From 14b2b30a9eb80d9dfb046f53d15890c97a962385 Mon Sep 17 00:00:00 2001
From: dan sinclair <dsinclair@google.com>
Date: Tue, 28 Jul 2020 23:18:20 -0400
Subject: [PATCH 1/7] Simple script to check for inclusive language.

This CL adds a simple script to check for inclusive language. All files
in the repo are scanned and any matches are output.
---
 tools/check_language.py | 99 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 99 insertions(+)
 create mode 100755 tools/check_language.py

diff --git a/tools/check_language.py b/tools/check_language.py
new file mode 100755
index 000000000..8e91c67ef
--- /dev/null
+++ b/tools/check_language.py
@@ -0,0 +1,99 @@
+#!/usr/bin/env python
+
+# Copyright 2020 The Amber Authors. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import print_function
+
+import fnmatch
+import os
+import re
+import sys
+
+REGEXES = [
+	r"(?i)(black|white|gr[ea]y)[-_]?list",
+	r"(?i)(first class citizen)",
+	r"(?i)(black|white|gr[ea]y)[-_]?hat",
+	r"(?i)(master|slave)",
+	r"(?i)\b(him|his|she|her|hers|man|woman)\b",
+	r"(?i)\s(he|he'd|he's|he'll)\s",
+	r"(?i)grandfather",
+	r"(?i)\bmitm\\b",
+	r"(?i)native",
+	r"(?i)\b(crazy|insane|blind\sto|flying\sblind|blind\seye|cripple|crippled|dumb|dummy|paranoid)\b",
+	r"(?i)\b(sane|sanity)\b",
+	r"(?i)red[-_]?line",
+]
+
+def find(top, filename_glob, skip_glob_list):
+    """Returns files in the tree rooted at top matching filename_glob but not
+    in directories matching skip_glob_list."""
+
+    file_list = []
+    for path, dirs, files in os.walk(top):
+        for glob in skip_glob_list:
+            for match in fnmatch.filter(dirs, glob):
+                dirs.remove(match)
+        for filename in fnmatch.filter(files, filename_glob):
+        	if filename == os.path.basename(__file__):
+      			continue
+        	file_list.append(os.path.join(path, filename))
+    return file_list
+
+
+def filtered_descendants(glob):
+    """Returns glob-matching filenames under the current directory, but skips
+    some irrelevant paths."""
+    return find('.', glob, ['third_party', 'external', 'build*', 'out*',
+                            'CompilerIdCXX', '.git'])
+
+
+def alert_if_lang_matches(glob):
+    """Prints names of all files matching non-inclusive language.
+
+    Finds all glob-matching files under the current directory and checks if they
+    contain the language pattern.  Prints the names of all the files that
+    match.
+
+    Returns the total number of file names printed.
+    """
+
+    reg_list = []
+    for reg in REGEXES:
+    	reg_list.append(re.compile(reg))
+
+    printed_count = 0
+    for file in filtered_descendants(glob):
+        has_match = False
+        with open(file) as contents:
+            for line in contents:
+            	for reg in reg_list:
+            		match = reg.search(line)
+            		if match:
+            			print(file, ': found non-inclusive language:', match.group(0))
+            			printed_count += 1
+
+    return printed_count
+
+
+def main():
+    globs = ['*']
+    count = 0
+    for glob in globs:
+        count += alert_if_lang_matches(glob)
+
+    sys.exit(count > 0)
+
+if __name__ == '__main__':
+  main()

From 78aaf1a9916759d7a6868ed06061fc828bcfe5bc Mon Sep 17 00:00:00 2001
From: dan sinclair <dsinclair@google.com>
Date: Tue, 28 Jul 2020 23:32:45 -0400
Subject: [PATCH 2/7] fix regex

---
 tools/check_language.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/check_language.py b/tools/check_language.py
index 8e91c67ef..991af73a0 100755
--- a/tools/check_language.py
+++ b/tools/check_language.py
@@ -29,7 +29,7 @@
 	r"(?i)\b(him|his|she|her|hers|man|woman)\b",
 	r"(?i)\s(he|he'd|he's|he'll)\s",
 	r"(?i)grandfather",
-	r"(?i)\bmitm\\b",
+	r"(?i)\bmitm\b",
 	r"(?i)native",
 	r"(?i)\b(crazy|insane|blind\sto|flying\sblind|blind\seye|cripple|crippled|dumb|dummy|paranoid)\b",
 	r"(?i)\b(sane|sanity)\b",

From 36306326637b785fa79e253ef2ca48de13679150 Mon Sep 17 00:00:00 2001
From: dan sinclair <dsinclair@google.com>
Date: Tue, 28 Jul 2020 23:36:26 -0400
Subject: [PATCH 3/7] formatting

---
 tools/check_language.py | 44 ++++++++++++++++++++---------------------
 1 file changed, 22 insertions(+), 22 deletions(-)

diff --git a/tools/check_language.py b/tools/check_language.py
index 991af73a0..4ccb07f3b 100755
--- a/tools/check_language.py
+++ b/tools/check_language.py
@@ -22,18 +22,18 @@
 import sys
 
