data(hanja): a lone consonant is a reading too

Every Korean keyboard's 한자 key answers a lone consonant with the KS X
1001 symbol palette, and has since 한글 워드프로세서: ㅁ for ※ ○ △ ㈜, ㄴ
for the brackets, ㄹ for the units, ㅇ for the circled numbers.  strans
sends that key to the same search as a syllable -- Khanja is Ctrl+H at
strans.c:830, and startsearch seeds the query with whatever ko.c left
pending -- but every one of hanja.dict's 187286 readings is a syllable, so
the popup came up with a query in it and nothing to pick:

	ㅁ: 0 candidates
	ㄴ: 0 candidates
	ㄹ: 0 candidates
	한: 99 candidates 韓 漢 寒 限 閑 恨 旱 汗 翰 邯 罕 悍 澣 閒 瀚

libhangul ships that palette beside the Hanja table already imported here:
data/hanja/mssymbol.txt, same commit, same author, same BSD-3 terms, same
key:value:comment format -- and keyed by the compatibility jamo ko.c
already holds, U+3141 for ㅁ.  So the engine does not change at all; the
same dictlookup on the same trie now finds something:

	ㅁ: 75 candidates ＃ ＆ ＊ ＠ § ※ ☆ ★ ○ ● ◎ ◇ ◆ □ ■ △ ▲ ▽ ▼
	ㄴ: 23 candidates ＂ （ ） ［ ］ ｛ ｝ ‘ ’ “ ” 〔 〕 〈 〉 《 》 「 」
	ㄹ: 94 candidates ＄ ％ ￦ Ｆ ′ ″ ℃ Å ￠ ￡ ￥ ¤ ℉ ‰ € ㎕ ㎖ ㎗ ℓ
	한: 99 candidates 韓 漢 寒 限 閑 恨 旱 汗 翰 邯 罕 悍 澣 閒 瀚

Both scripts widen by one rule -- a syllable reading gives Hanja, a jamo
reading gives a symbol -- and hanja.src regenerates byte for byte as it
was, because upstream's own non-syllable readings are words like ㄱ자집
whose values were never Hanja and still fall out.  985 of mssymbol.txt's
987 rows survive: its ideographic space and its soft hyphen do not, since
a candidate the popup cannot draw is not a candidate, and the row format
separates candidates with a space besides.

The two keyspaces cannot collide -- one is syllables, one is single jamo --
so the 187286 existing rows are unchanged, byte for byte, and 18 rows join
them.  mkhanja takes a source list as mkemoji already does, and keeps each
upstream header, which is why the licence text now appears twice.

89 unit, check-live, check-stress and valgrind all clean.  The five new
assertions were checked by breaking the change five ways: dropping
mssymbol.src from SOURCES, letting issymbol keep a formatting character,
letting a jamo reading keep Hanja, widening isjamo to the vowels, and
making mkhanja reject jamo readings.  Each fails only the tests that exist
for it.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

LICENSES/README.md

@@ -1,8 +1,9 @@
 # License inventory
 
-- `BSD-3-Clause-libhangul-hanja.txt` contains the terms for the
-  single-character Hanja data in `map/hanja.src` and generated
-  `map/hanja.dict`, derived from libhangul's `data/hanja/hanja.txt`.
+- `BSD-3-Clause-libhangul-hanja.txt` contains the terms for the Hanja data
+  in `map/hanja.src` and the symbol data in `map/mssymbol.src`, and for the
+  generated `map/hanja.dict` they share, derived from libhangul's
+  `data/hanja/hanja.txt` and `data/hanja/mssymbol.txt`.
 - `GPL-2.0-or-later.txt` contains GNU GPL version 2.  The header of
   `map/kanji.dict` grants the option to use GPL version 2 or any later
   version.

