cjk_auto_space 1.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 46f97e06e96ab1a04cb91ef23adac2300581af29d99b40485e98dd5059d6ba9b
+  data.tar.gz: 9a0d0d19b838185be702124b44c2f3a3c4a26a75036daf5195e3a6e96182d3ff
+SHA512:
+  metadata.gz: f60f7c271f76cffa17ddfa7b213303ed5de88b699e891978372c27d181ef610f68443d2352692c8bb78a22826e00a3a9f6903261bf9c941094cdc05af7b79ad2
+  data.tar.gz: 3004cea02af4e227af18a0c7be436e844f638e49f80f6f156b2c7d799604c4c6f105540e69f99a3dceab01311cea69643d3c2f8ef48f38627f4c2aa79f882ec1

data/README.md

@@ -0,0 +1,8 @@
+rubygem-cjk_auto_space
+------
+
+A rubygem that automatically add sapce(U+0020) between CJK and other unicode code points, for better reading experience, with Markdown syntax concerned.
+
+Usage:
+
+  "你好world哈哈".cjk_auto_space // => "你好 world 哈哈"

data/Rakefile

@@ -0,0 +1,13 @@
+require "rake/extensiontask"
+require "rake/testtask"
+
+Rake::ExtensionTask.new "cjk_auto_space" do |ext|
+  ext.lib_dir = "lib/cjk_auto_space"
+end
+
+Rake::TestTask.new do |t|
+  t.libs << "test"
+end
+
+desc "Run tests"
+task default::test

data/ext/cjk_auto_space/cjk_auto_space.c

@@ -0,0 +1,177 @@
+/*
+gcc ./cjkpad.c -o cjkpad `pkg-config --libs --cflags icu-uc icu-io`
+*/
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unicode/utext.h>
+/*#include <unicode/ustdio.h>*/
+#include "ruby.h"
+#include "extconf.h"
+
+static UErrorCode err = U_ZERO_ERROR;
+
+UBool u_iscjk(int ublock);
+
+typedef struct gra {
+  UChar32 cp; // code point
+  UBlockCode block; // unicode block
+  size_t start; // starting pos at the str[]
+  size_t length; // number of char needed (cjk is mostly 3 char)
+  bool cjk;
+} gra;
+
+UBool u_isMarkdown(gra* g, bool prefix);
+
+char* padCjk(const char* str) {
+    char* formatted = calloc(1024, sizeof(char));
+
+    gra* graphemes = malloc(1024 * sizeof(gra));
+    int graLen; // number of graphemes
+
+    UText *ut = utext_openUTF8(NULL, str, -1, &err);
+
+    int begin = 0;
+    int end;
+    int i = 0;
+    int blk;
+    int filled = 0;
+
+    for (UChar32 cp = utext_next32From(ut, 0);
+         cp > -1;
+         cp = utext_next32(ut), i++) {
+      end = utext_getNativeIndex(ut);
+      graphemes[i].cp = cp;
+      blk = ublock_getCode(cp);
+      graphemes[i].block = blk;
+      graphemes[i].start = begin;
+      graphemes[i].length = end - begin;
+      graphemes[i].cjk = u_iscjk(blk);
+
+      begin = end;
+    }
+
+    graLen = i;
+
+    filled += graphemes[0].length;
+    strncat(formatted, &str[graphemes[0].start], graphemes[0].length);
+
+    for (int j = 1; j <= graLen; j++) {
+      gra *prev = &graphemes[j-1];
+      gra *curr = &graphemes[j];
+      gra *next = &graphemes[j+1];
+
+      //u_printf("%C%C%C\n", prev->cp, curr->cp, next->cp);
+
+      if ((u_isMarkdown(curr, true) && !prev->cjk && !u_isspace(prev->cp) && next->cjk) || // d*哈
+         (!prev->cjk && !u_isspace(prev->cp) && !u_isMarkdown(prev, true) && curr->cjk) || // *哈
+         (!curr->cjk && !u_isspace(curr->cp) && !u_isMarkdown(curr, false) && prev->cjk)) { // 哈*
+        filled++;
+        if (filled == strlen(formatted)-1) {
+          formatted = realloc(formatted, strlen(formatted) * 2 * sizeof(char));
+        }
+        strcat(formatted, " ");
+      }
+      filled += curr->length;
+      if (filled == strlen(formatted)-1) {
+        formatted = realloc(formatted, strlen(formatted) * 2 * sizeof(char));
+      }
+      strncat(formatted, &str[curr->start], curr->length);
+
+      if (u_isMarkdown(curr, false) && prev->cjk && !u_isspace(next->cp) && !next->cjk) { // 哈*n
+        filled++;
+        if (filled == strlen(formatted)-1) {
+          formatted = realloc(formatted, strlen(formatted) * 2 * sizeof(char));
+        }
+        strcat(formatted, " ");
+      }
+    }
+
+    //printf("\n%s\n", formatted);
+    free(graphemes);
+
+    return formatted;
+}
+
+UBool u_isMarkdown(gra* g, bool prefix) {
+  UBool markdown;
+
+  switch (g->cp) {
+  case 0x005F: // _
+  case 0x002A: // *
+  case 0x0060: // `
+    markdown = 1;
+    break;
+  case 0x003E:
+  case 0x005B:
+    if (prefix) {
+      markdown = 1;
+      break;
+    }
+  case 0x005D:
+    if (!prefix) {
+      markdown = 1;
+      break;
+    }
+  default:
+    markdown = 0;
+    break;
+  };
+  return markdown;
+}
+
+UBool u_iscjk(int ublock) {
+  UBool cjk;
+
+  switch (ublock) {
+  case UBLOCK_CJK_UNIFIED_IDEOGRAPHS:
+  case UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A:
+  case UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B:
+  case UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C:
+  case UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D:
+  case UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E:
+  case UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F:
+  case UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G:
+  case UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H:
+  case UBLOCK_CJK_RADICALS_SUPPLEMENT:
+  case UBLOCK_CJK_SYMBOLS_AND_PUNCTUATION:
+  case UBLOCK_HIRAGANA:
+  case UBLOCK_KATAKANA:
+  case UBLOCK_BOPOMOFO:
+  case UBLOCK_BOPOMOFO_EXTENDED:
+  case UBLOCK_KANBUN:
+  case UBLOCK_CJK_STROKES:
+  case UBLOCK_KATAKANA_PHONETIC_EXTENSIONS:
+  case UBLOCK_ENCLOSED_CJK_LETTERS_AND_MONTHS:
+  case UBLOCK_CJK_COMPATIBILITY:
+  case UBLOCK_HANGUL_JAMO:
+  case UBLOCK_HANGUL_COMPATIBILITY_JAMO:
+  case UBLOCK_HANGUL_JAMO_EXTENDED_A:
+  case UBLOCK_HANGUL_SYLLABLES:
+  case UBLOCK_HANGUL_JAMO_EXTENDED_B:
+  case UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS:
+  case UBLOCK_CJK_COMPATIBILITY_FORMS:
+  case UBLOCK_KANA_EXTENDED_B:
+  case UBLOCK_KANA_SUPPLEMENT:
+  case UBLOCK_KANA_EXTENDED_A:
+  case UBLOCK_SMALL_KANA_EXTENSION:
+    cjk = 1;
+    break;
+  default:
+    cjk = 0;
+    break;
+  };
+  return cjk;
+}
+
+static VALUE rb_pad_cjk(VALUE self) {
+  Check_Type(self, T_STRING);
+
+  char* in = StringValueCStr(self);
+  char* out = padCjk(in);
+  return rb_str_new_cstr(out);
+}
+
+void Init_cjk_auto_space(void) {
+  rb_define_method(rb_cString, "cjk_auto_space", rb_pad_cjk, 0);
+}