 REGEXES = [
-	r"(?i)(black|white|gr[ea]y)[-_]?list",
-	r"(?i)(first class citizen)",
-	r"(?i)(black|white|gr[ea]y)[-_]?hat",
-	r"(?i)(master|slave)",
-	r"(?i)\b(him|his|she|her|hers|man|woman)\b",
-	r"(?i)\s(he|he'd|he's|he'll)\s",
-	r"(?i)grandfather",
-	r"(?i)\bmitm\b",
-	r"(?i)native",
-	r"(?i)\b(crazy|insane|blind\sto|flying\sblind|blind\seye|cripple|crippled|dumb|dummy|paranoid)\b",
-	r"(?i)\b(sane|sanity)\b",
-	r"(?i)red[-_]?line",
+    r"(?i)(black|white|gr[ea]y)[-_]?list",
+    r"(?i)(first class citizen)",
+    r"(?i)(black|white|gr[ea]y)[-_]?hat",
+    r"(?i)(master|slave)",
+    r"(?i)\b(him|his|she|her|hers|man|woman)\b",
+    r"(?i)\s(he|he'd|he's|he'll)\s",
+    r"(?i)grandfather",
+    r"(?i)\bmitm\b",
+    r"(?i)native",
+    r"(?i)\b(crazy|insane|blind\sto|flying\sblind|blind\seye|cripple|crippled|dumb|dummy|paranoid)\b",
+    r"(?i)\b(sane|sanity)\b",
+    r"(?i)red[-_]?line",
 ]
 
 def find(top, filename_glob, skip_glob_list):
@@ -46,9 +46,9 @@ def find(top, filename_glob, skip_glob_list):
             for match in fnmatch.filter(dirs, glob):
                 dirs.remove(match)
         for filename in fnmatch.filter(files, filename_glob):
-        	if filename == os.path.basename(__file__):
-      			continue
-        	file_list.append(os.path.join(path, filename))
+            if filename == os.path.basename(__file__):
+                continue
+            file_list.append(os.path.join(path, filename))
     return file_list
 
 
@@ -71,18 +71,18 @@ def alert_if_lang_matches(glob):
 
     reg_list = []
     for reg in REGEXES:
-    	reg_list.append(re.compile(reg))
+        reg_list.append(re.compile(reg))
 
     printed_count = 0
     for file in filtered_descendants(glob):
         has_match = False
         with open(file) as contents:
             for line in contents:
-            	for reg in reg_list:
-            		match = reg.search(line)
-            		if match:
-            			print(file, ': found non-inclusive language:', match.group(0))
-            			printed_count += 1
+                for reg in reg_list:
+                    match = reg.search(line)
+                    if match:
+                        print(file, ': found non-inclusive language:', match.group(0))
+                        printed_count += 1
 
     return printed_count
 
@@ -96,4 +96,4 @@ def main():
     sys.exit(count > 0)
 
 if __name__ == '__main__':
-  main()
+      main()

From 39c2f8c1f29bafd6f2cc80c835d60a1f9f0cf0c2 Mon Sep 17 00:00:00 2001
From: dan sinclair <dsinclair@chromium.org>
Date: Mon, 10 Aug 2020 17:14:49 -0400
Subject: [PATCH 4/7] Review feedback

---
 tools/check_language.py      | 191 ++++++++++++++++++++++++-----------
 tools/check_language.pyc     | Bin 0 -> 4656 bytes
 tools/check_language_test.py |  62 ++++++++++++
 3 files changed, 195 insertions(+), 58 deletions(-)
 create mode 100644 tools/check_language.pyc
 create mode 100755 tools/check_language_test.py

diff --git a/tools/check_language.py b/tools/check_language.py
index 4ccb07f3b..15cf0514e 100755
--- a/tools/check_language.py
+++ b/tools/check_language.py
@@ -6,7 +6,7 @@
 # you may not use this file except in compliance with the License.
 # You may obtain a copy of the License at
 #
-#     http://www.apache.org/licenses/LICENSE-2.0
+#	http://www.apache.org/licenses/LICENSE-2.0
 #
 # Unless required by applicable law or agreed to in writing, software
 # distributed under the License is distributed on an "AS IS" BASIS,
@@ -14,7 +14,13 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from __future__ import print_function
+"""
+Script to check files for inclusive language. The script will scan all files
+and flag non-inclusive terminology which is identified.
+
+Usage, run the script from a folder and the script will scan down through that
+folder.
+"""
 