README.md

@@ -16,7 +16,7 @@ and a GTK 3 module.
 | `Ctrl+T` | English |
 | `Ctrl+V` | Vietnamese Telex |
 | `Ctrl+E` | Emoji and symbol search |
-| `Ctrl+H` | One-shot Hanja search |
+| `Ctrl+H` | One-shot Hanja and symbol search |
 
 Only a plain `Ctrl` chord is a strans key: with `Shift`, `Alt` or `Super`
 held it commits what is pending and goes to the application, so
@@ -55,8 +55,11 @@ emoji's CLDR name and keywords in English, Korean and Japanese, and against
 ASCII aliases such as `->` and `<=`. `Ctrl+H` takes the syllable being
 composed as its query and composes on from it, converting a word as well as
 a syllable — 한자 gives 漢字, 대한민국 gives 大韓民國 — and `Esc` gives the
-syllable back. Text already committed belongs to the application and
-cannot be converted.
+syllable back. A lone consonant is a reading too, and answers with the
+symbol table a Korean keyboard's 한자 key has always offered: ㅁ gives ※ ○
+△ ㈜, ㄴ the brackets 「」『』, ㄹ the units ℃ ㎏ ℓ, ㅇ the circled numbers
+①②③. Text already committed belongs to the application and cannot be
+converted.
 
 Dead keys and Compose sequences are composed by strans itself for the
 Wayland, XIM and IBus frontends, from `XCOMPOSEFILE` or the locale; the

map/README

@@ -1,42 +1,53 @@
 # Dictionary data
 
-## Korean Hanja data
+## Korean Hanja and symbol data
 
-`hanja.src` is the tracked, reviewable source for Korean Hanja conversion.
-Every data row is Hanja, a tab, and its modern Hangul reading, a character
-or a word:
+`hanja.src` and `mssymbol.src` are the tracked, reviewable sources for what
+the Hanja search converts.  Every data row is a result, a tab, and its
+Hangul reading.  A Hanja reads as a syllable or a word; a symbol reads as
+the lone consonant a Korean keyboard's 한자 key offers it under:
 
 ```
 漢	한
 漢字	한자
+※	ㅁ
 ```
 
-`mkhanja` validates that contract and groups rows by their reading to
-produce the runtime dictionary.  Candidate order follows source order.  The
-source keeps all retained pairs for review; the generated dictionary stores
-the first 128 candidates per reading because that is the engine's lookup
-limit.
+`mkhanja` validates that contract and groups the rows of both sources by
+their reading to produce the runtime dictionary.  The two keyspaces do not
+meet: a reading is either syllables or one jamo.  Candidate order follows
+source order.  The sources keep all retained pairs for review; the
+generated dictionary stores the first 128 candidates per reading because
+that is the engine's lookup limit.
 
-The source is derived from libhangul release tag `libhangul-0.2.0`.  The
+The sources are derived from libhangul release tag `libhangul-0.2.0`.  The
 annotated tag object is `20afc38922e3595ee3ed5b186f2ea05afe663763`, its
 peeled commit is `41c702f5d3581325b646ef6249f1f641b0427ae0`, and
-`data/hanja/hanja.txt` has blob ID
-`199cfd70c4b306257ac2e018714a1285f7cf0ed3`.  Import and regenerate it from
-the repository root with:
+`data/hanja/hanja.txt` and `data/hanja/mssymbol.txt` have blob IDs
+`199cfd70c4b306257ac2e018714a1285f7cf0ed3` and
+`31c4e63d74293b6a759d4a2005cd1e7333746631`.  Import and regenerate them
+from the repository root with:
 
 ```sh
 curl -L https://raw.githubusercontent.com/libhangul/libhangul/41c702f5d3581325b646ef6249f1f641b0427ae0/data/hanja/hanja.txt -o upstream
 printf '%s  %s\n' dd44dcc856cf542b1022d0f39c2e9b9f8805fdcc5923be80f04849ed97ce0996 upstream | sha256sum -c -
 map/libhangul2hanja upstream >map/hanja.src
+curl -L https://raw.githubusercontent.com/libhangul/libhangul/41c702f5d3581325b646ef6249f1f641b0427ae0/data/hanja/mssymbol.txt -o upstream
+printf '%s  %s\n' b685a4ebe2716b25eb29c42f6da6493716ecd78b604b44a33420987d21948e99 upstream | sha256sum -c -
+map/libhangul2hanja upstream >map/mssymbol.src
 map/mkhanja >map/hanja.dict
 ```
 
