WJG (24th May, 2005):
RS inspired me to produce this humble offering. It takes a line of
ASCII formatted pinyin and spits out a string with the appropriate diacritics. At present it doesn't handle capitals.
# -------------------------------------------------------------
# pinyin_covert.tcl
# Written by William J Giddings, 2005
# -------------------------------------------------------------
# Usage:
# pinyin:parse <string>
#
# Args:
# <string> any ascii string representing hanyu pinyin in the form
# <initial sound><final sound><tone>
# e.g. chuang2
# <ch><uang>2
#
# Returns:
# correctly formatted unicode string
#
# Purpose:
# --------
# Convert linear 'ascii pinyin' Hanyu finals into correct forms
# complete with diacritics.
#
# Notes:
# ------
# Use versions of ttf 2.76 or higher. These include the necessary
# diacritics to display all pinyin vowels plus their tone marks.
#
# For further examples, see CEDIT dictionary
# http://www.mandarintools.com/cedict.html
#
# -------------------------------------------------------------
#-----------------------------------------------------------
# swap linear ascii input for correct finals including diacritics
#-----------------------------------------------------------
proc pinyin:parse {str} {
set str [string map {
a1 \u101 a2 \ue1 a3 \u103 a4 \ue0 a5 a
ai1 "\u101 i" ai2 "\ue1 i" ai3 "\u103 i" ai4 "\ue0 i" ai5 ai
ao1 "\u101 o" ao2 "\ue1 o" ao3 "\u103 o" ao4 "\ue0 o" ao5 ao
an1 "\u101 n" an2 "\ue1 n" an3 "\u103 n" an4 "\ue0 n" an5 an
ang1 "\u101 ng" ang2 "\ue1 ng" ang3 "\u103 ng" ang4 "\ue0 ng" ang5 ang
e1 \u113 e2 \ue9 e3 \u11b e4 \ue8 e5 e
ei1 "\u113 i" ei2 "\ue9 i" ei3 "\u11b i" ei4 "\ue8 i" ei5 ei
en1 "\u113 n" en2 "\ue9 n" en3 "\u11b n" en4 "\ue8 n" en5 en
eng1 "\u113 ng" eng2 "\ue9 ng" eng3 "\u11b ng" eng4 "\ue8 ng" eng5 eng
o1 \u14d o2 \uf3 o3 \u14f o4 \uf2 o5 o
ong1 "\u14d ng" ong2 "\uf3 ng" ong3 "\u14f ng" ong4 "\uf2 ng" ong5 ong
ou1 "\u14d u" ou2 "\uf3 u" ou3 "\u14f u" ou4 "\uf2 u" ou5 ou
i1 \u12b i2 \ued i3 \u12d i4 \uec i5 i
ia1 "i \u101" ia2 "i \ue1" ia3 "i \u103" ia4 "i \ue0" ia5 ia
iao1 "i \u101 o" iao2 "i \ue1 o" iao3 "i \u103 o" iao4 "i \ue0 o"
iu1 "i \u16b" iu2 "i \ufa" iu3 "i \u16d" iu4 "i \uf9" iu5 iu
ian1 "\u12b an" ian2 "\ued an" ian3 "\u12d an" ian4 "\uec an"
in1 "\u12b n" in2 "\ued n" in3 "\u12d n" in4 "\uec n" in5 in
iang1 "i \u101 ng" iang2 "i \ue1 ng" iang3 "i \u103 ng" iang4 "i \ue0 ng"
ing1 "\u12b ng" ing2 "\ued ng" ing3 "\u12d ng" ing4 "\uec ng" ing5 ing
iong1 "i \u14d ng" iong2 "i \uf3 ng" iong3 "i \u14f ng" iong4 "i \uf2 ng"
u1 \u16b u2 \ufa u3 \u16d u4 \uf9 u5 u
ua1 "u \u101" ua2 "u \ue1" ua3 "u \u103" ua4 "u \ue0" ua5 ua
uai1 "u \u101 i" uai2 "u \ue1 i" uai3 "u \u103 i" uai4 "u \ue0 i"
uo1 "u \u14d" uo2 "u \uf3" uo3 "u \u14f" uo4 "u \uf2" uo5 uo
ui1 "u \u12b" ui2 "u \ued" ui3 "u \u12d" ui4 "u \uec" ui4 ui
un1 "\u16b n" un2 "\ufa n" un3 "\u16d n" un4 "\uf9 n" un5 un
uan1 "u \u101 n" uan2 "u \ue1 n" uan3 "u \u103 n" uan4 "u \ue0 n"
uang1 "u \u101 ng" uang2 "u \ue1 ng" uang3 "u \u103 ng" uang4 "u\ue0 ng"
ueng1 "u \u113 ng" ueng2 "u \ue9 ng" ueng3 "u \u11b ng" ueng4 "u \ue8 ng"
u:1 \u1d6 u:2 \u1d8 u:3 \u1da u:4 \u1dc u:5 \ufc u: \ufc
u:e1 "\ufc \u113" u:e2 "\ufc \ue9" u:e3 "\ufc \u11b" u:e4 "\ufc \ue8" u:e5 "\ufc e"
u:an1 "\ufc \u101 n" u:an2 "\ufc \ue1 n" u:an3 "\ufc \u103 n" u:an4 "\ufc \ue0 n"
u:en1 "\ufc \u113 n" u:en2 "\ufc \ue9 n" u:en3 "\ufc \u11b n" u:en4 "\ufc \ue8 n"
er4 "\ue8 r"
} $str]
set str [string map {" " ""} $str]