 import fnmatch
 import os
@@ -22,78 +28,147 @@
 import sys
 
 REGEXES = [
-    r"(?i)(black|white|gr[ea]y)[-_]?list",
-    r"(?i)(first class citizen)",
-    r"(?i)(black|white|gr[ea]y)[-_]?hat",
-    r"(?i)(master|slave)",
-    r"(?i)\b(him|his|she|her|hers|man|woman)\b",
-    r"(?i)\s(he|he'd|he's|he'll)\s",
-    r"(?i)grandfather",
-    r"(?i)\bmitm\b",
-    r"(?i)native",
-    r"(?i)\b(crazy|insane|blind\sto|flying\sblind|blind\seye|cripple|crippled|dumb|dummy|paranoid)\b",
-    r"(?i)\b(sane|sanity)\b",
-    r"(?i)red[-_]?line",
+	r"(?i)black[-_]?list",
+	r"(?i)white[-_]?list",
+	r"(?i)gr[ea]y[-_]?list",
+	r"(?i)(first class citizen)",
+	r"(?i)black[-_]?hat",
+	r"(?i)white[-_]?hat",
+	r"(?i)gr[ea]y[-_]?hat",
+	r"(?i)master",
+	r"(?i)slave",
+	r"(?i)\bhim\b",
+	r"(?i)\bhis\b",
+	r"(?i)\bshe\b",
+	r"(?i)\bher\b",
+	r"(?i)\bhers\b",
+	r"(?i)\bman\b",
+	r"(?i)\bwoman\b",
+	r"(?i)\she\s",
+	r"(?i)\she$",
+	r"(?i)^he\s",
+	r"(?i)^he$",
+	"(?i)\\she['|\u2019]d\\s",
+	"(?i)\\she['|\u2019]d$",
+	"(?i)^he['|\u2019]d\\s",
+	"(?i)^he['|\u2019]d$",
+	"(?i)\\she['|\u2019]s\\s",
+	"(?i)\\she['|\u2019]s$",
+	"(?i)^he['|\u2019]s\\s",
+	"(?i)^he['|\u2019]s$",
+	"(?i)\\she['|\u2019]ll\\s",
+	"(?i)\\she['|\u2019]ll$",
+	"(?i)^he['|\u2019]ll\\s",
+	"(?i)^he['|\u2019]ll$",
+	r"(?i)grandfather",
+	r"(?i)\bmitm\b",
+	r"(?i)\bcrazy\b",
+	r"(?i)\binsane\b",
+	r"(?i)\bblind\sto\b",
+	r"(?i)\bflying\sblind\b",
+	r"(?i)\bblind\seye\b",
+	r"(?i)\bcripple\b",
+	r"(?i)\bcrippled\b",
+	r"(?i)\bdumb\b",
+	r"(?i)\bdummy\b",
+	r"(?i)\bparanoid\b",
+	r"(?i)\bsane\b",
+	r"(?i)\bsanity\b",
+	r"(?i)red[-_]?line",
+]
+
+SUPPRESSIONS = [
+	r"(?i)MS_SLAVE",
+	r"(?i)man[ -_]?page",
 ]
 
+
+REGEX_LIST = []
+for reg in REGEXES:
+	REGEX_LIST.append(re.compile(reg))
+
+SUPPRESSION_LIST = []
+for supp in SUPPRESSIONS:
+	SUPPRESSION_LIST.append(re.compile(supp))
+
 def find(top, filename_glob, skip_glob_list):
-    """Returns files in the tree rooted at top matching filename_glob but not
-    in directories matching skip_glob_list."""
+	"""Returns files in the tree rooted at top matching filename_glob but not
+	in directories matching skip_glob_list."""
 
-    file_list = []
-    for path, dirs, files in os.walk(top):
-        for glob in skip_glob_list:
-            for match in fnmatch.filter(dirs, glob):
-                dirs.remove(match)
-        for filename in fnmatch.filter(files, filename_glob):
-            if filename == os.path.basename(__file__):
-                continue
-            file_list.append(os.path.join(path, filename))
-    return file_list
+	file_list = []
+	for path, dirs, files in os.walk(top):
+		for glob in skip_glob_list:
+			for match in fnmatch.filter(dirs, glob):
+				dirs.remove(match)
+		for filename in fnmatch.filter(files, filename_glob):
+			if filename == os.path.basename(__file__):
+				continue
+			file_list.append(os.path.join(path, filename))
+	return file_list
 
 
 def filtered_descendants(glob):
-    """Returns glob-matching filenames under the current directory, but skips
-    some irrelevant paths."""
-    return find('.', glob, ['third_party', 'external', 'build*', 'out*',
-                            'CompilerIdCXX', '.git'])
+	"""Returns glob-matching filenames under the current directory, but skips
+	some irrelevant paths."""
+	return find('.', glob, ['third_party', 'external', 'build*', 'out*',
+							'CompilerIdCXX', '.git'])
+
+def check_match(filename, contents):
+	"""Check if contents contains any matching entries"""
+	ret = False
+	for reg in REGEX_LIST:
+		match = reg.search(contents)
+		if match:
+			suppressed = False
+			for supp in SUPPRESSION_LIST:
+				idx = match.start()
+				supp_match = supp.match(contents[idx:])
+				if supp_match:
+					suppressed = True
+
+				# This is a hack to handle the MS_ prefix that is needed
+				# to check for. Find a better way if we get more suppressions
+				# which modify the prefix of the string
+				if idx >= 3:
+					supp_match = supp.match(contents[idx - 3:])
+					if supp_match:
+						suppressed = True
+
+			if not suppressed:
+				# No matching suppression.
+				print("{}: found non-inclusive language: {}".format(
+						filename, match.group(0)))
+				ret = True
+
+	return ret
 
 
 def alert_if_lang_matches(glob):
-    """Prints names of all files matching non-inclusive language.
-
-    Finds all glob-matching files under the current directory and checks if they
-    contain the language pattern.  Prints the names of all the files that
-    match.
-
-    Returns the total number of file names printed.
-    """
+	"""Prints names of all files matching non-inclusive language.
 
