[llvm] 43d9f2d - [opt viewer] Python compat - decode/encode string

Wed Jan 29 14:49:59 PST 2020

Author: Yuanfang Chen
Date: 2020-01-29T14:49:24-08:00
New Revision: 43d9f2d1e8ae2765c1fc02b7cf757c9c05761ac0

URL: https://github.com/llvm/llvm-project/commit/43d9f2d1e8ae2765c1fc02b7cf757c9c05761ac0
DIFF: https://github.com/llvm/llvm-project/commit/43d9f2d1e8ae2765c1fc02b7cf757c9c05761ac0.diff

LOG: [opt viewer] Python compat - decode/encode string

Summary:
Use io.open instead of codecs.open according to here
https://stackoverflow.com/questions/10971033/backporting-python-3-openencoding-utf-8-to-python-2

Add `u` prefix to string literal to make them utf-8 in python2.

Reviewers: anemet, serge-sans-paille

Reviewed by: serge-sans-paille

Differential Revision: https://reviews.llvm.org/D73011

Added: 
    

Modified: 
    llvm/tools/opt-viewer/opt-viewer.py
    llvm/tools/opt-viewer/optrecord.py

Removed: 
    


################################################################################
diff  --git a/llvm/tools/opt-viewer/opt-viewer.py b/llvm/tools/opt-viewer/opt-viewer.py
index 4c105886cfdf..e98781595acc 100755

--- a/llvm/tools/opt-viewer/opt-viewer.py
+++ b/llvm/tools/opt-viewer/opt-viewer.py
@@ -4,9 +4,9 @@
 
 import argparse
 import cgi
-import codecs
 import errno
 import functools
+import io
 from multiprocessing import cpu_count
 import os.path
 import re
@@ -54,12 +54,12 @@ def __init__(self, source_dir, output_dir, filename, no_highlight):
                 existing_filename = fn
 
         self.no_highlight = no_highlight
-        self.stream = codecs.open(os.path.join(output_dir, optrecord.html_file_name(filename)), 'w', encoding='utf-8')
+        self.stream = io.open(os.path.join(output_dir, optrecord.html_file_name(filename)), 'w', encoding='utf-8')
         if existing_filename:
-            self.source_stream = open(existing_filename)
+            self.source_stream = io.open(existing_filename, encoding='utf-8')
         else:
             self.source_stream = None
-            print('''
+            print(u'''
 <html>
 <h1>Unable to locate file {}</h1>
 </html>
@@ -72,10 +72,7 @@ def render_source_lines(self, stream, line_remarks):
         file_text = stream.read()
 
         if self.no_highlight:
-            if sys.version_info.major >= 3:
-                html_highlighted = file_text
-            else:
-                html_highlighted = file_text.decode('utf-8')
+            html_highlighted = file_text
         else:
             html_highlighted = highlight(
             file_text,
@@ -147,7 +144,7 @@ def render(self, line_remarks):
         if not self.source_stream:
             return
 
-        print('''
+        print(u'''
 <html>
 <title>{}</title>
 <meta charset="utf-8" />
@@ -186,7 +183,7 @@ def render(self, line_remarks):
 <tbody>'''.format(os.path.basename(self.filename)), file=self.stream)
         self.render_source_lines(self.source_stream, line_remarks)
 
-        print('''
+        print(u'''
 </tbody>
 </table>
 </body>
@@ -195,7 +192,7 @@ def render(self, line_remarks):
 
 class IndexRenderer:
     def __init__(self, output_dir, should_display_hotness, max_hottest_remarks_on_index):
-        self.stream = codecs.open(os.path.join(output_dir, 'index.html'), 'w', encoding='utf-8')
+        self.stream = io.open(os.path.join(output_dir, 'index.html'), 'w', encoding='utf-8')
         self.should_display_hotness = should_display_hotness
         self.max_hottest_remarks_on_index = max_hottest_remarks_on_index
 
@@ -210,7 +207,7 @@ def render_entry(self, r, odd):
 </tr>'''.format(**locals()), file=self.stream)
 
     def render(self, all_remarks):
-        print('''
+        print(u'''
 <html>
 <meta charset="utf-8" />
 <head>
@@ -233,7 +230,7 @@ def render(self, all_remarks):
         for i, remark in enumerate(all_remarks[:max_entries]):
             if not suppress(remark):
                 self.render_entry(remark, i % 2)
-        print('''
+        print(u'''
 </table>
 </body>
 </html>''', file=self.stream)

diff  --git a/llvm/tools/opt-viewer/optrecord.py b/llvm/tools/opt-viewer/optrecord.py
index f6fd772689a9..2dff0c847c77 100644
--- a/llvm/tools/opt-viewer/optrecord.py
+++ b/llvm/tools/opt-viewer/optrecord.py
@@ -2,6 +2,7 @@
 
 from __future__ import print_function
 
+import io
 import yaml
 # Try to use the C parser.
 try:
@@ -272,7 +273,7 @@ def get_remarks(input_file, filter_=None):
     all_remarks = dict()
     file_remarks = defaultdict(functools.partial(defaultdict, list))
 
-    with open(input_file) as f:
+    with io.open(input_file, encoding = 'utf-8') as f:
         docs = yaml.load_all(f, Loader=Loader)
 
         filter_e = None


        