-`libhangul2hanja` retains only rows whose reading is modern Hangul syllables
-throughout and whose value is Hanja the popup can draw: U+3400–U+4DBF,
-U+4E00–U+9FFF, or U+F900–U+FAFF.  Thus jamo readings, mixed values, and
-supplementary-plane ideographs are omitted.  The import preserves the upstream license header and row order.
-The retained data is BSD 3-Clause licensed by Choe Hwanjin; the complete text
-is in `LICENSES/BSD-3-Clause-libhangul-hanja.txt`.
+`libhangul2hanja` keeps a syllable reading only when its value is Hanja the
+popup can draw: U+3400–U+4DBF, U+4E00–U+9FFF, or U+F900–U+FAFF.  Thus mixed
+values and supplementary-plane ideographs are omitted.  It keeps a jamo
+reading, U+3131–U+314E, only when its value is one rune the popup can draw
+and a candidate row can carry — so `mssymbol.txt`'s ideographic space and
+soft hyphen are omitted, leaving 985 of its 987 rows, and a Hanja under a
+jamo reading is omitted as noise.  The import preserves each upstream
+license header and row order.  The retained data is BSD 3-Clause licensed
+by Choe Hwanjin; the complete text is in
+`LICENSES/BSD-3-Clause-libhangul-hanja.txt`.
 
 ## Emoji and symbol data
 

map/hanja.dict

@@ -24,6 +24,32 @@
 ;; CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
 ;; ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
 ;; POSSIBILITY OF SUCH DAMAGE.
+;; Copyright (c) 2005-2014 Choe Hwanjin
+;; All rights reserved.
+;;
+;; Redistribution and use in source and binary forms, with or without
+;; modification, are permitted provided that the following conditions are met:
+;;
+;; 1. Redistributions of source code must retain the above copyright notice,
+;;    this list of conditions and the following disclaimer.
+;; 2. Redistributions in binary form must reproduce the above copyright notice,
+;;    this list of conditions and the following disclaimer in the documentation
+;;    and/or other materials provided with the distribution.
+;; 3. Neither the name of the author nor the names of its contributors
+;;    may be used to endorse or promote products derived from this software
+;;    without specific prior written permission.
+;;
+;; THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+;; AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+;; IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+;; ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+;; LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+;; CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+;; SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+;; INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+;; CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+;; ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+;; POSSIBILITY OF SUCH DAMAGE.
 