-    reg_list = []
-    for reg in REGEXES:
-        reg_list.append(re.compile(reg))
+	Finds all glob-matching files under the current directory and checks if they
+	contain the language pattern.  Prints the names of all the files that
+	match.
 
-    printed_count = 0
-    for file in filtered_descendants(glob):
-        has_match = False
-        with open(file) as contents:
-            for line in contents:
-                for reg in reg_list:
-                    match = reg.search(line)
-                    if match:
-                        print(file, ': found non-inclusive language:', match.group(0))
-                        printed_count += 1
+	Returns the total number of file names printed.
+	"""
+	printed_count = 0
+	for file in filtered_descendants(glob):
+		has_match = False
+		with open(file) as contents:
+			if check_match(file, contents.read()):
+				printed_count += 1
 
-    return printed_count
+	return printed_count
 
 
 def main():
-    globs = ['*']
-    count = 0
-    for glob in globs:
-        count += alert_if_lang_matches(glob)
+	globs = ['*']
+	count = 0
+	for glob in globs:
+		count += alert_if_lang_matches(glob)
 
-    sys.exit(count > 0)
+	sys.exit(count > 0)
 
 if __name__ == '__main__':
-      main()
+	main()
diff --git a/tools/check_language.pyc b/tools/check_language.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..b8d9e29f8a26e7d676a7bf2128a7384a04974f28
GIT binary patch
literal 4656
zcmcInO>-N^5$y#?kPDHfWa>MLw6<vrQY2Dxtk_niVy8%2QI(^}fE21I(p!t20WjoZ
z7uXq)gbkeNd#ZBD%~d(%5BQW@D#u)W%rS@jh5Ufz^(+=3WGR;@BzAT_dS<$3Ucc@w
z{%f%u{`syS(&%pu?@#gQ1BXZuZKHHZ6ex0N8<nhHpzT6lFVc1~ug}o-3<)$*&XOpR
zm?JSy!X;5Aaf-wOiA54`kXRydn#36rZ<1IhahAk666Z-=AaRkzB@&lO{D{OA5<ez!
zmBcj?9*MU|yiMXA5-TL$CGj4K>m({9ZjiW1;wL0-k+@A_mBbo}J0$K>bB(s4$@?UJ
zN=>L;q9%-*qoWm)v$U~$g|_EO&e5JrvPgSnlJj)z@XzV~leSp+loc*z!V4r%oe*9a
z3okia;sg2y@-Xn8t-#Em*$RyP&{kmbN49c?Bn<zU_6wAzjyyxhL{5yeE>Nv<pU?jv
zD9W`kRUPA*#0y(8-1izPlG<w|si)#F>S=W#y(oyAy`U*qy(cZ{>1@WKiXzm5*b7jx
z)5<|Cyhao>y*P<)Pv#q$wpE-&Nwe=Awp7^il=hU6u~7{r#cH|yRAc#DUfPR2Gufh%
zCT%Z(GLev}$BUmBoa`@>L!Oo<y=DvVz?8EYt7Y|X{5{fd!qCbm>P9^Z!u{vB{oPL@
zrOmh-Dj7NHK0A_brq5-t+n)?v8Vyt$D%Hjdqd;pfR7QOz;~V<S4>o}&<KD?0+`Ige
zEx5lt>Td@cXQtgzQ%Avp)Tc(Roq9{Pcj{AZJ=NANIn{2-6zzq{e5^es&<<j>7smpJ
zN!F9=v%@Ruu|C{f8MnT)WAmfQXszgT`AQIcetodhd;iYek9P%@$Pbs7I5Dy^9>Dw)
z{g{!T)%3ut_Rz1~L%(7Vp7GK>FyZ`5?T8{wdAW&EG*N6yVLK-`{)Lehy)@dVnF8dE
z04PsSTvuBezVFHPglX_qA3bm6>eW@OgP1QpN8wJr9;p~7ZW8p4m900TzKWYWIvcHz
zePApv`@Br9&`zD5y%TZY>G5u(K7q~&s6?+_N5@1<bhKH^$-GVg`w}%hZ>0Fd7IY|c
za$+jQ$O&UP-tgBozxMerf4e!h7>IrDv2S-kC1DZDGI~pR*74}Spa9hli*)oI8KOOh
z2E^35vHM5bDbjF;hO;y*(a}dVD4_Qa4Z-2p$rNa>NP}4#%+WCqEYonF+j}!KuuSfB
zH)*STi?)uQ<kBS?fZ<vCQyRK7aP5|uQzC<99Lvgopspq`@&Hj`J{N#6)^&NZjSw13
zpQkOz)GCOVq!ScXX?kf4nzm%EGSW1ulwO)7MhY)rM(=p-z=SQ_w-t<ow)C4(QupdT
z1BNzb7c+%QWoVLAf%V7YdS7*{sLw>XTH%w#IS?h<%;0qxMEkIVs1e&ahL0J_fV6Bi
zmF?s}TG0;BY?vJCftIX-ZTLQ`?)z3c=yYT(tn^-@;%qm*K$u_{Pb@pu-Y`<86*Nqg
zc0pFRI?Gd8P1vRlw|Femob9(=ncl2ezIp|9vW4dGxb{@T3)h6^I2NdMZ9^W&DCx8j
zw$_4nU8ZX$Ng};w<EB53k)6KXy8-X}63bX(qnVO(%~^CVIp^?PbV|;O6Y_2H!^&HT
zzKsfyi3AA9M3{ad%W0PAm{GtwYhF4>0o!zYe0RAy+Uvy}HaTR5y)=c|<IC>fvKZh~
z)MZyEZRsgUMDiej6knNMHLTmJ;izL;DiuDw*Yxe}$s=5J97LM0z1~xixT*QPlb*S0
zFKj(&cW~tCL$UtsnH^efDr50mwOq?<S1mE1@_G)P$rZLkGbwx_bqGws8Vv^{s{$3z
zIU$3X4}8oEe@6p{J}l7D-v~Bu?EaNWf_<`Jo!DV&fKR52R&JJ#x@3xwQ_L0^01q5v
zfjJtKXb&`j>zku%a9*Z~c}f)l<=__fbmXe={aH%yO-ZBk;)xmGj%IYfrS3icZGmp|
z_l$`>Y=d>MD{|hVO$`h5;8(mufx6#QcaeWvV6a++uS9dUy>2r*)$qb3HoyV07E}TR
z4J1|liQ8j{c|fu6=@k@T5AP%U0*+ot=yI^%_r4w~$WevQ)cVzDfQ2+n7}d=Oo6r2u
zAJ(2&FV`|i!<OMouRVSIxVl-ZJ^an1Y@B^m8{n(T@yq(ple8!8Jfxz)wq3i46t82q
zs&Yzav6!2LD<Mjy8NHj?O00+ObvmikT4of(O)I3tk=2tseCs~1j{(?gGG54dhShiv
z1r<u5fh7<CzZaZkyxrLa=K|iR3nh%6#oJN?p9#CVr3Q9)fMn><(H9KEJanz|wF9+4
zEch9>4%q$f1|t?GqB({q!b$p=u?Y-)h-CoAE#T*iXWeC>#mUjK0LOfsDuxIXuJ)3~
zB)y*iWjejj(SSVO{S34RRN;%@hphBp8Of&i_Q>#Q&|uc;m)#LeEr;d1Fg-E-ta{!^
zQ)aj+ZMnlzJ|^O8z_oY4+U1PN0wys*<i*HZK$0+%CybWq@CopDiEF{Fn5`aF_(G}|
zx!?~03(^FEtIDXctyBgglVXrtA{?#chj1b@iVKmn@v0T*40YAFApQEF$GKhr?lrz@
z*r=54BK7YvU{gkNOBQ%bh(;F*A-aj3hv~wC?ExwPTNALdafnfOl_9sWd!F$IxG)4Q
z*ceNkp8$gyUjkqIAVhrJ3OIU&7k*?z$<2%?xTCs?!up`@XJJ_$Aw2L<=I01#S>U$k
z_L>6)+t~*B{RwaT#YK*5-SKQ;l$-FV?^ifd*(}HRMH2dcm4inWPnHX%vU(?%uw1uU
zGn@{eV7FTJGCHd7aKXN8R|~V?SiQo%?{dK#WyoR}*wd+gfZ9kMoBH?@gxK2unxn8f
zKW`_Z7s+2-KwW=>qEuJ_DdE3ZbpC(;?o82fkr6FAmn|J$F1V-Nl6%!%cIOwI{{XER
BXq5l}

