altprintf 0.3.0 → 0.3.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 30fe21097d8d96fc45f13bf03bc0c66c73cabd30e27d9a5829d33022e54d21fb
-  data.tar.gz: 2e3974374ac51f2f6750cdf48b660711ac9c4de60c14a9ba3c239a345cf9541d
+  metadata.gz: f63f172e7adfa43e47580f1c3372cbfb47b5ef09a019b75867ad2e22bbeb40df
+  data.tar.gz: 1ffef927437beb637f22e4a6661ceb07d328debf699a88fcc26154d13dd4b118
 SHA512:
-  metadata.gz: 5dfa57f474993381bd7c9c5704b09a867d02795abaa10f6fda6bc6a64a76b6c970bc80af41f225ef6dd98b610013b75eb2b101661dddea7e7407f06f3dc21bb2
-  data.tar.gz: 95b00d639a18eaccb25105c80129cab7f651c7f3cb5bcc0836177c06ad0170548e8abd6849e48efed84fca54c1750b411f5f736c87e4e1940488e41a1d5c5b67
+  metadata.gz: 99ff97d971d496a5696a54bbaf2b91ae382beb829977e50b01b53fa02d258d60f1ebe575fc237e1ec0026dc78aa7ca843c0493425f9e29d1f422c09f36b78c8b
+  data.tar.gz: a4ffaab4d5e5af7f0fa97cefb52783acbab60de1d98579ea8a6063be1f4b60c1d01cef532fa5fbefe4ddfd04a1587120cee8dbad782722d0dfb99ab77989396a

data/altprintf.gemspec

@@ -1,26 +1,27 @@
 require 'date'
 require_relative 'lib/altprintf/version'
 
-Altprintf::SPEC = Gem::Specification.new do |s|
-  s.name          = 'altprintf'
-  s.version       = Altprintf::VERSION.join('.')
-  s.date          = Date.today.strftime('%Y-%m-%d')
-  s.summary       = 'A powerful printf-like template language'
-  s.authors       = ['Stone Tickle']
-  s.email         = 'lattis@mochiro.moe'
-  s.homepage      = 'https://github.com/annacrombie/altprintf/tree/master/gem'
-  s.license       = 'MIT'
+module Altprintf
+  SPEC ||=
+    Gem::Specification.new do |s|
+      s.name          = 'altprintf'
+      s.version       = ::Altprintf::VERSION.join('.')
+      s.date          = Date.today.strftime('%Y-%m-%d')
+      s.summary       = 'A powerful printf-like template language'
+      s.authors       = ['Stone Tickle']
+      s.email         = 'lattis@mochiro.moe'
+      s.homepage      = 'https://github.com/annacrombie/altprintf/tree/master/gem'
+      s.license       = 'MIT'
 
-  s.files         = Dir['{**/*}'] - ['Rakefile']
+      s.files         = Dir['{**/*}']
+      s.extensions    = Dir["ext/**/extconf.rb"]
+      s.require_paths = ['lib']
 
-  s.platform = Gem::Platform::RUBY
-  s.extensions = Dir["ext/**/extconf.rb"]
-  s.require_paths = ['lib']
-
-  s.required_ruby_version = '>= 2.5.7'
-
-  s.add_development_dependency 'benchmark-ips', '~> 2.7'
-  s.add_development_dependency 'rake-compiler', '~> 1.0'
-  s.add_development_dependency 'rake', '~> 12.3'
-  s.add_development_dependency 'rspec', '~> 3.9'
-end unless Altprintf.const_defined?(:'SPEC')
+      s.platform = Gem::Platform::RUBY
+      s.required_ruby_version = '>= 2.5.7'
+      s.add_development_dependency 'benchmark-ips', '~> 2.7'
+      s.add_development_dependency 'rake-compiler', '~> 1.0'
+      s.add_development_dependency 'rake', '~> 12.3'
+      s.add_development_dependency 'rspec', '~> 3.9'
+    end
+end