 가	可 家 加 歌 價 街 假 佳 暇 架 价 賈 伽 柯 迦 軻 嘉 駕 嫁 稼 哥 呵 苛 袈 訶 枷 珂 茄 痂 跏 斝 葭 舸 笳 哿 坷 檟 謌 珈 砢 佉 呿 榎 仮 傢 咖 瘕 耞 宊 椵 叚 価 猳 髂 瘸 鴐 䴥 拁 㤎 榢 毠 溊 牁 豭 槚 诃 贾 轲 镓 驾 鲄 婽 尜 岢 幏 彁 徦 愘 戓 戨 斚 樖 泇 渮 滒 炣 牫 牱 犌 玍 癿 笴 糘 胢 腵 蚵 貑 跒 酠 鉫 鉲 鎵 鎶 魺 鴚 麚 㗎 㚙 㞹 㢦 㤉 㧝 㪃 㪼 㱒 㹢 䂟 䈔 䑝 䔅 䕒 䪪 䯊 䶗 嘏
 가가	假家 可呵 可嘉 家家 呵呵
@@ -187311,3 +187337,21 @@
 힐책	詰責
 힐척	詰斥
 힐항	詰抗
+ㄱ	！ ＇ ， ． ／ ： ； ？ ＾ ＿ ｀ ｜ ￣ 、 。 · ‥ … ¨ 〃 ― ∥ ＼ ∼ ´ ～ ˇ ˘ ˝ ˚ ˙ ¸ ˛ ¡ ¿ ː
+ㄲ	Æ Ð Ħ IJ Ŀ Ł Ø Œ Þ Ŧ Ŋ æ đ ð ħ ı ij ĸ ŀ ł ø œ ß þ ŧ ŋ ʼn
+ㄴ	＂ （ ） ［ ］ ｛ ｝ ‘ ’ “ ” 〔 〕 〈 〉 《 》 「 」 『 』 【 】
+ㄷ	＋ － ＜ ＝ ＞ ± × ÷ ≠ ≤ ≥ ∞ ∴ ♂ ♀ ∠ ⊥ ⌒ ∂ ∇ ≡ ≒ ≪ ≫ √ ∽ ∝ ∵ ∫ ∬ ∈ ∋ ⊆ ⊇ ⊂ ⊃ ∪ ∩ ∧ ∨ ￢ ⇒ ⇔ ∀ ∃ ∮ ∑ ∏
+ㄸ	ぁ あ ぃ い ぅ う ぇ え ぉ お か が き ぎ く ぐ け げ こ ご さ ざ し じ す ず せ ぜ そ ぞ た だ ち ぢ っ つ づ て で と ど な に ぬ ね の は ば ぱ ひ び ぴ ふ ぶ ぷ へ べ ぺ ほ ぼ ぽ ま み む め も ゃ や ゅ ゆ ょ よ ら り る れ ろ ゎ わ ゐ ゑ を ん
+ㄹ	＄ ％ ￦ Ｆ ′ ″ ℃ Å ￠ ￡ ￥ ¤ ℉ ‰ € ㎕ ㎖ ㎗ ℓ ㎘ ㏄ ㎣ ㎤ ㎥ ㎦ ㎙ ㎚ ㎛ ㎜ ㎝ ㎞ ㎟ ㎠ ㎡ ㎢ ㏊ ㎍ ㎎ ㎏ ㏏ ㎈ ㎉ ㏈ ㎧ ㎨ ㎰ ㎱ ㎲ ㎳ ㎴ ㎵ ㎶ ㎷ ㎸ ㎹ ㎀ ㎁ ㎂ ㎃ ㎄ ㎺ ㎻ ㎼ ㎽ ㎾ ㎿ ㎐ ㎑ ㎒ ㎓ ㎔ Ω ㏀ ㏁ ㎊ ㎋ ㎌ ㏖ ㏅ ㎭ ㎮ ㎯ ㏛ ㎩ ㎪ ㎫ ㎬ ㏝ ㏐ ㏓ ㏃ ㏉ ㏜ ㏆
+ㅁ	＃ ＆ ＊ ＠ § ※ ☆ ★ ○ ● ◎ ◇ ◆ □ ■ △ ▲ ▽ ▼ → ← ↑ ↓ ↔ 〓 ◁ ◀ ▷ ▶ ♤ ♠ ♡ ♥ ♧ ♣ ⊙ ◈ ▣ ◐ ◑ ▒ ▤ ▥ ▨ ▧ ▦ ▩ ♨ ☏ ☎ ☜ ☞ ¶ † ‡ ↕ ↗ ↙ ↖ ↘ ♭ ♩ ♪ ♬ ㉿ ㈜ № ㏇ ™ ㏂ ㏘ ℡ ® ª º