literal 0
HcmV?d00001

diff --git a/tools/check_language_test.py b/tools/check_language_test.py
new file mode 100755
index 000000000..3534dab1b
--- /dev/null
+++ b/tools/check_language_test.py
@@ -0,0 +1,62 @@
+#!/usr/bin/env python
+
+# Copyright 2020 The Amber Authors. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+"""Unit tests for check_language.py."""
+
+import os
+import sys
+import unittest
+
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+import check_language
+
+class TestCheckLanguage(unittest.TestCase):
+	def testMatches(self):
+		tests = ["blacklist", "black-list", "black_list", "whitelist",
+			"white-list", "white_list", "greylist", "grey-list", "grey_list",
+			"graylist", "gray-list", "gray_list", "first class citizen",
+			"blackhat", "black-hat", "black_hat", "whitehat", "white-hat",
+			"white_hat", "greyhat", "grey-hat", "grey_hat", "grayhat",
+			"gray-hat", "gray_hat", "master", "slave", "him", "his", "she",
+			"her", "hers", "man", "woman", "he", "he'd", "he's", "he'll",
+			#"he\u2019d", "he\u2019s", "he\u2019ll",
+			"grandfather", "mitm", "crazy", "insane", "blind to",
+			"flying blind", "blind eye", "cripple", "crippled", "dumb",
+			"dummy", "paranoid", "sane", "sanity", "redline", "red-line",
+			"red_line"]
+
+		for word in tests:
+			self.assertTrue(
+				check_language.check_match("", "this is a " + word + " attempt"),
+				word)
+
+
+	def testSuppression(self):
+		self.assertFalse(check_language.check_match("", "in the man-pages"))
+		self.assertFalse(check_language.check_match("", "the MS_SLAVE test"))
+
+
+	def testMatchStartofFileWhenRequireSpace(self):
+		self.assertTrue(check_language.check_match("", "he said"))
+
+
+	def testMatchOverNewline(self):
+		self.assertTrue(check_language.check_match("", "flying\nblind"))
+
+
+if __name__ == '__main__':
+	unittest.main()