return $str
}
#-----------------------------------------------------------
# work through each word in a string, may not be needed.
#-----------------------------------------------------------
proc pinyin:convertstring {str} {
set ret ""
foreach word $str {
lappend ret [pinyin:parse $word]
}
return $ret
}
#-----------------------------------------------------------
# demo
#-----------------------------------------------------------
proc demo {} {
package require Tk
text .t -font {{Bitstream Cyberbit} 14}
pack .t -fill both -expand 1
.t insert end [pinyin:convertstring "A few test words"]\n
.t insert end [pinyin:convertstring "nu:3ren2"]\n
.t insert end [pinyin:convertstring "chuang2"]\n
.t insert end [pinyin:convertstring "ni3 hao3 ma?"]\n
.t insert end [pinyin:convertstring "jiang1"]\n\n
.t insert end [pinyin:convertstring "Test out for all logical final/tone combinations"]\n
.t insert end [pinyin:convertstring "a1 a2 a3 a4 a"]\n
.t insert end [pinyin:convertstring "ai1 ai2 ai3 ai4 ai"]\n
.t insert end [pinyin:convertstring "ao1 ao2 ao3 ao4 ao"]\n
.t insert end [pinyin:convertstring "an1 an2 an3 an4 an"]\n
.t insert end [pinyin:convertstring "ang1 ang2 ang3 ang4 ang"]\n\n
.t insert end [pinyin:convertstring "e1 e2 e3 e4 e"]\n
.t insert end [pinyin:convertstring "ei1 ei2 ei3 ei4 ei"]\n
.t insert end [pinyin:convertstring "en1 en2 en3 en4 en"]\n
.t insert end [pinyin:convertstring "eng1 eng2 eng3 eng4 eng"]\n\n
.t insert end [pinyin:convertstring "i1 i2 i3 i4 i"]\n
.t insert end [pinyin:convertstring "ia1 ia2 ia3 ia4 ia"]\n
.t insert end [pinyin:convertstring "iao1 iao2 iao3 iao4 iao"]\n
.t insert end [pinyin:convertstring "iu1 iu2 iu3 iu4 iu"]\n
.t insert end [pinyin:convertstring "ian1 ian2 ian3 ian4 ian"]\n
.t insert end [pinyin:convertstring "in1 in2 in3 in4 in"]\n
.t insert end [pinyin:convertstring "iang1 iang2 iang3 iang4 iang"]\n
.t insert end [pinyin:convertstring "ing1 ing2 ing3 ing4 ing"]\n
.t insert end [pinyin:convertstring "iong1 iong2 iong3 iong4 iong"]\n\n
.t insert end [pinyin:convertstring "o1 o2 o3 o4 o"]\n
.t insert end [pinyin:convertstring "ong1 ong2 ong3 ong4 ong"]\n\n
.t insert end [pinyin:convertstring "ou1 ou2 ou3 ou4 ou"]\n
.t insert end [pinyin:convertstring "u1 u2 u3 u4 u"]\n
.t insert end [pinyin:convertstring "ua1 ua2 ua3 ua4 ua"]\n
.t insert end [pinyin:convertstring "uai1 uai2 uai3 uai4 uai"]\n
.t insert end [pinyin:convertstring "uo1 uo2 uo3 uo4 uo"]\n
.t insert end [pinyin:convertstring "ui1 ui2 ui3 ui4 ui"]\n
.t insert end [pinyin:convertstring "uan1 uan2 uan3 uan4 uan"]\n
.t insert end [pinyin:convertstring "uang1 uang2 uang3 uang4 uang"]\n
.t insert end [pinyin:convertstring "uen1 uen2 uen3 uen4 uen"]\n
.t insert end [pinyin:convertstring "ueng1 ueng2 ueng3 ueng4 ueng"]\n\n
.t insert end [pinyin:convertstring "u:1 u:2 u:3 u:4 u:"]\n