+ㅂ	─ │ ┌ ┐ ┘ └ ├ ┬ ┤ ┴ ┼ ━ ┃ ┏ ┓ ┛ ┗ ┣ ┳ ┫ ┻ ╋ ┠ ┯ ┨ ┷ ┿ ┝ ┰ ┥ ┸ ╂ ┒ ┑ ┚ ┙ ┖ ┕ ┎ ┍ ┞ ┟ ┡ ┢ ┦ ┧ ┩ ┪ ┭ ┮ ┱ ┲ ┵ ┶ ┹ ┺ ┽ ┾ ╀ ╁ ╃ ╄ ╅ ╆ ╇ ╈ ╉ ╊
+ㅃ	ァ ア ィ イ ゥ ウ ェ エ ォ オ カ ガ キ ギ ク グ ケ ゲ コ ゴ サ ザ シ ジ ス ズ セ ゼ ソ ゾ タ ダ チ ヂ ッ ツ ヅ テ デ ト ド ナ ニ ヌ ネ ノ ハ バ パ ヒ ビ ピ フ ブ プ ヘ ベ ペ ホ ボ ポ マ ミ ム メ モ ャ ヤ ュ ユ ョ ヨ ラ リ ル レ ロ ヮ ワ ヰ ヱ ヲ ン ヴ ヵ ヶ
+ㅅ	㉠ ㉡ ㉢ ㉣ ㉤ ㉥ ㉦ ㉧ ㉨ ㉩ ㉪ ㉫ ㉬ ㉭ ㉮ ㉯ ㉰ ㉱ ㉲ ㉳ ㉴ ㉵ ㉶ ㉷ ㉸ ㉹ ㉺ ㉻ ㈀ ㈁ ㈂ ㈃ ㈄ ㈅ ㈆ ㈇ ㈈ ㈉ ㈊ ㈋ ㈌ ㈍ ㈎ ㈏ ㈐ ㈑ ㈒ ㈓ ㈔ ㈕ ㈖ ㈗ ㈘ ㈙ ㈚ ㈛
+ㅆ	А Б В Г Д Е Ё Ж З И Й К Л М Н О П Р С Т У Ф Х Ц Ч Ш Щ Ъ Ы Ь Э Ю Я а б в г д е ё ж з и й к л м н о п р с т у ф х ц ч ш щ ъ ы ь э ю я
+ㅇ	ⓐ ⓑ ⓒ ⓓ ⓔ ⓕ ⓖ ⓗ ⓘ ⓙ ⓚ ⓛ ⓜ ⓝ ⓞ ⓟ ⓠ ⓡ ⓢ ⓣ ⓤ ⓥ ⓦ ⓧ ⓨ ⓩ ① ② ③ ④ ⑤ ⑥ ⑦ ⑧ ⑨ ⑩ ⑪ ⑫ ⑬ ⑭ ⑮ ⒜ ⒝ ⒞ ⒟ ⒠ ⒡ ⒢ ⒣ ⒤ ⒥ ⒦ ⒧ ⒨ ⒩ ⒪ ⒫ ⒬ ⒭ ⒮ ⒯ ⒰ ⒱ ⒲ ⒳ ⒴ ⒵ ⑴ ⑵ ⑶ ⑷ ⑸ ⑹ ⑺ ⑻ ⑼ ⑽ ⑾ ⑿ ⒀ ⒁ ⒂
+ㅈ	０ １ ２ ３ ４ ５ ６ ７ ８ ９ ⅰ ⅱ ⅲ ⅳ ⅴ ⅵ ⅶ ⅷ ⅸ ⅹ Ⅰ Ⅱ Ⅲ Ⅳ Ⅴ Ⅵ Ⅶ Ⅷ Ⅸ Ⅹ
+ㅊ	½ ⅓ ⅔ ¼ ¾ ⅛ ⅜ ⅝ ⅞ ¹ ² ³ ⁴ ⁿ ₁ ₂ ₃ ₄
+ㅋ	ㄱ ㄲ ㄳ ㄴ ㄵ ㄶ ㄷ ㄸ ㄹ ㄺ ㄻ ㄼ ㄽ ㄾ ㄿ ㅀ ㅁ ㅂ ㅃ ㅄ ㅅ ㅆ ㅇ ㅈ ㅉ ㅊ ㅋ ㅌ ㅍ ㅎ ㅏ ㅐ ㅑ ㅒ ㅓ ㅔ ㅕ ㅖ ㅗ ㅘ ㅙ ㅚ ㅛ ㅜ ㅝ ㅞ ㅟ ㅠ ㅡ ㅢ ㅣ
+ㅌ	ㅥ ㅦ ㅧ ㅨ ㅩ ㅪ ㅫ ㅬ ㅭ ㅮ ㅯ ㅰ ㅱ ㅲ ㅳ ㅴ ㅵ ㅶ ㅷ ㅸ ㅹ ㅺ ㅻ ㅼ ㅽ ㅾ ㅿ ㆀ ㆁ ㆂ ㆃ ㆄ ㆅ ㆆ ㆇ ㆈ ㆉ ㆊ ㆋ ㆌ ㆍ ㆎ
+ㅍ	Ａ Ｂ Ｃ Ｄ Ｅ Ｆ Ｇ Ｈ Ｉ Ｊ Ｋ Ｌ Ｍ Ｎ Ｏ Ｐ Ｑ Ｒ Ｓ Ｔ Ｕ Ｖ Ｗ Ｘ Ｙ Ｚ ａ ｂ ｃ ｄ ｅ ｆ ｇ ｈ ｉ ｊ ｋ ｌ ｍ ｎ ｏ ｐ ｑ ｒ ｓ ｔ ｕ ｖ ｗ ｘ ｙ ｚ
+ㅎ	Α Β Γ Δ Ε Ζ Η Θ Ι Κ Λ Μ Ν Ξ Ο Π Ρ Σ Τ Υ Φ Χ Ψ Ω α β γ δ ε ζ η θ ι κ λ μ ν ξ ο π ρ σ τ υ φ χ ψ ω