From 77d5795c5afe7f42d83f9531812f3049a6c97ec2 Mon Sep 17 00:00:00 2001
From: dan sinclair <dsinclair@chromium.org>
Date: Mon, 10 Aug 2020 17:29:55 -0400
Subject: [PATCH 5/7] more review

---
 tools/check_language.py  |  35 ++++++++++++++++++++---------------
 tools/check_language.pyc | Bin 4656 -> 4779 bytes
 2 files changed, 20 insertions(+), 15 deletions(-)

diff --git a/tools/check_language.py b/tools/check_language.py
index 15cf0514e..b7ca528b2 100755
--- a/tools/check_language.py
+++ b/tools/check_language.py
@@ -48,18 +48,18 @@
 	r"(?i)\she$",
 	r"(?i)^he\s",
 	r"(?i)^he$",
-	"(?i)\\she['|\u2019]d\\s",
-	"(?i)\\she['|\u2019]d$",
-	"(?i)^he['|\u2019]d\\s",
-	"(?i)^he['|\u2019]d$",
-	"(?i)\\she['|\u2019]s\\s",
-	"(?i)\\she['|\u2019]s$",
-	"(?i)^he['|\u2019]s\\s",
-	"(?i)^he['|\u2019]s$",
-	"(?i)\\she['|\u2019]ll\\s",
-	"(?i)\\she['|\u2019]ll$",
-	"(?i)^he['|\u2019]ll\\s",
-	"(?i)^he['|\u2019]ll$",
+	r"(?i)\she['|\u2019]d\s",
+	r"(?i)\she['|\u2019]d$",
+	r"(?i)^he['|\u2019]d\s",
+	r"(?i)^he['|\u2019]d$",
+	r"(?i)\she['|\u2019]s\s",
+	r"(?i)\she['|\u2019]s$",
+	r"(?i)^he['|\u2019]s\s",
+	r"(?i)^he['|\u2019]s$",
+	r"(?i)\she['|\u2019]ll\s",
+	r"(?i)\she['|\u2019]ll$",
+	r"(?i)^he['|\u2019]ll\s",
+	r"(?i)^he['|\u2019]ll$",
 	r"(?i)grandfather",
 	r"(?i)\bmitm\b",
 	r"(?i)\bcrazy\b",
@@ -152,12 +152,17 @@ def alert_if_lang_matches(glob):
 
 	Returns the total number of file names printed.
 	"""
+	verbose = False
 	printed_count = 0
 	for file in filtered_descendants(glob):
 		has_match = False
-		with open(file) as contents:
-			if check_match(file, contents.read()):
-				printed_count += 1
+		try:
+			with open(file, 'r', encoding='utf8') as contents:
+				if check_match(file, contents.read()):
+					printed_count += 1
+		except:
+			if verbose:
+				print("skipping {}".format(file))
 
 	return printed_count
 
diff --git a/tools/check_language.pyc b/tools/check_language.pyc
index b8d9e29f8a26e7d676a7bf2128a7384a04974f28..b1f3815fae34cc3f814897bddeef2c52087d363b 100644
GIT binary patch
delta 386
zcmXv}Jxc>Y6r6V-n?yZwBEcLMTByV}D5lncR)QyzG#17^<sw{?yNxK`ks?-U1h2EP
zRvX3Ezv8dRAMkC&VrKWfnR)y6WBq+Ym{VtN=lfICosj@gWb8ANCng1C1WCvY+>W3K
zDKI89&j!fMnQY;%31uKPAq_}o3uA*Gw~*OTrtYUUy4>WXfw+T|Z8mm!WCXONz;U}Z
z@IbUlDIuOf7SOeIkY74D98AD!o6+LrNv-(x>UcEbU4U5Wb%W@lC&TDUSzHX&Wh2zu
zQ8Le*T!;NWYisveO@Gh#G*y{q?p{BL{MvsN2j|jX<?7Gs>VARgCWt$|Bv20D`*9el
zK;~9?vZBYJBuLN_!=x%zXqitzUj9-ZQa!J@5A>ElyL+^q|G1~3&H=xXHx{RMwNzZ7
EU(Rbu^8f$<

delta 264
zcmZ3jx<Q4F`7<w9@{WycM!fZ`3=9k$K<o^}#c@C)g^{6_k)a}xp@e~<hJm4(k-;U_
znW2`6p#&(w%uvF_P{RZg?bl?eWnm~`261ax7_wLxnt`gB7>WWIY8V+(m>A4~#^f<D
zgr_hw1V$7JGlT<$gEd${_V6$=Fa#83=9Lt0e$C6xXqE}&Gx%wM+!7=KA|!!C2}o&v
zL26!*28>sfnwSDnB>)tfoXI~;kPpaU;ACSIW@KaJXB1@=pDZO%%BVMaf<O!7(#fKN
cPK*YVBLqX)^nl8OOeSv@{LCuM$-%=20IR7l4gdfE