data/ext/altprintf/cwidth.c

@@ -0,0 +1,277 @@
+/*
+ * This is an implementation of wcwidth() and wcswidth() (defined in
+ * IEEE Std 1002.1-2001) for Unicode.
+ *
+ * http://www.opengroup.org/onlinepubs/007904975/functions/wcwidth.html
+ * http://www.opengroup.org/onlinepubs/007904975/functions/wcswidth.html
+ *
+ * In fixed-width output devices, Latin characters all occupy a single
+ * "cell" position of equal width, whereas ideographic CJK characters
+ * occupy two such cells. Interoperability between terminal-line
+ * applications and (teletype-style) character terminals using the
+ * UTF-8 encoding requires agreement on which character should advance
+ * the cursor by how many cell positions. No established formal
+ * standards exist at present on which Unicode character shall occupy
+ * how many cell positions on character terminals. These routines are
+ * a first attempt of defining such behavior based on simple rules
+ * applied to data provided by the Unicode Consortium.
+ *
+ * For some graphical characters, the Unicode standard explicitly
+ * defines a character-cell width via the definition of the East Asian
+ * FullWidth (F), Wide (W), Half-width (H), and Narrow (Na) classes.
+ * In all these cases, there is no ambiguity about which width a
+ * terminal shall use. For characters in the East Asian Ambiguous (A)
+ * class, the width choice depends purely on a preference of backward
+ * compatibility with either historic CJK or Western practice.
+ * Choosing single-width for these characters is easy to justify as
+ * the appropriate long-term solution, as the CJK practice of
+ * displaying these characters as double-width comes from historic
+ * implementation simplicity (8-bit encoded characters were displayed
+ * single-width and 16-bit ones double-width, even for Greek,
+ * Cyrillic, etc.) and not any typographic considerations.
+ *
+ * Much less clear is the choice of width for the Not East Asian
+ * (Neutral) class. Existing practice does not dictate a width for any
+ * of these characters. It would nevertheless make sense
+ * typographically to allocate two character cells to characters such
+ * as for instance EM SPACE or VOLUME INTEGRAL, which cannot be
+ * represented adequately with a single-width glyph. The following
+ * routines at present merely assign a single-cell width to all
+ * neutral characters, in the interest of simplicity. This is not
+ * entirely satisfactory and should be reconsidered before
+ * establishing a formal standard in this area. At the moment, the
+ * decision which Not East Asian (Neutral) characters should be
+ * represented by double-width glyphs cannot yet be answered by
+ * applying a simple rule from the Unicode database content. Setting
+ * up a proper standard for the behavior of UTF-8 character terminals
+ * will require a careful analysis not only of each Unicode character,
+ * but also of each presentation form, something the author of these
+ * routines has avoided to do so far.
+ *
+ * http://www.unicode.org/unicode/reports/tr11/
+ *
+ * Markus Kuhn -- 2007-05-26 (Unicode 5.0)
+ *
+ * Permission to use, copy, modify, and distribute this software
+ * for any purpose and without fee is hereby granted. The author
+ * disclaims all warranties with regard to this software.
+ *
+ * Latest version: http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c
+ *
+ * ---
+ *
+ * Stone Tickle -- 2019 - 10 - 16
+ *
+ *
+ * Removal of *_cjk functions
+ * Functions altered to take long codepoint rather than wchar_t