map/libhangul2hanja

@@ -1,7 +1,8 @@
 #!/usr/bin/env python3
-"""Extract Hanja readings from libhangul data."""
+"""Extract Hanja and symbol readings from libhangul data."""
 
 import sys
+import unicodedata
 from pathlib import Path
 
 
@@ -9,12 +10,31 @@ def ishangul(s):
     return s != "" and all(0xAC00 <= ord(c) <= 0xD7A3 for c in s)
 
 
+def isjamo(s):
+    return len(s) == 1 and 0x3131 <= ord(s) <= 0x314E
+
+
 def ishanja(s):
     return s != "" and all(0x3400 <= ord(c) <= 0x4DBF
                            or 0x4E00 <= ord(c) <= 0x9FFF
                            or 0xF900 <= ord(c) <= 0xFAFF for c in s)
 
 
+def issymbol(s):
+    """One rune the popup can draw and a candidate row can carry: not a
+    space, which the row separates candidates with, and not a formatting
+    character, which would leave a blank candidate to pick."""
+    return (len(s) == 1 and not s.isspace() and not ishanja(s)
+            and not unicodedata.category(s).startswith("C"))
+
+
+def keeps(reading, value):
+    """A syllable reading gives Hanja; a jamo reading gives a symbol."""
+    if ishangul(reading):
+        return ishanja(value)
+    return isjamo(reading) and issymbol(value)
+
+
 def extract(src, name):
     comments = []
     entries = []
@@ -32,16 +52,16 @@ def extract(src, name):
         fields = line.split(":")
         if len(fields) != 3:
             raise ValueError(f"{name}:{lineno}: need key:value:comment")
-        reading, hanja, _ = fields
-        if not ishangul(reading) or not ishanja(hanja):
+        reading, value, _ = fields
+        if not keeps(reading, value):
             continue
-        pair = (hanja, reading)
+        pair = (value, reading)
         if pair in seen:
-            raise ValueError(f"{name}:{lineno}: duplicate Hanja reading")
+            raise ValueError(f"{name}:{lineno}: duplicate reading")
         seen.add(pair)
         entries.append(pair)
     if not entries:
-        raise ValueError(f"{name}: no Hanja readings")
+        raise ValueError(f"{name}: no readings")
     return comments, entries
 
