Add ltr to all characters

Even rigth-to-left languages like Arabic or Hebrew are easier to read
with their English description if they're formatted left-to-right with
the character first.
If we ever have descriptions in other languages, we must re-evaluate
that argument, but for now, I think it's better like this.

Also, more classes now use the `Character` type. That should hopefully
simplify something, too.

CHANGELOG.md

@@ -1,15 +1,16 @@
 # [NEXT]
 ## Added
-- rofimoji now has a manpage (#57).
+- rofimoji now has a manpage. (#57)
 - There's a new file for [Nerd Font icons](https://www.nerdfonts.com/).
 
 ## Changed
 - The emojis from 13.1 have been added!
 - Instead of several parameters to choose the input method, they have been consolidated into `--action` (`-a`).
-- The annotations on emojis don't contain their name (#59).
-- The results are now sorted by rofi, by default based on Levenshtein distance (#59).
+- The annotations on emojis don't contain their name. (#59)
+- The results are now sorted by rofi, by default based on Levenshtein distance. (#59)
+- All entries are now forced to be left aligned, even for right-to-left languages. (#62)
 - The dependency on `pyxdg` was removed.
-- Some code cleanup (#56, #58).
+- Some code cleanup. (#56, #58)
 
 # [4.3.0]
 ## Added

extractors/blockextractor.py

@@ -36,7 +36,7 @@ def write_to_files(self: 'BlockExtractor'):
 
             with Path(f"../picker/data/{block.name.lower().replace(' ', '_')}.csv").open('w') as symbol_file:
                 for character in block.characters:
-                    symbol_file.write(f"{character.char} {html.escape(character.name)}\n")
+                    symbol_file.write(f'{character.directional_char} {html.escape(character.name)}\n')
 
     def extract(self):
         self.fetch_blocks()

extractors/characterfactory.py

@@ -1,12 +1,20 @@
 from typing import Union
 
 import requests
+from unicodedata import bidirectional
 
 
 class Character(object):
+    ltr_mark = '\u200e'
+
     def __init__(self, char: int, name: str):
         self.char = chr(char)
         self.name = name.strip().title()
+        self.force_ltr = bidirectional(self.char) in ('AL', 'AN', 'R', 'RLE', 'RLI', 'RLO')
+
+    @property
+    def directional_char(self):
+        return f'{self.ltr_mark if self.force_ltr else ""}{self.char}'
 
 
 class CharacterFactory(object):

extractors/nerdextractor.py

@@ -1,13 +1,11 @@
 import html
 from pathlib import Path
-from collections import namedtuple
-from unicodedata import bidirectional
 
 import requests
 from bs4 import BeautifulSoup
 
-Icon = namedtuple('Icon', 'icon name force_ltr')
-ltr_mark = '\u200e'
+from extractors.characterfactory import Character
+
 
 class NerdExtractor(object):
     def __init__(self: 'NerdExtractor'):
@@ -23,18 +21,17 @@ def fetch_icons(self: 'NerdExtractor'):
 
         characters = BeautifulSoup(response.text, 'html.parser').find(id='glyphCheatSheet').find_all(class_='column')
         for c in characters:
-            icon = chr(int(c.find(class_='codepoint').string, 16))
+            icon = int(c.find(class_='codepoint').string, 16)
             name = c.find(class_='class-name').string
-            force_ltr = bidirectional(icon) in ('AL', 'AN', 'R', 'RLE', 'RLI', 'RLO')
-            self.icons.append(Icon(icon, name, force_ltr))
+            self.icons.append(Character(icon, name))
 
     def write_to_file(self: 'NerdExtractor'):
         if len(self.icons) == 0:
             return
 
         with Path("../picker/data/nerd_font.csv").open('w') as symbol_file:
             for icon in self.icons:
-                symbol_file.write(f"{ltr_mark if icon.force_ltr else ''}{icon.icon} {html.escape(icon.name.lower())}\n")
+                symbol_file.write(f"{icon.directional_char} {html.escape(icon.name.lower())}\n")
 
     def extract(self: 'NerdExtractor'):
         self.fetch_icons()

