charlotte 0.1.1 → 0.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: a44e734b24416c3ff9b2b0cc178d15e8d03417e3
-  data.tar.gz: 7dc568b7fbb302a23639b5c3f46a76967227a054
+  metadata.gz: ff389cc8403185a02af43180f937a237ba067359
+  data.tar.gz: ab349762b023a4456b4b04f4794d218bd06f9621
 SHA512:
-  metadata.gz: 5e2b740400db55f30e1623e14da783d2341a5b8593c07be0de86f296a54b0098d2e18ec3c202dcedb3a4ea39dd36a47060d3c51d69bef28c6f837ced01c7a3a0
-  data.tar.gz: cce9165998efa8f618648204e0880830f5fb8cdcee12f418cfb372fc04434277912c8d2efe2d0261f5ebadabcc897e53f1a526158c846fe4f314c8d806dfd5fd
+  metadata.gz: af29dbe4041a757db953f777c7abf1a9707b957e638ad6e59ebc92296ccdb9f55ba5715b5f6b1f2846e9d332b0e3b79a42d488d2c7783381273c8279db48a306
+  data.tar.gz: e681b2a4f956237a45dd13d5adbf0b302b301012bbc699d4d5ada118a09fc1278005f48e5542cfb20fc72a6e395fb177a796b1add128e570e1ba0bdedefb9364

data/bin/charlotte

@@ -1,2 +1,2 @@
 #!/usr/bin/env bash -x
-time ruby -r "charlotte" -e "ARGV.each{|arg| puts arg; puts File.binread(arg).detect_encoding; puts ''}" -- $(find "$@" -type f)
+time ruby -r "charlotte" -e "ARGV.each{|arg| puts arg; puts File.binread(arg).detect_encoding.to_s.gsub('ASCII-8BIT','BINARY'; puts ''}" -- $(find "$@" -type f)

data/test/other/chardet.sh

@@ -0,0 +1,2 @@
+#!/usr/bin/env bash -x
+time ruby -e "require 'rchardet'; ARGV.each{|arg| if File.file?(arg) && File.readable?(arg); puts arg; puts CharDet.detect(File.binread(arg)); puts ''; end}" $(find "$@" -type f)

data/test/other/charlock.sh

@@ -0,0 +1,2 @@
+#!/usr/bin/env bash -x
+time ruby -e "require 'charlock_holmes'; require 'charlock_holmes/string'; ARGV.each{|arg| if File.file?(arg) && File.readable?(arg); puts arg; puts File.binread(arg).detect_encoding; puts ''; end}" $(find "$@" -type f)

data/test/other/charlotte.sh

@@ -0,0 +1,2 @@
+#!/usr/bin/env bash -x
+time ruby -r "charlotte" -e "ARGV.each{|arg| puts arg; puts File.binread(arg).detect_encoding.to_s.gsub('ASCII-8BIT','BINARY'; puts ''}" -- $(find "$@" -type f)

data/test/samples/8-BIT-NON-ISO-EXTENDED

@@ -0,0 +1,45 @@
+#!/bin/sh
+
+# �ܡ���������
+
+#SET_PATH - This line is a placeholder to ease patching this script.
+
+# Instead of unsetting XZ_OPT, just make sure that xz will use file format
+# autodetection. This way memory usage limit and thread limit can be
+# specified via XZ_OPT.
+xz='xz --format=auto'
+
+version='xzless (XZ Utils) 5.1.4beta'
+
+usage="Usage: ${0##*/} [OPTION]... [FILE]...
+Like 'less', but operate on the uncompressed contents of xz compressed FILEs.
+
+Options are the same as for 'less'.
+
+Report bugs to <lasse.collin@tukaani.org>."
+
+case $1 in
+	--help)    echo "$usage" || exit 2; exit;;
+	--version) echo "$version" || exit 2; exit;;
+esac
+
+if test "${LESSMETACHARS+set}" != set; then
+	# Work around a bug in less 394 and earlier;
+	# it mishandles the metacharacters '$%=~'.
+	space=' '
+	tab='	'
+	nl='
+'
+	LESSMETACHARS="$space$tab$nl'"';*?"()<>[|&^`#\$%=~'
+fi
+
+if test "$(less -V | { read less ver re && echo ${ver}; })" -ge 429; then
+	# less 429 or later: LESSOPEN pipe will be used on
+	# standard input if $LESSOPEN begins with |-.
+	LESSOPEN="|-$xz -cdfq -- %s"
+else
+	LESSOPEN="|$xz -cdfq -- %s"
+fi
+export LESSMETACHARS LESSOPEN
+
+exec less "$@"