+ * Function added to convert utf8 string to codepoint
+ * Functions added to get width of utf8 strings / chars
+ */
+
+#include <string.h>
+#include <stdlib.h>
+
+struct interval {
+	int first;
+	int last;
+};
+
+/* auxiliary function for binary search in interval table */
+static int bisearch(long ucs, const struct interval *table, int max)
+{
+	int min = 0;
+	int mid;
+
+	if (ucs < table[0].first || ucs > table[max].last)
+		return 0;
+	while (max >= min) {
+		mid = (min + max) / 2;
+		if (ucs > table[mid].last)
+			min = mid + 1;
+		else if (ucs < table[mid].first)
+			max = mid - 1;
+		else
+			return 1;
+	}
+
+	return 0;
+}
+
+
+/* The following two functions define the column width of an ISO 10646
+ * character as follows:
+ *
+ *    - The null character (U+0000) has a column width of 0.
+ *
+ *    - Other C0/C1 control characters and DEL will lead to a return
+ *      value of -1.
+ *
+ *    - Non-spacing and enclosing combining characters (general
+ *      category code Mn or Me in the Unicode database) have a
+ *      column width of 0.
+ *
+ *    - SOFT HYPHEN (U+00AD) has a column width of 1.
+ *
+ *    - Other format characters (general category code Cf in the Unicode
+ *      database) and ZERO WIDTH SPACE (U+200B) have a column width of 0.
+ *
+ *    - Hangul Jamo medial vowels and final consonants (U+1160-U+11FF)
+ *      have a column width of 0.
+ *
+ *    - Spacing characters in the East Asian Wide (W) or East Asian
+ *      Full-width (F) category as defined in Unicode Technical
+ *      Report #11 have a column width of 2.
+ *
+ *    - All remaining characters (including all printable
+ *      ISO 8859-1 and WGL4 characters, Unicode control characters,
+ *      etc.) have a column width of 1.
+ *
+ * This implementation assumes that wchar_t characters are encoded
+ * in ISO 10646.
+ */
+
+static int cpwidth(long ucs)
+{
+	/* sorted list of non-overlapping intervals of non-spacing characters */
+	/* generated by "uniset +cat=Me +cat=Mn +cat=Cf -00AD +1160-11FF +200B c" */
+	static const struct interval combining[] = {
+		{ 0x0300, 0x036F }, { 0x0483, 0x0486 }, { 0x0488, 0x0489 },
+		{ 0x0591, 0x05BD }, { 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 },
+		{ 0x05C4, 0x05C5 }, { 0x05C7, 0x05C7 }, { 0x0600, 0x0603 },
+		{ 0x0610, 0x0615 }, { 0x064B, 0x065E }, { 0x0670, 0x0670 },
+		{ 0x06D6, 0x06E4 }, { 0x06E7, 0x06E8 }, { 0x06EA, 0x06ED },
+		{ 0x070F, 0x070F }, { 0x0711, 0x0711 }, { 0x0730, 0x074A },
+		{ 0x07A6, 0x07B0 }, { 0x07EB, 0x07F3 }, { 0x0901, 0x0902 },
+		{ 0x093C, 0x093C }, { 0x0941, 0x0948 }, { 0x094D, 0x094D },
+		{ 0x0951, 0x0954 }, { 0x0962, 0x0963 }, { 0x0981, 0x0981 },
+		{ 0x09BC, 0x09BC }, { 0x09C1, 0x09C4 }, { 0x09CD, 0x09CD },
+		{ 0x09E2, 0x09E3 }, { 0x0A01, 0x0A02 }, { 0x0A3C, 0x0A3C },
+		{ 0x0A41, 0x0A42 }, { 0x0A47, 0x0A48 }, { 0x0A4B, 0x0A4D },
+		{ 0x0A70, 0x0A71 }, { 0x0A81, 0x0A82 }, { 0x0ABC, 0x0ABC },
+		{ 0x0AC1, 0x0AC5 }, { 0x0AC7, 0x0AC8 }, { 0x0ACD, 0x0ACD },
+		{ 0x0AE2, 0x0AE3 }, { 0x0B01, 0x0B01 }, { 0x0B3C, 0x0B3C },
+		{ 0x0B3F, 0x0B3F }, { 0x0B41, 0x0B43 }, { 0x0B4D, 0x0B4D },
+		{ 0x0B56, 0x0B56 }, { 0x0B82, 0x0B82 }, { 0x0BC0, 0x0BC0 },
+		{ 0x0BCD, 0x0BCD }, { 0x0C3E, 0x0C40 }, { 0x0C46, 0x0C48 },
+		{ 0x0C4A, 0x0C4D }, { 0x0C55, 0x0C56 }, { 0x0CBC, 0x0CBC },
+		{ 0x0CBF, 0x0CBF }, { 0x0CC6, 0x0CC6 }, { 0x0CCC, 0x0CCD },
+		{ 0x0CE2, 0x0CE3 }, { 0x0D41, 0x0D43 }, { 0x0D4D, 0x0D4D },
+		{ 0x0DCA, 0x0DCA }, { 0x0DD2, 0x0DD4 }, { 0x0DD6, 0x0DD6 },
+		{ 0x0E31, 0x0E31 }, { 0x0E34, 0x0E3A }, { 0x0E47, 0x0E4E },