picker/data/adlam.csv

@@ -1,88 +1,88 @@
-𞤀 Adlam Capital Letter Alif
-𞤁 Adlam Capital Letter Daali
-𞤂 Adlam Capital Letter Laam
-𞤃 Adlam Capital Letter Miim
-𞤄 Adlam Capital Letter Ba
-𞤅 Adlam Capital Letter Sinnyiiyhe
-𞤆 Adlam Capital Letter Pe
-𞤇 Adlam Capital Letter Bhe
-𞤈 Adlam Capital Letter Ra
-𞤉 Adlam Capital Letter E
-𞤊 Adlam Capital Letter Fa
-𞤋 Adlam Capital Letter I
-𞤌 Adlam Capital Letter O
-𞤍 Adlam Capital Letter Dha
-𞤎 Adlam Capital Letter Yhe
-𞤏 Adlam Capital Letter Waw
-𞤐 Adlam Capital Letter Nun
-𞤑 Adlam Capital Letter Kaf
-𞤒 Adlam Capital Letter Ya
-𞤓 Adlam Capital Letter U
-𞤔 Adlam Capital Letter Jiim
-𞤕 Adlam Capital Letter Chi
-𞤖 Adlam Capital Letter Ha
-𞤗 Adlam Capital Letter Qaaf
-𞤘 Adlam Capital Letter Ga
-𞤙 Adlam Capital Letter Nya
-𞤚 Adlam Capital Letter Tu
-𞤛 Adlam Capital Letter Nha
-𞤜 Adlam Capital Letter Va
-𞤝 Adlam Capital Letter Kha
-𞤞 Adlam Capital Letter Gbe
-𞤟 Adlam Capital Letter Zal
-𞤠 Adlam Capital Letter Kpo
-𞤡 Adlam Capital Letter Sha
-𞤢 Adlam Small Letter Alif
-𞤣 Adlam Small Letter Daali
-𞤤 Adlam Small Letter Laam
-𞤥 Adlam Small Letter Miim
-𞤦 Adlam Small Letter Ba
-𞤧 Adlam Small Letter Sinnyiiyhe
-𞤨 Adlam Small Letter Pe
-𞤩 Adlam Small Letter Bhe
-𞤪 Adlam Small Letter Ra
-𞤫 Adlam Small Letter E
-𞤬 Adlam Small Letter Fa
-𞤭 Adlam Small Letter I
-𞤮 Adlam Small Letter O
-𞤯 Adlam Small Letter Dha
-𞤰 Adlam Small Letter Yhe
-𞤱 Adlam Small Letter Waw
-𞤲 Adlam Small Letter Nun
-𞤳 Adlam Small Letter Kaf
-𞤴 Adlam Small Letter Ya
-𞤵 Adlam Small Letter U
-𞤶 Adlam Small Letter Jiim
-𞤷 Adlam Small Letter Chi
-𞤸 Adlam Small Letter Ha
-𞤹 Adlam Small Letter Qaaf
-𞤺 Adlam Small Letter Ga
-𞤻 Adlam Small Letter Nya
-𞤼 Adlam Small Letter Tu
-𞤽 Adlam Small Letter Nha
-𞤾 Adlam Small Letter Va
-𞤿 Adlam Small Letter Kha
-𞥀 Adlam Small Letter Gbe
-𞥁 Adlam Small Letter Zal
-𞥂 Adlam Small Letter Kpo
-𞥃 Adlam Small Letter Sha
+‎𞤀 Adlam Capital Letter Alif
+‎𞤁 Adlam Capital Letter Daali
+‎𞤂 Adlam Capital Letter Laam
+‎𞤃 Adlam Capital Letter Miim
+‎𞤄 Adlam Capital Letter Ba
+‎𞤅 Adlam Capital Letter Sinnyiiyhe
+‎𞤆 Adlam Capital Letter Pe
+‎𞤇 Adlam Capital Letter Bhe
+‎𞤈 Adlam Capital Letter Ra
+‎𞤉 Adlam Capital Letter E
+‎𞤊 Adlam Capital Letter Fa
+‎𞤋 Adlam Capital Letter I
+‎𞤌 Adlam Capital Letter O
+‎𞤍 Adlam Capital Letter Dha