data/test/samples/ISO-8859-1

@@ -0,0 +1,43 @@
+#!/bin/sh �ܡ���
+
+#SET_PATH - This line is a placeholder to ease patching this script.
+
+# Instead of unsetting XZ_OPT, just make sure that xz will use file format
+# autodetection. This way memory usage limit and thread limit can be
+# specified via XZ_OPT.
+xz='xz --format=auto'
+
+version='xzless (XZ Utils) 5.1.4beta'
+
+usage="Usage: ${0##*/} [OPTION]... [FILE]...
+Like 'less', but operate on the uncompressed contents of xz compressed FILEs.
+
+Options are the same as for 'less'.
+
+Report bugs to <lasse.collin@tukaani.org>."
+
+case $1 in
+	--help)    echo "$usage" || exit 2; exit;;
+	--version) echo "$version" || exit 2; exit;;
+esac
+
+if test "${LESSMETACHARS+set}" != set; then
+	# Work around a bug in less 394 and earlier;
+	# it mishandles the metacharacters '$%=~'.
+	space=' '
+	tab='	'
+	nl='
+'
+	LESSMETACHARS="$space$tab$nl'"';*?"()<>[|&^`#\$%=~'
+fi
+
+if test "$(less -V | { read less ver re && echo ${ver}; })" -ge 429; then
+	# less 429 or later: LESSOPEN pipe will be used on
+	# standard input if $LESSOPEN begins with |-.
+	LESSOPEN="|-$xz -cdfq -- %s"
+else
+	LESSOPEN="|$xz -cdfq -- %s"
+fi
+export LESSMETACHARS LESSOPEN
+
+exec less "$@"

data/test/samples/MacRoman

@@ -0,0 +1,47 @@
+#!/bin/sh
+
+# The original version for gzip was written by Paul Eggert.
+# Modified for XZ Utils by Andrew Dudman and Lasse Collin.
+# �ܡ���
+
+#SET_PATH - This line is a placeholder to ease patching this script.
+
+# Instead of unsetting XZ_OPT, just make sure that xz will use file format
+# autodetection. This way memory usage limit and thread limit can be
+# specified via XZ_OPT.
+xz='xz --format=auto'
+
+version='xzless (XZ Utils) 5.1.4beta'
+
+usage="Usage: ${0##*/} [OPTION]... [FILE]...
+Like 'less', but operate on the uncompressed contents of xz compressed FILEs.
+
+Options are the same as for 'less'.
+
+Report bugs to <lasse.collin@tukaani.org>."
+
+case $1 in
+	--help)    echo "$usage" || exit 2; exit;;
+	--version) echo "$version" || exit 2; exit;;
+esac
+
+if test "${LESSMETACHARS+set}" != set; then
+	# Work around a bug in less 394 and earlier;
+	# it mishandles the metacharacters '$%=~'.
+	space=' '
+	tab='	'
+	nl='
+'
+	LESSMETACHARS="$space$tab$nl'"';*?"()<>[|&^`#\$%=~'
+fi
+
+if test "$(less -V | { read less ver re && echo ${ver}; })" -ge 429; then
+	# less 429 or later: LESSOPEN pipe will be used on
+	# standard input if $LESSOPEN begins with |-.
+	LESSOPEN="|-$xz -cdfq -- %s"
+else
+	LESSOPEN="|$xz -cdfq -- %s"
+fi
+export LESSMETACHARS LESSOPEN
+
+exec less "$@"