.t insert end [pinyin:convertstring "u:e1 u:e2 u:e3 u:e4 u:e"]\n
.t insert end [pinyin:convertstring "u:an1 u:an2 u:an3 u:an4 u:an"]\n
.t insert end [pinyin:convertstring "u:en1 u:en2 u:en3 u:en4 u:en"]\n\n
.t insert end [pinyin:convertstring "Something more substantial"]\n
set testtext {
{Chinese}
{Ding1 yun2 shi4 Ying1yu3 xi4 de xue2sheng. Ta1 cong1 Bei3jing1 lai2 zher4 xue3xi.}
{Ying1yu3 xi4 you3 wu3ge zhong1guo2 liu2xue2sheng1. Ta1men dou1 zai4 xue2sheng su4she4 zhu4.}
{}
{Translation}
{Ding1 Yun2 is a student in the English language department. She has come from Bei3jing1 to study here.}
{The English language deparment has five foreign students. They all live in the students dormitory.}
}
foreach str $testtext {
.t insert end [pinyin:convertstring $str]\n
}
}
demoWJG (24/JUN/11) Took another look at this sample script and reworked the mappings. In the previous example 'logical tone-syllable' combinations are created using this approach is not wholly satisfying, some of the possible combinations are not found in Chinese in practice. The following mapping should be used:
#---------------
#!/bin/sh
# the next line restarts using tclsh \
exec tclsh "$0" "$@"
#---------------
set pinyin_map {
a1 ā a2 á a3 ǎ a4 à a5 a
ai1 āi ai2 ái ai3 ǎi ai4 ài ai5 ai
ao1 āo ao2 áo ao3 ǎo ao4 ào ao5 ao
an1 ān an2 án an3 ǎn an4 àn an5 an
ang1 āng ang2 áng ang3 ǎng ang4 àng ang5 ang
e1 ē e2 é e3 ě e4 è e5 e
ei1 ēi ei2 éi ei3 ěi ei4 èi ei5 ei
en1 ēn en2 én en3 ěn en4 èn en5 en
eng1 ēng eng2 éng eng3 ěng eng4 èng eng5 eng
i1 ī i2 í i3 ǐ i4 ì i5 i
ia1 iā ia2 iá ia3 iǎ ia4 ià ia5 ia
iao1 iāo iao2 iáo iao3 iǎo iao4 iào iao5 iao
iu1 iū iu2 iú iu3 iǔ iu4 iù iu5 iu
ian1 iān ian2 ián ian3 iǎn ian4 iàn ian5 ian
in1 īn in2 ín in3 ǐn in4 ìn in5 in
iang1 iāng iang2 iáng iang3 iǎng iang4 iàng iang5 iang
ing1 īng ing2 íng ing3 ǐng ing4 ìng ing5 ing
iong1 iōng iong2 ióng iong3 iǒng iong4 iòng iong5 iong
o1 ō o2 ó o3 ǒ o4 ò o5 o
ong1 ōng ong2 óng ong3 ǒng ong4 òng ong5 ong
ou1 ōu ou2 óu ou3 ǒu ou4 òu ou5 ou
u1 ū u2 ú u3 ǔ u4 ù u5 u
ua1 uā ua2 uá ua3 uǎ ua4 uà ua5 ua
uai1 uā uai2 uá uai3 uǎ uai4 uà uai5 ua
uo1 uō uo2 uó uo3 uǒ uo4 uò uo5 uo
ui1 uī ui2 uí ui3 uǐ ui4 uì ui5 ui
uan1 uān uan2 uán uan3 uǎn uan4 uàn uan5 uan
uang1 uāng uang2 uáng uang3 uǎng uang4 uàng uang5 uang
un1 ūn un2 ún un3 ǔn un4 ùn un5 un
u:1 ǖ u:2 ǘ u:3 ǚ u:4 ǜ u:5 ü
}
set testtext {
{Chinese}
{Ding1 yun2 shi4 Ying1yu3 xi4 de xue2sheng. Ta1 cong1 Bei3jing1 lai2 zher4 xue3xi.}
{Ying1yu3 xi4 you3 wu3ge zhong1guo2 liu2xue2sheng1. Ta1men dou1 zai4 xue2sheng su4she4 zhu4.}
{}
{Translation}
{Ding1 Yun2 is a student in the English language department. She has come from Bei3jing1 to study here.}
{The English language deparment has five foreign students. They all live in the students dormitory.}
}
puts [string map $pinyin_map $testtext]
