[llvm] r374649 - Reland r374389: [lit] Clean up internal diff's encoding handling

Joel E. Denny via llvm-commits llvm-commits at lists.llvm.org
Sat Oct 12 04:57:20 PDT 2019


Author: jdenny
Date: Sat Oct 12 04:57:20 2019
New Revision: 374649

URL: http://llvm.org/viewvc/llvm-project?rev=374649&view=rev
Log:
Reland r374389: [lit] Clean up internal diff's encoding handling

To avoid breaking some tests, D66574, D68664, D67643, and D68668
landed together.  However, D68664 introduced an issue now addressed by
D68839, with which these are now all relanding.

Differential Revision: https://reviews.llvm.org/D68664

Added:
    llvm/trunk/utils/lit/tests/Inputs/shtest-shell/diff-encodings.txt
    llvm/trunk/utils/lit/tests/Inputs/shtest-shell/diff-in.bin   (with props)
    llvm/trunk/utils/lit/tests/Inputs/shtest-shell/diff-in.utf16   (with props)
    llvm/trunk/utils/lit/tests/Inputs/shtest-shell/diff-in.utf8
Modified:
    llvm/trunk/utils/lit/lit/builtin_commands/diff.py
    llvm/trunk/utils/lit/tests/max-failures.py
    llvm/trunk/utils/lit/tests/shtest-shell.py

Modified: llvm/trunk/utils/lit/lit/builtin_commands/diff.py
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/utils/lit/lit/builtin_commands/diff.py?rev=374649&r1=374648&r2=374649&view=diff
==============================================================================
--- llvm/trunk/utils/lit/lit/builtin_commands/diff.py (original)
+++ llvm/trunk/utils/lit/lit/builtin_commands/diff.py Sat Oct 12 04:57:20 2019
@@ -1,6 +1,7 @@
 import difflib
 import functools
 import getopt
+import locale
 import os
 import sys
 
@@ -24,37 +25,26 @@ def getDirTree(path, basedir=""):
         return path, sorted(child_trees)
 
 def compareTwoFiles(flags, filepaths):
-    compare_bytes = False
-    encoding = None
     filelines = []
     for file in filepaths:
-        try:
-            with open(file, 'r') as f:
-                filelines.append(f.readlines())
-        except UnicodeDecodeError:
-            try:
-                with io.open(file, 'r', encoding="utf-8") as f:
-                    filelines.append(f.readlines())
-                encoding = "utf-8"
-            except:
-                compare_bytes = True
-
-    if compare_bytes:
-        return compareTwoBinaryFiles(flags, filepaths)
-    else:
-        return compareTwoTextFiles(flags, filepaths, encoding)
+        with open(file, 'rb') as file_bin:
+            filelines.append(file_bin.readlines())
 
-def compareTwoBinaryFiles(flags, filepaths):
-    filelines = []
-    for file in filepaths:
-        with open(file, 'rb') as f:
-            filelines.append(f.readlines())
+    try:
+        return compareTwoTextFiles(flags, filepaths, filelines,
+                                   locale.getpreferredencoding(False))
+    except UnicodeDecodeError:
+        try:
+            return compareTwoTextFiles(flags, filepaths, filelines, "utf-8")
+        except:
+            return compareTwoBinaryFiles(flags, filepaths, filelines)
 
+def compareTwoBinaryFiles(flags, filepaths, filelines):
     exitCode = 0
     if hasattr(difflib, 'diff_bytes'):
         # python 3.5 or newer
         diffs = difflib.diff_bytes(difflib.unified_diff, filelines[0], filelines[1], filepaths[0].encode(), filepaths[1].encode())
-        diffs = [diff.decode() for diff in diffs]
+        diffs = [diff.decode(errors="backslashreplace") for diff in diffs]
     else:
         # python 2.7
         if flags.unified_diff:
@@ -68,15 +58,14 @@ def compareTwoBinaryFiles(flags, filepat
         exitCode = 1
     return exitCode
 
-def compareTwoTextFiles(flags, filepaths, encoding):
+def compareTwoTextFiles(flags, filepaths, filelines_bin, encoding):
     filelines = []
-    for file in filepaths:
-        if encoding is None:
-            with open(file, 'r') as f:
-                filelines.append(f.readlines())
-        else:
-            with io.open(file, 'r', encoding=encoding) as f:
-                filelines.append(f.readlines())
+    for lines_bin in filelines_bin:
+        lines = []
+        for line_bin in lines_bin:
+            line = line_bin.decode(encoding=encoding)
+            lines.append(line)
+        filelines.append(lines)
 
     exitCode = 0
     def compose2(f, g):

Added: llvm/trunk/utils/lit/tests/Inputs/shtest-shell/diff-encodings.txt
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/utils/lit/tests/Inputs/shtest-shell/diff-encodings.txt?rev=374649&view=auto
==============================================================================
--- llvm/trunk/utils/lit/tests/Inputs/shtest-shell/diff-encodings.txt (added)
+++ llvm/trunk/utils/lit/tests/Inputs/shtest-shell/diff-encodings.txt Sat Oct 12 04:57:20 2019
@@ -0,0 +1,9 @@
+# Check that diff falls back to binary mode if it cannot decode a file.
+
+# RUN: diff -u diff-in.bin diff-in.bin
+# RUN: diff -u diff-in.utf16 diff-in.bin && false || true
+# RUN: diff -u diff-in.utf8 diff-in.bin && false || true
+# RUN: diff -u diff-in.bin diff-in.utf8 && false || true
+
+# Fail so lit will print output.
+# RUN: false

Added: llvm/trunk/utils/lit/tests/Inputs/shtest-shell/diff-in.bin
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/utils/lit/tests/Inputs/shtest-shell/diff-in.bin?rev=374649&view=auto
==============================================================================
Binary file - no diff available.