data/test/samples/UTF-8

@@ -0,0 +1,48 @@
+#!/bin/sh
+
+# Copyright (C) 1998, 2002, 2006, 2007 Free Software Foundation
+
+# ‚‹°›€‡ß
+
+
+#SET_PATH - This line is a placeholder to ease patching this script.
+
+# Instead of unsetting XZ_OPT, just make sure that xz will use file format
+# autodetection. This way memory usage limit and thread limit can be
+# specified via XZ_OPT.
+xz='xz --format=auto'
+
+version='xzless (XZ Utils) 5.1.4beta'
+
+usage="Usage: ${0##*/} [OPTION]... [FILE]...
+Like 'less', but operate on the uncompressed contents of xz compressed FILEs.
+
+Options are the same as for 'less'.
+
+Report bugs to <lasse.collin@tukaani.org>."
+
+case $1 in
+	--help)    echo "$usage" || exit 2; exit;;
+	--version) echo "$version" || exit 2; exit;;
+esac
+
+if test "${LESSMETACHARS+set}" != set; then
+	# Work around a bug in less 394 and earlier;
+	# it mishandles the metacharacters '$%=~'.
+	space=' '
+	tab='	'
+	nl='
+'
+	LESSMETACHARS="$space$tab$nl'"';*?"()<>[|&^`#\$%=~'
+fi
+
+if test "$(less -V | { read less ver re && echo ${ver}; })" -ge 429; then
+	# less 429 or later: LESSOPEN pipe will be used on
+	# standard input if $LESSOPEN begins with |-.
+	LESSOPEN="|-$xz -cdfq -- %s"
+else
+	LESSOPEN="|$xz -cdfq -- %s"
+fi
+export LESSMETACHARS LESSOPEN
+
+exec less "$@"

data/test/samples/UTF-8-WITH-BOM

@@ -0,0 +1,47 @@
+#!/bin/sh
+
+# The original version for gzip was written by Paul Eggert.
+# Modified for XZ Utils by Andrew Dudman and Lasse Collin.
+# ‚‹°›€‡ß
+
+#SET_PATH - This line is a placeholder to ease patching this script.
+
+# Instead of unsetting XZ_OPT, just make sure that xz will use file format
+# autodetection. This way memory usage limit and thread limit can be
+# specified via XZ_OPT.
+xz='xz --format=auto'
+
+version='xzless (XZ Utils) 5.1.4beta'
+
+usage="Usage: ${0##*/} [OPTION]... [FILE]...
+Like 'less', but operate on the uncompressed contents of xz compressed FILEs.
+
+Options are the same as for 'less'.
+
+Report bugs to <lasse.collin@tukaani.org>."
+
+case $1 in
+	--help)    echo "$usage" || exit 2; exit;;
+	--version) echo "$version" || exit 2; exit;;
+esac
+
+if test "${LESSMETACHARS+set}" != set; then
+	# Work around a bug in less 394 and earlier;
+	# it mishandles the metacharacters '$%=~'.
+	space=' '
+	tab='	'
+	nl='
+'
+	LESSMETACHARS="$space$tab$nl'"';*?"()<>[|&^`#\$%=~'
+fi
+
+if test "$(less -V | { read less ver re && echo ${ver}; })" -ge 429; then
+	# less 429 or later: LESSOPEN pipe will be used on
+	# standard input if $LESSOPEN begins with |-.
+	LESSOPEN="|-$xz -cdfq -- %s"
+else
+	LESSOPEN="|$xz -cdfq -- %s"
+fi
+export LESSMETACHARS LESSOPEN
+
+exec less "$@"

data/test/samples/utf-8-with-bom-file

@@ -0,0 +1,2 @@
+#!/bin/sh
+

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: charlotte
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.1.2
 platform: ruby
 authors:
 - Geoff Nixon
@@ -14,12 +14,31 @@ description: A simple (but fast!) character set encoding/binary detector and aut
   for common encodings (UTF-8/16/32, ISO-8859-1, MacRoman, etc.). Extends String with
   String.detect_encoding, String.autoencode.
 email: geoff@geoff.codes
-executables: []
+executables:
+- charlotte
 extensions: []
 extra_rdoc_files: []
 files:
 - bin/charlotte
 - lib/charlotte.rb
+- test/other/chardet.sh
+- test/other/charlock.sh
+- test/other/charlotte.sh
+- test/samples/8-BIT-NON-ISO-EXTENDED
+- test/samples/BINARY
+- test/samples/EMPTY
+- test/samples/ISO-8859-1
+- test/samples/MacRoman
+- test/samples/TEXT-WITH-BINARY
+- test/samples/UTF-16BE
+- test/samples/UTF-16LE
+- test/samples/UTF-32BE
+- test/samples/UTF-32LE
+- test/samples/UTF-8
+- test/samples/UTF-8-WITH-BOM
+- test/samples/utf-16be-file
+- test/samples/utf-16le-file
+- test/samples/utf-8-with-bom-file
 homepage: https://github.com/geoff-codes/charlotte
 licenses:
 - MIT