+‎𞤎 Adlam Capital Letter Yhe
+‎𞤏 Adlam Capital Letter Waw
+‎𞤐 Adlam Capital Letter Nun
+‎𞤑 Adlam Capital Letter Kaf
+‎𞤒 Adlam Capital Letter Ya
+‎𞤓 Adlam Capital Letter U
+‎𞤔 Adlam Capital Letter Jiim
+‎𞤕 Adlam Capital Letter Chi
+‎𞤖 Adlam Capital Letter Ha
+‎𞤗 Adlam Capital Letter Qaaf
+‎𞤘 Adlam Capital Letter Ga
+‎𞤙 Adlam Capital Letter Nya
+‎𞤚 Adlam Capital Letter Tu
+‎𞤛 Adlam Capital Letter Nha
+‎𞤜 Adlam Capital Letter Va
+‎𞤝 Adlam Capital Letter Kha
+‎𞤞 Adlam Capital Letter Gbe
+‎𞤟 Adlam Capital Letter Zal
+‎𞤠 Adlam Capital Letter Kpo
+‎𞤡 Adlam Capital Letter Sha
+‎𞤢 Adlam Small Letter Alif
+‎𞤣 Adlam Small Letter Daali
+‎𞤤 Adlam Small Letter Laam
+‎𞤥 Adlam Small Letter Miim
+‎𞤦 Adlam Small Letter Ba
+‎𞤧 Adlam Small Letter Sinnyiiyhe
+‎𞤨 Adlam Small Letter Pe
+‎𞤩 Adlam Small Letter Bhe
+‎𞤪 Adlam Small Letter Ra
+‎𞤫 Adlam Small Letter E
+‎𞤬 Adlam Small Letter Fa
+‎𞤭 Adlam Small Letter I
+‎𞤮 Adlam Small Letter O
+‎𞤯 Adlam Small Letter Dha
+‎𞤰 Adlam Small Letter Yhe
+‎𞤱 Adlam Small Letter Waw
+‎𞤲 Adlam Small Letter Nun
+‎𞤳 Adlam Small Letter Kaf
+‎𞤴 Adlam Small Letter Ya
+‎𞤵 Adlam Small Letter U
+‎𞤶 Adlam Small Letter Jiim
+‎𞤷 Adlam Small Letter Chi
+‎𞤸 Adlam Small Letter Ha
+‎𞤹 Adlam Small Letter Qaaf
+‎𞤺 Adlam Small Letter Ga
+‎𞤻 Adlam Small Letter Nya
+‎𞤼 Adlam Small Letter Tu
+‎𞤽 Adlam Small Letter Nha
+‎𞤾 Adlam Small Letter Va
+‎𞤿 Adlam Small Letter Kha
+‎𞥀 Adlam Small Letter Gbe
+‎𞥁 Adlam Small Letter Zal
+‎𞥂 Adlam Small Letter Kpo
+‎𞥃 Adlam Small Letter Sha
 𞥄 Adlam Alif Lengthener
 𞥅 Adlam Vowel Lengthener
 𞥆 Adlam Gemination Mark
 𞥇 Adlam Hamza
 𞥈 Adlam Consonant Modifier
 𞥉 Adlam Geminate Consonant Modifier
 𞥊 Adlam Nukta
-𞥋 Adlam Nasalization Mark
-𞥐 Adlam Digit Zero
-𞥑 Adlam Digit One
-𞥒 Adlam Digit Two
-𞥓 Adlam Digit Three
-𞥔 Adlam Digit Four
-𞥕 Adlam Digit Five
-𞥖 Adlam Digit Six
-𞥗 Adlam Digit Seven
-𞥘 Adlam Digit Eight
-𞥙 Adlam Digit Nine
-𞥞 Adlam Initial Exclamation Mark
-𞥟 Adlam Initial Question Mark
+‎𞥋 Adlam Nasalization Mark
+‎𞥐 Adlam Digit Zero
+‎𞥑 Adlam Digit One
+‎𞥒 Adlam Digit Two
+‎𞥓 Adlam Digit Three
+‎𞥔 Adlam Digit Four
+‎𞥕 Adlam Digit Five
+‎𞥖 Adlam Digit Six
+‎𞥗 Adlam Digit Seven
+‎𞥘 Adlam Digit Eight
+‎𞥙 Adlam Digit Nine
+‎𞥞 Adlam Initial Exclamation Mark
+‎𞥟 Adlam Initial Question Mark