Propchange: llvm/trunk/utils/lit/tests/Inputs/shtest-shell/diff-in.bin
------------------------------------------------------------------------------
    svn:mime-type = application/octet-stream

Added: llvm/trunk/utils/lit/tests/Inputs/shtest-shell/diff-in.utf16
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/utils/lit/tests/Inputs/shtest-shell/diff-in.utf16?rev=374649&view=auto
==============================================================================
Binary file - no diff available.

Propchange: llvm/trunk/utils/lit/tests/Inputs/shtest-shell/diff-in.utf16
------------------------------------------------------------------------------
    svn:mime-type = application/octet-stream

Added: llvm/trunk/utils/lit/tests/Inputs/shtest-shell/diff-in.utf8
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/utils/lit/tests/Inputs/shtest-shell/diff-in.utf8?rev=374649&view=auto
==============================================================================
--- llvm/trunk/utils/lit/tests/Inputs/shtest-shell/diff-in.utf8 (added)
+++ llvm/trunk/utils/lit/tests/Inputs/shtest-shell/diff-in.utf8 Sat Oct 12 04:57:20 2019
@@ -0,0 +1,3 @@
+foo
+bar
+baz

Modified: llvm/trunk/utils/lit/tests/max-failures.py
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/utils/lit/tests/max-failures.py?rev=374649&r1=374648&r2=374649&view=diff
==============================================================================
--- llvm/trunk/utils/lit/tests/max-failures.py (original)
+++ llvm/trunk/utils/lit/tests/max-failures.py Sat Oct 12 04:57:20 2019
@@ -8,7 +8,7 @@
 #
 # END.
 
-# CHECK: Failing Tests (27)
+# CHECK: Failing Tests (28)
 # CHECK: Failing Tests (1)
 # CHECK: Failing Tests (2)
 # CHECK: error: argument --max-failures: requires positive integer, but found '0'

Modified: llvm/trunk/utils/lit/tests/shtest-shell.py
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/utils/lit/tests/shtest-shell.py?rev=374649&r1=374648&r2=374649&view=diff
==============================================================================
--- llvm/trunk/utils/lit/tests/shtest-shell.py (original)
+++ llvm/trunk/utils/lit/tests/shtest-shell.py Sat Oct 12 04:57:20 2019
@@ -34,6 +34,58 @@
 # CHECK: error: command failed with exit status: 127
 # CHECK: ***
 
+
+# CHECK: FAIL: shtest-shell :: diff-encodings.txt
+# CHECK: *** TEST 'shtest-shell :: diff-encodings.txt' FAILED ***
+
+# CHECK: $ "diff" "-u" "diff-in.bin" "diff-in.bin"
+# CHECK-NOT: error
+
+# CHECK: $ "diff" "-u" "diff-in.utf16" "diff-in.bin"
+# CHECK: # command output:
+# CHECK-NEXT: ---
+# CHECK-NEXT: +++
+# CHECK-NEXT: @@
+# CHECK-NEXT: {{^ .f.o.o.$}}
+# CHECK-NEXT: {{^-.b.a.r.$}}
+# CHECK-NEXT: {{^\+.b.a.r..}}
+# CHECK-NEXT: {{^ .b.a.z.$}}
+# CHECK: error: command failed with exit status: 1
+# CHECK: $ "true"
+
+# CHECK: $ "diff" "-u" "diff-in.utf8" "diff-in.bin"
+# CHECK: # command output:
+# CHECK-NEXT: ---
+# CHECK-NEXT: +++
+# CHECK-NEXT: @@
+# CHECK-NEXT: -foo
+# CHECK-NEXT: -bar
+# CHECK-NEXT: -baz
+# CHECK-NEXT: {{^\+.f.o.o.$}}
+# CHECK-NEXT: {{^\+.b.a.r..}}
+# CHECK-NEXT: {{^\+.b.a.z.$}}
+# CHECK: error: command failed with exit status: 1
+# CHECK: $ "true"
+
+# CHECK: $ "diff" "-u" "diff-in.bin" "diff-in.utf8"
+# CHECK: # command output:
+# CHECK-NEXT: ---
+# CHECK-NEXT: +++
+# CHECK-NEXT: @@
+# CHECK-NEXT: {{^\-.f.o.o.$}}
+# CHECK-NEXT: {{^\-.b.a.r..}}
+# CHECK-NEXT: {{^\-.b.a.z.$}}
+# CHECK-NEXT: +foo
+# CHECK-NEXT: +bar
+# CHECK-NEXT: +baz
+# CHECK: error: command failed with exit status: 1
+# CHECK: $ "true"
+
+# CHECK: $ "false"
+
+# CHECK: ***
+
+
 # CHECK: FAIL: shtest-shell :: diff-error-1.txt
 # CHECK: *** TEST 'shtest-shell :: diff-error-1.txt' FAILED ***
 # CHECK: $ "diff" "-B" "temp1.txt" "temp2.txt"
@@ -245,4 +297,4 @@
 # CHECK: PASS: shtest-shell :: sequencing-0.txt
 # CHECK: XFAIL: shtest-shell :: sequencing-1.txt
 # CHECK: PASS: shtest-shell :: valid-shell.txt
-# CHECK: Failing Tests (27)
+# CHECK: Failing Tests (28)




More information about the llvm-commits mailing list