From 87edc51cf005760ed81e3db3b225a71ebbbe9fc3 Mon Sep 17 00:00:00 2001
From: dan sinclair <dsinclair@chromium.org>
Date: Tue, 11 Aug 2020 10:20:25 -0400
Subject: [PATCH 6/7] Remove pyc file

---
 .gitignore               |   2 ++
 tools/check_language.pyc | Bin 4779 -> 0 bytes
 2 files changed, 2 insertions(+)
 delete mode 100644 tools/check_language.pyc

diff --git a/.gitignore b/.gitignore
index 55f5ccee7..d5f3eb0f8 100644
--- a/.gitignore
+++ b/.gitignore
@@ -19,6 +19,8 @@ third_party/vulkan-loader
 third_party/vulkan-validationlayers/
 .vs
 
+*.pyc
+
 # Vim swap files
 [._]*.s[a-w][a-z]
 
diff --git a/tools/check_language.pyc b/tools/check_language.pyc
deleted file mode 100644
index b1f3815fae34cc3f814897bddeef2c52087d363b..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001

literal 4779
zcmcIn&vV<x6@DNkN}#3Kj(@vuj3i1-yS8MzaqW0IO*)q1cqVmS(5^hP6by)6k}H7#
ziCxNKEKU!~DVNUl(pzSF?Xl<1bb9P1#~yp=ztBIR{oaBgMaS-?u0#O)<GtPYcE9(%
z-SWQ{tGE7qBZz49w}S7dc=WDAB#1Wfc1V;cc4z~Iyj-G<Qc*6`M!6`@(8df2RPmlA
zQ6Vu$VxELcqDtZji3JjiB;F!%l*BO-$4R_R;slA4Bu<eyP2voRvn0-uI8WjSBrcHn
zA&GZLTqNO<c$dU`B;F^nMB)PyACkC4qDJB}i7O<2MB*xmYb2IQtdO`);s&)=Xaknq
zB=KWv!R!jP;M5%LEs>n1)vXJ(F;8-iwq25C+OCqErvrz7PVb+z&ca8ma3vRBAbI4F
z@WNR5sIx9UqOTzj2XEN|-290xz}efj0GIFB!f}#t{A1cFQI<LKI2{l<3D&wq_1axt
z|9{|Btw)*a8qcI&)RxhX*Hp38UNg-+l|*r0t6k~EVbbb{ExGJHZc9(+8qZZ6qZ}q)
zh=NtChKcZ+aoF;bG`Tj>H!|y}B#qP7z<b_SQQK46Q$i+2HI)?0)#?+C;jemGKk>|D
zie{E}yb#93LS`NheyDRYzeu06T9)=(ZG1yh%{7**>fiW#sNaU8wNKRLMjS>v&#nbq
zpTtU=aWhOZa?*TqB;CrM$#82h={Ps)s5MoljTgnC)?TEH`bs93_3`gb0!zlNlR3Ec
z#4D!Y_Ufp;6KbrPc1Kkmhr3cA8Pzr$ZPnRqOx5*NUAN^_y)84;7bf}`drF`aCa5ot
z1)isQOJUC@kEqA?aCK>1`_lH!kCahc(x-}%Ao%Rk{$~H?^&1~=2@FvzE)Q|2XKCC4
z{X^~0DAsDa<8^cB*Uq6|GY4zDat<h*ex)CA43$^A7{?RCrVO?^h4U}<Ea{`8d0H7j
z-VA~A?9g^~l;QoJY)_PhUk%XmR$*R4B|1!a(+d=CHX5-?u;L~~>)6;vGajg<wW;&o
z#yAGX@^Zk#6b5ZJIM}-}w;dbLHfj@SoPbL7I}J2UtVBbHt(@p}L-?1fX}yu*6JOAv
z%wfe$ict_Iay;QL>OuXBpZ|Jo>@g7g%;VVZf=Z$?jAisz@Z7_r|AH5&c37spKanBY
zc4(iNT35IJK$~S6&d_j{h85boL;EGPUZ){A{1TZGZI@|(miFi9fICjmaGvYiGqi7+
z-07{+dhaT&?>#Q0E3^-WXX#IA=+eGxr-V+042E$mEB~H)n!w2W$O`j?0E98F%gQ!G
zXbgRt)*(}`AzzYC@$#kVX9;N9lC{c7(_~V5S(+LtypS2a>vcjCwXxq;FbO*{XvJy6
zYxE5m+EiU=3YE#oq?rQikHz(l>RQo&iE_EdD~WX=O0}86=Xn_Kzz?EkVs#8JGmHUg
z*<vO;>8`Y*U7*=8IW$5o*#uh&0yaGetaRAz%0yV{?NlZCY`lSR!7!d!c5J<2q)Z!V
zm?-UlY_31cs%$2F(}ru@ms`&M+os%ZHmn%EhBDcg=JdGoL?a4UgyuXJs%&Ld?#ejr
zc96DK!cIeGD<(~2y<+obFwT+Pft|aF==&1GSYo4@igVFfbj~@a@SJrj&XN=HZt}y%
zTZq1g0+5LV5Ri#9{n9C?RiOh$0o$y3=mG`o)3x#574B%SpK#jblo|E23}%lvdvMia
zfLBphU7dEMryvo_-4If|WqR4LZOewUj%lk*1c+WUu)8Psu+d2vYu@%oU&Z2z=Jihd
z=8E00dugYOCC?s+drzO*uH}|87QepbS{~cC#DKz^S#%~>_zugY2!zxTFa>Wk0*tH)
zR6gZI3}RmJF)#cb6)gI&M0<ZD_`JIHS0)LL$&w9Xhp7QEnJrqmS=#H7DML;%Tc86x
zaDV~kXum?+pb2c>99=~4GEK}=rU)npw{WE6tcuv5rR>&}G#bwy()f0y(fgKqxA?aX
zy3yY;CblsR#=)#O^Oo(=utfJi=NU@W`;K~x{96Zu)oZ*ZnoryJ?8#0wy(mo#aDY<_
z3L%mP4poCm*rSViKymEpCA?k?@8a|Y9KCd)E5Lr&dofgyqZ+TNjjPW93u%}z{I&aQ
zPlGQW)F0a@*D}naw&6{$KY8@XU#r(2{PJPm&oQbE@a1#<vhnjc>r1PLqbRU#$8O<>
z*R@mme5A8jEL_5t5M|PgzO8&DwnO*3-ArmNbBf`r6;fi)+Q|)p4WBp1030<rFXTMK
zW_*Yjl`5ctqaXnOE;uLfb!QixGx#1WRnU79UrP;)P!4rV4ZlNyQEIP8jMd*TR*MAI
zW5jaz3=LM9sDa)we;kyY-(F_?!D+PTi3@;5g2@`3>Tr#^jUfTgbzG-@^>n>=jvU7U
zj<aw0cEy;sNW1@e?;AqrQ#?7sEEO#vm>*?|VZ|h^y|g*G5=_7~eI+OmgtNc<8K@FS
z#4Y0cO!i+{%w7rXGUGbYWTqQb-4V1c?-jE!r7>kKd)~-WX2mIMxxuChDB=d;+I?f|
z3YKL7lbSI05}b5EtZ<VRM#FS@1^6!G+JLa^ndNMmM5#a$wy^G-<{icC_t2i-nSr~U
zpkEAYyx~6IG5oW<+m=v~7=1>itz|M4{zcSsQH~^=gm-1uND*|LDo17n5u(;uEw<4n
z$abi6nEUVY7<k?c@$%s^1lgNFHEkNqXOWsgtJxQF8SjksGLqjZpuLRpxl+V^9JlPN
z#rb^{K!z=lr%izX{N6i^^VO}>%y0lDa1PLdUT>q5k49MPoT>r&9dI%3)dCz-<AERA
zeYlcy6gT)c@v`Bs2l<IW?jbXAS57g=rTLk`uHYNaQS4_2y!%Id?PZS~7b~&ooGguw
zMcf+%HBORtZ-YRjQ4si?w|qSLF)Wk*M}>r?*|oaillUQGt^4QE;J?o=4pTc?l;>st
z0=Is^FP_Na&BDyCj(>;6StkhWsVkUZ#g_ip;}H-2(@rY-vHaN?l=atmRZ0usL;RP^
iK*#^<-<>HtE)HXh&Uwqk=S%J}x8lCzo^|IJoc{piB!Za$