picker/data/alphabetic_presentation_forms.csv

@@ -10,49 +10,49 @@
 ﬕ Armenian Small Ligature Men Ini
 ﬖ Armenian Small Ligature Vew Now
 ﬗ Armenian Small Ligature Men Xeh
-יִ Hebrew Letter Yod With Hiriq
+‎יִ Hebrew Letter Yod With Hiriq
 ﬞ Hebrew Point Judeo-Spanish Varika
-ײַ Hebrew Ligature Yiddish Yod Yod Patah
-ﬠ Hebrew Letter Alternative Ayin
-ﬡ Hebrew Letter Wide Alef
-ﬢ Hebrew Letter Wide Dalet
-ﬣ Hebrew Letter Wide He
-ﬤ Hebrew Letter Wide Kaf
-ﬥ Hebrew Letter Wide Lamed
-ﬦ Hebrew Letter Wide Final Mem
-ﬧ Hebrew Letter Wide Resh
-ﬨ Hebrew Letter Wide Tav
+‎ײַ Hebrew Ligature Yiddish Yod Yod Patah
+‎ﬠ Hebrew Letter Alternative Ayin
+‎ﬡ Hebrew Letter Wide Alef
+‎ﬢ Hebrew Letter Wide Dalet
+‎ﬣ Hebrew Letter Wide He
+‎ﬤ Hebrew Letter Wide Kaf
+‎ﬥ Hebrew Letter Wide Lamed
+‎ﬦ Hebrew Letter Wide Final Mem
+‎ﬧ Hebrew Letter Wide Resh
+‎ﬨ Hebrew Letter Wide Tav
 ﬩ Hebrew Letter Alternative Plus Sign
-שׁ Hebrew Letter Shin With Shin Dot
-שׂ Hebrew Letter Shin With Sin Dot
-שּׁ Hebrew Letter Shin With Dagesh And Shin Dot
-שּׂ Hebrew Letter Shin With Dagesh And Sin Dot
-אַ Hebrew Letter Alef With Patah
-אָ Hebrew Letter Alef With Qamats
-אּ Hebrew Letter Alef With Mapiq
-בּ Hebrew Letter Bet With Dagesh
-גּ Hebrew Letter Gimel With Dagesh
-דּ Hebrew Letter Dalet With Dagesh
-הּ Hebrew Letter He With Mapiq
-וּ Hebrew Letter Vav With Dagesh
-זּ Hebrew Letter Zayin With Dagesh
-טּ Hebrew Letter Tet With Dagesh
-יּ Hebrew Letter Yod With Dagesh
-ךּ Hebrew Letter Final Kaf With Dagesh
-כּ Hebrew Letter Kaf With Dagesh
-לּ Hebrew Letter Lamed With Dagesh
-מּ Hebrew Letter Mem With Dagesh
-נּ Hebrew Letter Nun With Dagesh
-סּ Hebrew Letter Samekh With Dagesh
-ףּ Hebrew Letter Final Pe With Dagesh
-פּ Hebrew Letter Pe With Dagesh
-צּ Hebrew Letter Tsadi With Dagesh
-קּ Hebrew Letter Qof With Dagesh
-רּ Hebrew Letter Resh With Dagesh
-שּ Hebrew Letter Shin With Dagesh
-תּ Hebrew Letter Tav With Dagesh
-וֹ Hebrew Letter Vav With Holam
-בֿ Hebrew Letter Bet With Rafe
-כֿ Hebrew Letter Kaf With Rafe
-פֿ Hebrew Letter Pe With Rafe
-ﭏ Hebrew Ligature Alef Lamed
+‎שׁ Hebrew Letter Shin With Shin Dot
+‎שׂ Hebrew Letter Shin With Sin Dot
+‎שּׁ Hebrew Letter Shin With Dagesh And Shin Dot
+‎שּׂ Hebrew Letter Shin With Dagesh And Sin Dot
+‎אַ Hebrew Letter Alef With Patah
+‎אָ Hebrew Letter Alef With Qamats
+‎אּ Hebrew Letter Alef With Mapiq
+‎בּ Hebrew Letter Bet With Dagesh
+‎גּ Hebrew Letter Gimel With Dagesh
+‎דּ Hebrew Letter Dalet With Dagesh
+‎הּ Hebrew Letter He With Mapiq
+‎וּ Hebrew Letter Vav With Dagesh
+‎זּ Hebrew Letter Zayin With Dagesh
+‎טּ Hebrew Letter Tet With Dagesh
+‎יּ Hebrew Letter Yod With Dagesh
+‎ךּ Hebrew Letter Final Kaf With Dagesh
+‎כּ Hebrew Letter Kaf With Dagesh
+‎לּ Hebrew Letter Lamed With Dagesh
+‎מּ Hebrew Letter Mem With Dagesh
+‎נּ Hebrew Letter Nun With Dagesh
+‎סּ Hebrew Letter Samekh With Dagesh
+‎ףּ Hebrew Letter Final Pe With Dagesh
+‎פּ Hebrew Letter Pe With Dagesh
+‎צּ Hebrew Letter Tsadi With Dagesh
+‎קּ Hebrew Letter Qof With Dagesh
+‎רּ Hebrew Letter Resh With Dagesh
+‎שּ Hebrew Letter Shin With Dagesh
+‎תּ Hebrew Letter Tav With Dagesh
+‎וֹ Hebrew Letter Vav With Holam
+‎בֿ Hebrew Letter Bet With Rafe
+‎כֿ Hebrew Letter Kaf With Rafe
+‎פֿ Hebrew Letter Pe With Rafe
+‎ﭏ Hebrew Ligature Alef Lamed