[lit] Implement -I option for builtin "diff" command to ignore changes where all lines match RE

[yubing]

small fix to make llvm/utils/lit/tests/shtest-shell.py pass

[pengfei]

LGTM.

llvm/utils/lit/lit/builtin_commands/diff.py

 import difflib
 import functools
 import getopt
 import io
 import locale
 import os
+import re
 import sys
 
 import util
 from util import to_string
 
 class DiffFlags():
     def __init__(self):
         self.ignore_all_space = False
         self.ignore_space_change = False
+        self.ignore_matching_lines = False
+        self.ignore_matching_lines_regex = ""
         self.unified_diff = False
         self.num_context_lines = 3
         self.recursive_diff = False
         self.strip_trailing_cr = False
 
 def getDirTree(path, basedir=""):
     # Tree is a tuple of form (dirname, child_trees).
     # An empty dir has child_trees = [], a file has child_trees = None.
if flags.strip_trailing_cr:
         f = compose2(lambda line: line.replace('\r\n', '\n'), f)
     if flags.ignore_all_space or flags.ignore_space_change:
         ignoreSpace = lambda line, separator: \
                           separator.join(line.split()) + "\n"
         ignoreAllSpaceOrSpaceChange = functools.partial(ignoreSpace, separator='' if flags.ignore_all_space else ' ')
         f = compose2(ignoreAllSpaceOrSpaceChange, f)
 
     for idx, lines in enumerate(filelines):
+        if flags.ignore_matching_lines:
+            lines = filter(lambda x: not re.match(r"{}".format(flags.ignore_matching_lines_regex), x), lines)
         filelines[idx]= [f(line) for line in lines]
 
     func = difflib.unified_diff if flags.unified_diff else difflib.context_diff
     for diff in func(filelines[0], filelines[1], filepaths[0], filepaths[1],
                      n = flags.num_context_lines):
         sys.stdout.write(to_string(diff))
         exitCode = 1
     return exitCode
if sys.platform == "win32":
             # python 3
             sys.stdout = io.TextIOWrapper(sys.stdout.buffer, newline='\n')
         else:
             # python 2.7
             import msvcrt
             msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
     args = argv[1:]
     try:
-        opts, args = getopt.gnu_getopt(args, "wbuU:r", ["strip-trailing-cr"])
+        opts, args = getopt.gnu_getopt(args, "wbuI:U:r", ["strip-trailing-cr"])
     except getopt.GetoptError as err:
         sys.stderr.write("Unsupported: 'diff': %s\n" % str(err))
         sys.exit(1)
 
     flags = DiffFlags()
     filelines, filepaths, dir_trees = ([] for i in range(3))
     for o, a in opts:
         if o == "-w":
             flags.ignore_all_space = True
         elif o == "-b":
             flags.ignore_space_change = True
         elif o == "-u":
             flags.unified_diff = True
         elif o.startswith("-U"):
             flags.unified_diff = True
             try:
                 flags.num_context_lines = int(a)
                 if flags.num_context_lines < 0:
                     raise ValueException
             except:
                 sys.stderr.write("Error: invalid '-U' argument: {}\n"
                                  .format(a))
                 sys.exit(1)
+        elif o == "-I":
+            flags.ignore_matching_lines = True
+            flags.ignore_matching_lines_regex = a
         elif o == "-r":
             flags.recursive_diff = True
         elif o == "--strip-trailing-cr":
             flags.strip_trailing_cr = True
         else:
             assert False, "unhandled option"
 
     if len(args) != 2:

llvm/utils/lit/tests/Inputs/shtest-shell/diff-I.txt

+# Check diff ("diff -I") which is aimed to ignore changes where all lines match RE.
+
+# RUN: echo 'foo' > %t.0
+# RUN: echo 'bar1' >> %t.0
+# RUN: echo 'foo' >> %t.0
+
+# RUN: echo 'foo' > %t.1
+# RUN: echo 'bar2' >> %t.1
+# RUN: echo 'foo' >> %t.1
+
+# RUN: diff -I "bar*" %t.0 %t.1
 No newline at end of file