+		{ 0x0EB1, 0x0EB1 }, { 0x0EB4, 0x0EB9 }, { 0x0EBB, 0x0EBC },
+		{ 0x0EC8, 0x0ECD }, { 0x0F18, 0x0F19 }, { 0x0F35, 0x0F35 },
+		{ 0x0F37, 0x0F37 }, { 0x0F39, 0x0F39 }, { 0x0F71, 0x0F7E },
+		{ 0x0F80, 0x0F84 }, { 0x0F86, 0x0F87 }, { 0x0F90, 0x0F97 },
+		{ 0x0F99, 0x0FBC }, { 0x0FC6, 0x0FC6 }, { 0x102D, 0x1030 },
+		{ 0x1032, 0x1032 }, { 0x1036, 0x1037 }, { 0x1039, 0x1039 },
+		{ 0x1058, 0x1059 }, { 0x1160, 0x11FF }, { 0x135F, 0x135F },
+		{ 0x1712, 0x1714 }, { 0x1732, 0x1734 }, { 0x1752, 0x1753 },
+		{ 0x1772, 0x1773 }, { 0x17B4, 0x17B5 }, { 0x17B7, 0x17BD },
+		{ 0x17C6, 0x17C6 }, { 0x17C9, 0x17D3 }, { 0x17DD, 0x17DD },
+		{ 0x180B, 0x180D }, { 0x18A9, 0x18A9 }, { 0x1920, 0x1922 },
+		{ 0x1927, 0x1928 }, { 0x1932, 0x1932 }, { 0x1939, 0x193B },
+		{ 0x1A17, 0x1A18 }, { 0x1B00, 0x1B03 }, { 0x1B34, 0x1B34 },
+		{ 0x1B36, 0x1B3A }, { 0x1B3C, 0x1B3C }, { 0x1B42, 0x1B42 },
+		{ 0x1B6B, 0x1B73 }, { 0x1DC0, 0x1DCA }, { 0x1DFE, 0x1DFF },
+		{ 0x200B, 0x200F }, { 0x202A, 0x202E }, { 0x2060, 0x2063 },
+		{ 0x206A, 0x206F }, { 0x20D0, 0x20EF }, { 0x302A, 0x302F },
+		{ 0x3099, 0x309A }, { 0xA806, 0xA806 }, { 0xA80B, 0xA80B },
+		{ 0xA825, 0xA826 }, { 0xFB1E, 0xFB1E }, { 0xFE00, 0xFE0F },
+		{ 0xFE20, 0xFE23 }, { 0xFEFF, 0xFEFF }, { 0xFFF9, 0xFFFB },
+		{ 0x10A01, 0x10A03 }, { 0x10A05, 0x10A06 }, { 0x10A0C, 0x10A0F },
+		{ 0x10A38, 0x10A3A }, { 0x10A3F, 0x10A3F }, { 0x1D167, 0x1D169 },
+		{ 0x1D173, 0x1D182 }, { 0x1D185, 0x1D18B }, { 0x1D1AA, 0x1D1AD },
+		{ 0x1D242, 0x1D244 }, { 0xE0001, 0xE0001 }, { 0xE0020, 0xE007F },
+		{ 0xE0100, 0xE01EF }
+	};
+
+	/* test for 8-bit control characters */
+	if (ucs == 0)
+		return 0;
+	if (ucs < 32 || (ucs >= 0x7f && ucs < 0xa0))
+		return -1;
+
+	/* binary search in table of non-spacing characters */
+	if (bisearch(ucs, combining,
+		     sizeof(combining) / sizeof(struct interval) - 1))
+		return 0;
+
+	/* if we arrive here, ucs is not a combining or C0/C1 control character */
+
+	return 1 +
+	       (ucs >= 0x1100 &&
+		(ucs <= 0x115f ||         /* Hangul Jamo init. consonants */
+		 ucs == 0x2329 || ucs == 0x232a ||
+		 (ucs >= 0x2e80 && ucs <= 0xa4cf &&
+		  ucs != 0x303f) ||     /* CJK ... Yi */
+		 (ucs >= 0xac00 && ucs <= 0xd7a3) || /* Hangul Syllables */
+		 (ucs >= 0xf900 && ucs <= 0xfaff) || /* CJK Compatibility Ideographs */
+		 (ucs >= 0xfe10 && ucs <= 0xfe19) || /* Vertical forms */
+		 (ucs >= 0xfe30 && ucs <= 0xfe6f) || /* CJK Compatibility Forms */
+		 (ucs >= 0xff00 && ucs <= 0xff60) || /* Fullwidth Forms */
+		 (ucs >= 0xffe0 && ucs <= 0xffe6) ||
+		 (ucs >= 0x20000 && ucs <= 0x2fffd) ||
+		 (ucs >= 0x30000 && ucs <= 0x3fffd)));
+}
+
+static int codepoint(const char *utf8, long *res)
+{
+	int bytes, i;
+	unsigned char c;
+	unsigned long cp;
+
+	bytes = 0;
+	c = utf8[0];
+
+	if ((c & 0x7f) == c) {
+		cp = c & 0x7f;
+		bytes = 0;
+	} else if ((c & 0xdf) == c) {
+		cp = c & 0x1f;
+		bytes = 1;
+	} else if ((c & 0xef) == c) {
+		cp = c & 0x0f;
+		bytes = 2;
+	} else if ((c & 0xf7) == c) {
+		cp = c & 0x07;
+		bytes = 3;
+	} else {
+		return 0;
+	}
+
+	for (i = 0; i < bytes; i++) {
+		cp <<= 6;
+		cp |= ((unsigned char)utf8[i + 1] & 0x3f);
+	}
+
+	*res = cp;
+	return bytes + 1;
+}
+
+int cwidth(const char* utf8)
+{
+	long cp;
+
+	codepoint(utf8, &cp);
+	return cpwidth(cp);
+}
+
+int cswidth(const char *utf8, size_t maxlen)
+{
+	int w = 0;
+	long cp;
+	size_t i, len;
+
+	len = strlen(utf8);
+
+	for (i = 0; i < len;) {
+		i += codepoint(&utf8[i], &cp);
+		w += cpwidth(cp);
+
+		if (i > maxlen)
+			break;
+	}
+
+	return w;
+}

