self.data.values()
+    def keys(self):
+        return self.data.keys()
+    def __len__(self):
+        return len(self.data)
+
+kGCCErrorRE = re.compile('(.*):([0-9]+): error: (.*)')
+kGCCWarningRE = re.compile('(.*):([0-9]+): warning: (.*)')
+kClangErrorRE = re.compile('(.*):([0-9]+):([0-9]+): error: (.*)')
+kClangWarningRE = re.compile('(.*):([0-9]+):([0-9]+): warning: (.*)')
+kAssertionRE = re.compile('Assertion failed: (.*, function .*, file .*, line [0-9]+\\.)')
+kStackDumpLineRE = re.compile('^[0-9]+ +([^ ]+) +0x[0-9a-fA-F]+ +([^ ]+)')
+
+def readInfo(path, opts):
+    f = open(path)
+    data = f.read()
+    f.close()
+
+    if opts.truncate != -1:
+        data = data[:opts.truncate]
+
+    gccwarnings = multidict([(m.group(3),m) for m in kGCCWarningRE.finditer(data)]).items()
+    gccerrors = multidict([(m.group(3),m) for m in kGCCErrorRE.finditer(data)]).items()
+    assertions = multidict([(m.group(1),m) for m in kAssertionRE.finditer(data)]).items()
+
+    # Manual scan for stack traces
+    aborts = multidict()
+    prevLine = None
+    lnIter = iter(data.split('\n'))
+    for ln in lnIter:
+        m = kStackDumpLineRE.match(ln)
+        if m:
+            stack = [m.group(2)]
+            for ln in lnIter:
+                m = kStackDumpLineRE.match(ln)
+                if not m:
+                    break
+                stack.append(m.group(2))
+            if prevLine is None or not kAssertionRE.match(prevLine):
+                aborts[tuple(stack)] = stack
+        prevLine = ln
+
+    sections = [
+        (gccwarnings, 'Warnings'),
+        (gccerrors, 'Errors'),
+        (assertions, 'Assertions'),
+        (aborts.items(), 'Aborts'),
+        ]
+
+    if opts.ascending:
+        sections.reverse()
+
+    for l,title in sections:
+        l.sort(key = lambda (a,b): -len(b))
+        if l:
+            print '-- %d %s (%d kinds) --' % (sum([len(b) for a,b in l]), title, len(l))
+            for name,elts in l:
+                print '%5d:' % len(elts), name
+
+def main():
+    global options
+    from optparse import OptionParser
+    parser = OptionParser("usage: %prog [options] {inputs}")
+    parser.add_option("", "--ascending", dest="ascending",
+                      help="Print output in ascending order of severity.",
+                      action="store_true", default=False)
+    parser.add_option("", "--truncate", dest="truncate",
+                      help="Truncate input file (for testing).",
+                      type=int, action="store", default=-1)
+    (opts, args) = parser.parse_args()
+    
+    if not args:
+        parser.error('No inputs specified')
+
+    for arg in args:
+        readInfo(arg, opts)
+
+if __name__=='__main__':
+    main()