[pushed,gdb/contrib] Add words.sh script

Message ID 20191107095107.B0E4225B28@gnutoolchain-gerrit.osci.io
State Superseded
Headers show
Series
  • [pushed,gdb/contrib] Add words.sh script
Related show

Commit Message

Sourceware to Gerrit sync (Code Review) Nov. 7, 2019, 9:51 a.m.
The original change was created by Tom de Vries.

Change URL: https://gnutoolchain-gerrit.osci.io/r/c/binutils-gdb/+/282
......................................................................

[gdb/contrib] Add words.sh script

Add a script that takes a list of files as arguments and output a list of
words from the C comments with their frequencies.

For:
...
$ ./gdb/contrib/words.sh $(find gdb -type f -name "*.c" -o -name "*.h")
...
it generates a list of ~15000 words prefixed with frequency.

This could be used to generate a dictionary that is kept as part of the
sources, against which new code can be checked, generating a warning or
error.  The hope is that misspellings would trigger this frequently, and rare
words rarely, otherwise the burden of updating the dictionary would be too
much.

And for:
...
$ ./gdb/contrib/words.sh -f 1 $(find gdb -type f -name "*.c" -o -name "*.h")
...
it generates a list of ~5000 words with frequency 1.

This can be used to scan for misspellings manually.

Change-Id: I7b119c9a4519cdbf62a3243d1df2927c80813e8b
---
A gdb/contrib/words.sh
1 file changed, 129 insertions(+), 0 deletions(-)




-- 
Gerrit-Project: binutils-gdb
Gerrit-Branch: master
Gerrit-Change-Id: I7b119c9a4519cdbf62a3243d1df2927c80813e8b
Gerrit-Change-Number: 282
Gerrit-PatchSet: 3
Gerrit-Owner: Tom de Vries <tdevries@suse.de>
Gerrit-Reviewer: Luis Machado <luis.machado@linaro.org>
Gerrit-Reviewer: Tom Tromey <tromey@sourceware.org>
Gerrit-Reviewer: Tom de Vries <tdevries@suse.de>
Gerrit-CC: Simon Marchi <simon.marchi@polymtl.ca>
Gerrit-MessageType: newpatchset

Patch

diff --git a/gdb/contrib/words.sh b/gdb/contrib/words.sh
new file mode 100755
index 0000000..ae38539
--- /dev/null
+++ b/gdb/contrib/words.sh
@@ -0,0 +1,129 @@ 
+#!/bin/sh
+
+# Copyright (C) 2019 Free Software Foundation, Inc.
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+# This script intends to facilitate spell checking of comments in C sources.
+# It:
+# - extracts comments from C files
+# - transforms the comments into a list of lowercase words
+# - prefixes each word with the frequency
+# - filters out words within a frequency range
+# - sorts the words, longest first
+#
+# For:
+# ...
+# $ ./gdb/contrib/words.sh $(find gdb -type f -name "*.c" -o -name "*.h")
+# ...
+# it generates a list of ~15000 words prefixed with frequency.
+#
+# This could be used to generate a dictionary that is kept as part of the
+# sources, against which new code can be checked, generating a warning or
+# error.  The hope is that misspellings would trigger this frequently, and rare
+# words rarely, otherwise the burden of updating the dictionary would be too
+# much.
+#
+# And for:
+# ...
+# $ ./gdb/contrib/words.sh -f 1 $(find gdb -type f -name "*.c" -o -name "*.h")
+# ...
+# it generates a list of ~5000 words with frequency 1.
+#
+# This can be used to scan for misspellings manually.
+#
+
+minfreq=
+maxfreq=
+while [ $# -gt 0 ]; do
+    case "$1" in
+	--freq|-f)
+	    minfreq=$2
+	    maxfreq=$2
+	    shift 2
+	    ;;
+	--min)
+	    minfreq=$2
+	    if [ "$maxfreq" = "" ]; then
+		maxfreq=0
+	    fi
+	    shift 2
+	    ;;
+	--max)
+	    maxfreq=$2
+	    if [ "$minfreq" = "" ]; then
+		minfreq=0
+	    fi
+	    shift 2
+	    ;;
+	*)
+	    break;
+	    ;;
+    esac
+done
+
+if [ "$minfreq" = "" ] && [ "$maxfreq" = "" ]; then
+    minfreq=0
+    maxfreq=0
+fi
+
+awkfile=$(mktemp)
+trap 'rm -f "$awkfile"' EXIT
+
+cat > "$awkfile" <<EOF
+BEGIN {
+    in_comment=0
+}
+
+// {
+    line=\$0
+}
+
+/\/\*/ {
+    in_comment=1
+    sub(/.*\/\*/, "", line)
+}
+
+/\*\// {
+    sub(/\*\/.*/, "", line)
+    in_comment=0
+    print line
+    next
+}
+
+// {
+    if (in_comment) {
+	print line
+    }
+}
+EOF
+
+# Stabilize sort.
+export LC_ALL=C
+
+awk \
+    -f "$awkfile" \
+    -- "$@" \
+    | sed 's/[%^$~#{}`&=@,. \t\/_()|<>\+\*-]/\n/g' \
+    | sed 's/\[/\n/g' \
+    | sed 's/\]/\n/g' \
+    | sed 's/[0-9][0-9]*/\n/g' \
+    | tr '[:upper:]' '[:lower:]' \
+    | sed 's/[ \t]*//g' \
+    | sort \
+    | uniq -c \
+    | awk "{ if (($minfreq == 0 || $minfreq <= \$1) \
+                 && ($maxfreq == 0 || \$1 <= $maxfreq)) { print \$0; } }" \
+    | awk '{ print length($0) " " $0; }' \
+    | sort -n -r \
+    | cut -d ' ' -f 2-