 
@@ -63,8 +83,8 @@ def main():
             print(line)
         if comments:
             print()
-        for hanja, reading in entries:
-            print(f"{hanja}\t{reading}")
+        for value, reading in entries:
+            print(f"{value}\t{reading}")
     except (OSError, UnicodeError, ValueError) as error:
         print(error, file=sys.stderr)
         return 1

map/mkhanja

@@ -1,11 +1,13 @@
 #!/usr/bin/env python3
-"""Write hanja.dict from a Hanja-per-row UTF-8 source."""
+"""Write hanja.dict from result-per-row UTF-8 sources."""
 
 import sys
+import unicodedata
 from pathlib import Path
 
 
-SOURCE = Path(__file__).with_name("hanja.src")
+SOURCES = [Path(__file__).with_name(name)
+           for name in ("hanja.src", "mssymbol.src")]
 MAXCANDIDATES = 128
 
 
@@ -13,17 +15,29 @@ def ishangul(s):
     return s != "" and all(0xAC00 <= ord(c) <= 0xD7A3 for c in s)
 
 
+def isjamo(s):
+    return len(s) == 1 and 0x3131 <= ord(s) <= 0x314E
+
+
 def ishanja(s):
     return s != "" and all(0x3400 <= ord(c) <= 0x4DBF
                            or 0x4E00 <= ord(c) <= 0x9FFF
                            or 0xF900 <= ord(c) <= 0xFAFF for c in s)
 
 
-def read(path):
+def issymbol(s):
+    """One rune the popup can draw and a candidate row can carry: not a
+    space, which the row separates candidates with, and not a formatting
+    character, which would leave a blank candidate to pick."""
+    return (len(s) == 1 and not s.isspace() and not ishanja(s)
+            and not unicodedata.category(s).startswith("C"))
+
+
+def read(path, table, seen):
+    """Adds path's rows to table, keyed by reading, and returns its header."""
     comments = []
-    table = {}
-    seen = set()
     leading = True
+    found = False
     with path.open(encoding="utf-8") as src:
         for lineno, raw in enumerate(src, 1):
             line = raw.rstrip("\r\n")
@@ -36,31 +50,36 @@ def read(path):
             leading = False
             fields = line.split("\t")
             if len(fields) != 2:
-                raise ValueError(f"{path}:{lineno}: need Hanja<TAB>reading")
-            hanja, reading = fields
-            if not ishanja(hanja):
-                raise ValueError(f"{path}:{lineno}: need BMP Hanja")
-            if not ishangul(reading):
-                raise ValueError(f"{path}:{lineno}: need Hangul syllables")
-            pair = (hanja, reading)
+                raise ValueError(f"{path}:{lineno}: need result<TAB>reading")
+            value, reading = fields
+            if ishangul(reading):
+                if not ishanja(value):
+                    raise ValueError(f"{path}:{lineno}: need BMP Hanja")
+            elif isjamo(reading):
+                if not issymbol(value):
+                    raise ValueError(f"{path}:{lineno}: need one symbol rune")
+            else:
+                raise ValueError(f"{path}:{lineno}: need a syllable or jamo "
+                                 "reading")
+            pair = (value, reading)
             if pair in seen:
-                raise ValueError(f"{path}:{lineno}: duplicate Hanja reading")
+                raise ValueError(f"{path}:{lineno}: duplicate reading")
             seen.add(pair)
-            table.setdefault(reading, []).append(hanja)
-    if not seen:
-        raise ValueError(f"{path}: no Hanja readings")
-    return comments, table
+            found = True
+            table.setdefault(reading, []).append(value)
+    if not found:
+        raise ValueError(f"{path}: no readings")
+    return comments
 