From d1439a029bbfb4ca50cde428046df496aa9a43d9 Mon Sep 17 00:00:00 2001
From: dan sinclair <dsinclair@chromium.org>
Date: Tue, 11 Aug 2020 15:52:10 -0400
Subject: [PATCH 7/7] enable tests

---
 tools/check_language_test.py | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/tools/check_language_test.py b/tools/check_language_test.py
index 3534dab1b..8f20791ad 100755
--- a/tools/check_language_test.py
+++ b/tools/check_language_test.py
@@ -33,7 +33,7 @@ def testMatches(self):
 			"white_hat", "greyhat", "grey-hat", "grey_hat", "grayhat",
 			"gray-hat", "gray_hat", "master", "slave", "him", "his", "she",
 			"her", "hers", "man", "woman", "he", "he'd", "he's", "he'll",
-			#"he\u2019d", "he\u2019s", "he\u2019ll",
+			"he\u2019d", "he\u2019s", "he\u2019ll",
 			"grandfather", "mitm", "crazy", "insane", "blind to",
 			"flying blind", "blind eye", "cripple", "crippled", "dumb",
 			"dummy", "paranoid", "sane", "sanity", "redline", "red-line",
@@ -41,8 +41,7 @@ def testMatches(self):
 
 		for word in tests:
 			self.assertTrue(
-				check_language.check_match("", "this is a " + word + " attempt"),
-				word)
+				check_language.check_match("", "this is a " + word + " attempt"), word)
 
 
 	def testSuppression(self):