bug#34215: 27.0.50; Provide elisp access to Chinese pinyin-to-character mapping

[Eric Abrahamsen <eric@ericabrahamsen.net>]

[-- Attachment #1: Type: text/plain, Size: 510 bytes --]

Robert Pluim <rpluim@gmail.com> writes:

> Eric Abrahamsen <eric@ericabrahamsen.net> writes:
>
>>
>> Oh, after reading a couple of "make" tutorials, I see maybe the make
>> rule could be simplified to:
>>
>> ${leimdir}/../lisp/language/pinyin.el: ${srcdir}/MISC-DIC/pinyin.map
>>   $(AM_V_GEN)${RUN_EMACS} -l titdic-cnv -f pinyin-convert $< $0
>
> $@ , I think.

Ah, right you are, thanks. I was wondering why that wasn't working. This
version should do the trick; it also gitignores the generated file.

Eric

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #2: 0001-Make-pinyin-to-Chinese-character-mapping-available-t.patch --]
[-- Type: text/x-patch, Size: 3372 bytes --]

From 2395d1a62e66206c04b7069d372fdb4f10787863 Mon Sep 17 00:00:00 2001
From: Eric Abrahamsen <eric@ericabrahamsen.net>
Date: Wed, 30 Jan 2019 12:31:49 -0800
Subject: [PATCH 1/2] Make pinyin to Chinese character mapping available to
 elisp

* leim/Makefile.in: Build the file pinyin.el from pinyin.map.
* lisp/international/titdic-cnv.el (pinyin-convert): New function that
  writes the library pinyin.el, containing a new constant
  `pinyin-character-map'.
* .gitignore: Ignore the generated pinyin.el file.
---
 .gitignore                       |  1 +
 leim/Makefile.in                 |  6 +++++-
 lisp/international/titdic-cnv.el | 32 ++++++++++++++++++++++++++++++++
 3 files changed, 38 insertions(+), 1 deletion(-)

diff --git a/.gitignore b/.gitignore
index 53f41f0f3e..f3d5ccb0f8 100644
--- a/.gitignore
+++ b/.gitignore
@@ -199,6 +199,7 @@ lisp/international/charscript.el
 lisp/international/cp51932.el
 lisp/international/eucjp-ms.el
 lisp/international/uni-*.el
+lisp/language/pinyin.el
 
 # Documentation.
 *.aux
diff --git a/leim/Makefile.in b/leim/Makefile.in
index c2fc8c41f2..4307d50087 100644
--- a/leim/Makefile.in
+++ b/leim/Makefile.in
@@ -84,7 +84,8 @@ MISC=
 	${leimdir}/quail/PY.el		\
 	${leimdir}/quail/ZIRANMA.el	\
 	${leimdir}/quail/CTLau.el	\
-	${leimdir}/quail/CTLau-b5.el
+	${leimdir}/quail/CTLau-b5.el    \
+	${srcdir}/../lisp/language/pinyin.el
 
 ## All the generated .el files.
 TIT_MISC = ${TIT_GB} ${TIT_BIG5} ${MISC}
@@ -142,6 +143,9 @@ ${leimdir}/ja-dic/ja-dic.el:
 	$(AM_V_GEN)$(RUN_EMACS) -batch -l ja-dic-cnv \
 	  -f batch-skkdic-convert -dir "$(leimdir)/ja-dic" "$<"
 
+${srcdir}/../lisp/language/pinyin.el: ${srcdir}/MISC-DIC/pinyin.map
+	$(AM_V_GEN)${RUN_EMACS} -l titdic-cnv -f pinyin-convert $< $@
+
 
 .PHONY: bootstrap-clean distclean maintainer-clean extraclean
 
diff --git a/lisp/international/titdic-cnv.el b/lisp/international/titdic-cnv.el
index 2ce2c527b9..d33e9ff229 100644
--- a/lisp/international/titdic-cnv.el
+++ b/lisp/international/titdic-cnv.el
@@ -1203,6 +1203,38 @@ batch-miscdic-convert
 	(miscdic-convert filename dir))))
   (kill-emacs 0))
 
+(defun pinyin-convert ()
+  "Convert text file pinyin.map into an elisp library.
+The library is named pinyin.el, and contains the constant
+`pinyin-character-map'."
+  (let ((src-file (car command-line-args-left))
+        (dst-file (cadr command-line-args-left))
+        (coding-system-for-write 'utf-8-emacs))
+    (with-temp-file dst-file
+      (insert ";; This file is automatically generated from pinyin.map,\
+ by the\n;; function pinyin-convert.\n\n")
+      (insert "(defconst pinyin-character-map\n'(")
+      (let ((pos (point)))
+        (insert-file-contents src-file)
+        (goto-char pos)
+        (re-search-forward "^[a-z]")
+        (beginning-of-line)
+        (delete-region pos (point))
+        (while (not (eobp))
+          (insert "(\"")
+          (skip-chars-forward "a-z")
+          (insert "\" . \"")
+          (delete-char 1)
+          (end-of-line)
+          (while (= (preceding-char) ?\r)
+	    (delete-char -1))
+          (insert "\")")
+          (forward-line 1)))
+      (insert ")\n\"An alist holding correspondences between pinyin syllables\
+ and\nChinese characters.\")\n\n")
+      (insert "(provide 'pinyin)\n"))
+    (kill-emacs 0)))
+
 ;; Prevent "Local Variables" above confusing Emacs.
 \f
 
-- 
2.20.1