data/ext/altprintf/extconf.rb

@@ -0,0 +1,4 @@
+#!/usr/bin/env ruby
+
+require_relative 'extconf_helper'
+ExtconfHelper.setup

data/ext/altprintf/extconf_helper.rb

@@ -33,6 +33,6 @@ module ExtconfHelper
     end
 
     create_header
-    create_makefile('altprintf')
+    create_makefile('altprintf/altprintf')
   end
 end

data/lib/altprintf/version.rb

@@ -1,3 +1,3 @@
 module Altprintf
-  VERSION = [0, 3, 0]
+  VERSION ||= [0, 3, 1]
 end

data/readme.md

@@ -14,3 +14,33 @@ argument is accepted:
 
 + `<val>` - access the value of the given hash with key `val` rather than
   try to read the next argument.
+
+## Setup
+
+``sh
+$ bundle install
+``
+
+## Compiling
+
+First, you must build `libaltprintf` with the build directory set to `build`.
+
+Then,
+
+```sh
+$ rake compile
+```
+
+## Running tests
+
+Note: You must also have built the cli.
+
+```sh
+$ rspec
+```
+
+## Building the gem
+
+```sh
+$ rake gem:build
+```

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: altprintf
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 0.3.1
 platform: ruby
 authors:
 - Stone Tickle
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-10-19 00:00:00.000000000 Z
+date: 2019-10-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: benchmark-ips
@@ -69,7 +69,8 @@ dependencies:
 description: 
 email: lattis@mochiro.moe
 executables: []
-extensions: []
+extensions:
+- ext/altprintf/extconf.rb
 extra_rdoc_files: []
 files:
 - altprintf.gemspec
@@ -82,16 +83,16 @@ files:
 - ext/altprintf/altprintf/parsef.h
 - ext/altprintf/altprintf/strbuf.h
 - ext/altprintf/altprintf/syntax.h
+- ext/altprintf/cwidth.c
 - ext/altprintf/ext.c
 - ext/altprintf/extconf.h
+- ext/altprintf/extconf.rb
 - ext/altprintf/extconf_helper.rb
 - ext/altprintf/fmt.c
 - ext/altprintf/fmte.c
 - ext/altprintf/parsef.c
 - ext/altprintf/strbuf.c
 - lib/altprintf.rb
-- lib/altprintf/alt_printf.so
-- lib/altprintf/altprintf.so
 - lib/altprintf/version.rb
 - readme.md
 homepage: https://github.com/annacrombie/altprintf/tree/master/gem