 
 def main():
     sys.stdout.reconfigure(encoding="utf-8")
     sys.stderr.reconfigure(encoding="utf-8")
-    if len(sys.argv) > 2:
-        print(f"usage: {sys.argv[0]} [hanja.src]", file=sys.stderr)
-        return 2
-    path = Path(sys.argv[1]) if len(sys.argv) == 2 else SOURCE
+    paths = [Path(arg) for arg in sys.argv[1:]] or SOURCES
+    table = {}
+    seen = set()
     try:
-        comments, table = read(path)
+        comments = [line for path in paths for line in read(path, table, seen)]
         for line in comments:
             print(line)
         if comments:

tests/mkhanja_test.py

@@ -64,6 +64,24 @@ class MkhanjaTest(unittest.TestCase):
                                      "\u91d1\t\uae40",
                                      "\u6f22\u5b57\t\ud55c\uc790"])
 
+    def test_imports_symbol_rows_under_a_jamo(self):
+        result = run(
+            IMPORT,
+            self.source(
+                "\u3141:\u203b:reference mark\n"
+                "\u3134:\u300c:bracket\n"
+                "\u3131:\u3000:ideographic space\n"
+                "\u3131:\u00ad:soft hyphen\n"
+                "\u3131:\u52a0:Hanja under a jamo\n"
+                "\u3141:\u203b\u203b:two runes\n"
+                "\u3141\u3134:\u203b:two jamo\n"
+                "\u314f:\u203b:a vowel\n"
+            ),
+        )
+        self.assertEqual(result.returncode, 0, result.stderr)
+        self.assertEqual(result.stdout.splitlines(),
+                         ["\u203b\t\u3141", "\u300c\t\u3134"])
+
     def test_import_rejects_malformed_and_duplicate_rows(self):
         bad = [
             "한 漢\n",
@@ -110,6 +128,19 @@ class MkhanjaTest(unittest.TestCase):
             ],
         )
 
+    def test_groups_symbols_under_their_jamo(self):
+        result = run(
+            GENERATE,
+            self.source(
+                "※\tㅁ\n"
+                "○\tㅁ\n"
+                "「\tㄴ\n"
+            ),
+        )
+        self.assertEqual(result.returncode, 0, result.stderr)
+        self.assertEqual(result.stdout.splitlines(),
+                         ["ㅁ\t※ ○", "ㄴ\t「"])
+
     def test_generator_rejects_bad_rows(self):
         bad = [
             "漢a\t한\n",
@@ -117,6 +148,12 @@ class MkhanjaTest(unittest.TestCase):
             "𠀀\t한\n",
             "漢\t한\n漢\t한\n",
             "漢 한\n",
+            "加\tㅁ\n",
+            "※\t한\n",
+            "※\tㅁㄴ\n",
+            "※※\tㅁ\n",
+            "\u3000\tㄱ\n",
+            "\u00ad\tㄱ\n",
         ]
         for text in bad:
             with self.subTest(text=repr(text)):
@@ -131,6 +168,15 @@ class MkhanjaTest(unittest.TestCase):
         self.assertEqual(result.returncode, 0, result.stderr)
         self.assertIn("한\t", result.stdout)
 
+    def test_generator_reads_both_sources(self):
+        result = run(GENERATE)
+        self.assertEqual(result.returncode, 0, result.stderr)
+        lines = result.stdout.splitlines()
+        self.assertEqual(lines.count(";; All rights reserved."), 2)
+        rows = dict(line.split("\t") for line in lines if "\t" in line)
+        self.assertIn("漢", rows["한"].split())
+        self.assertIn("※", rows["ㅁ"].split())
+
     def test_generator_keeps_runtime_candidate_limit(self):
         rows = "".join(f"{chr(0x4E00 + n)}\t한\n" for n in range(129))
         result = run(GENERATE, self.source(rows))