data/ext/cjk_auto_space/extconf.rb

@@ -0,0 +1,10 @@
+require 'mkmf'
+
+dir_config("/usr/lib64", "/usr/lib", "/usr/include/unicode")
+
+abort("missing \"unicode/utext.h\"") unless find_header("unicode/utext.h")
+find_library("icuuc", "utext_openUTF8", "/usr/lib64", "/usr/lib")
+abort("missing \"utext_openUTF8\"") unless have_library("icuuc", "utext_openUTF8", "unicode/utext.h")
+
+create_header
+create_makefile 'cjk_auto_space/cjk_auto_space'

data/lib/cjk_auto_space.rb

@@ -0,0 +1,12 @@
+begin
+  ruby_version = /(\d+\.\d+)/.match(::RUBY_VERSION)
+  require_relative "cjk_auto_space/#{ruby_version}/cjk_auto_space"
+rescue LoadError
+  require "cjk_auto_space/cjk_auto_space"
+end
+
+String.class_eval do
+  def cjk_auto_space!
+    sub!(self, self.cjk_auto_space)
+  end
+end

metadata

@@ -0,0 +1,52 @@
+--- !ruby/object:Gem::Specification
+name: cjk_auto_space
+version: !ruby/object:Gem::Version
+  version: 1.0.0
+platform: ruby
+authors:
+- Marguerite Su
+- Shenlebantongying
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2023-01-22 00:00:00.000000000 Z
+dependencies: []
+description: A rubygem that automatically add sapce(U+0020) between CJK and other
+  unicode code points, for better reading experience, with Markdown syntax concerned.
+email:
+- marguerite@opensuse.org
+- shenlebantongying@gmail.com
+executables: []
+extensions:
+- ext/cjk_auto_space/extconf.rb
+extra_rdoc_files: []
+files:
+- README.md
+- Rakefile
+- ext/cjk_auto_space/cjk_auto_space.c
+- ext/cjk_auto_space/extconf.rb
+- lib/cjk_auto_space.rb
+homepage: https://github.com/openSUSE-zh/rubygem-cjk_auto_space
+licenses:
+- MIT
+metadata: {}
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.4.1
+signing_key:
+specification_version: 4
+summary: Automatically add spacing between CJK and others with MarkDown syntax concerned
+test_files: []