Add Catalan/Valencian alphabet and fix English ASCII mapping

NOTES.md

@@ -20,6 +20,11 @@ Uses same implementation as Spanish.
 
 Uses same implementation as Spanish.
 
+## Catalan/Valencian
+
+- Uses same implementation as Spanish except for accent marks which differs.
+- The character "L geminate" has not been found in unicode database.
+
 # Other useful resources
 
 - [World Braille Usage][world-braille-usage]

README.md

@@ -9,6 +9,9 @@ text-to-Braille converter.
 | ------ | ----------- |
 | English | [North American Braille ASCII code][en-wiki] |
 | Spanish | [Braille español (Grado 1)][es-cbe-guide] by [CBE][cbe-once] |
+| Galician | [Braille español (Grado 1)][es-cbe-guide] by [CBE][cbe-once] |
+| Euskera | [Braille español (Grado 1)][es-cbe-guide] by [CBE][cbe-once] |
+| Catalan/Valencian | [Braille español (Grado 1)][es-cbe-guide] by [CBE][cbe-once] |
 
 > See [`NOTES.md`][notes] to check the limitations of each implementation.
 
@@ -20,19 +23,12 @@ text-to-Braille converter.
  `Preferences` -> `System` -> `Users extensions`.
 1. Run Inkscape and you'll see the extension in `Extensions` -> `Text`.
 
-## How to use
+## Usage
 
-Select a text that you want to convert in Braille, open this extension,
-choose a locale and press `Apply`.
-
-## TODO
-
-- [x] ~~Spanish Braille conversion for texts not prepared for Braille
- translation. Add prefixes before numbers and before uppercased letters.~~
-- [ ] Catalán/valenciano
-- [x] ~~Gallego~~
-- [x] ~~Euskera~~
-- [x] ~~Spanish combinations~~
+1. Select a text that you want to convert in Braille.
+1. Open this extension.
+1. Choose an alphabet for character mappings.
+1. Press `Apply`.
 
 [notes]: https://github.com/mondeja/inkscape-braille-l18n-ext/blob/master/NOTES.md
 [download-repo]: https://github.com/mondeja/inkscape-braille-l18n-ext/archive/refs/heads/master.zip

text_braille_l18n.inx

@@ -10,6 +10,7 @@
  <option value="es">Spanish</option>
  <option value="gl">Galician</option>
  <option value="eu">Basque</option>
+ <option value="ca">Catalan/Valencian</option>
  </param>
 
  <effect>

text_braille_l18n.py

@@ -3,138 +3,218 @@
 
 import inkex
 
+# ---------------------------------
+
+# UTILITIES
+
+# English based locales
+
+EN_ASCII = " A1B'K2L@CIF/MSP\"E3H9O6R^DJG>NTQ,*5<-U8V.%[$+X!&;:4\\0Z7(_?W]#Y)="
+
+# Spanish based locales
+
+ES_NUMBERS = {
+ "1": 0x2801,
+ "2": 0x2803,
+ "3": 0x2809,
+ "4": 0x2819,
+ "5": 0x2811,
+ "6": 0x280B,
+ "7": 0x281b,
+ "8": 0x2813,
+ "9": 0x280a,
+ "0": 0x281a,
+}
+
+ES_LETTERS = {
+ "A": 0x2801,
+ "B": 0x2803,
+ "C": 0x2809,
+ "D": 0x2819,
+ "E": 0x2811,
+ "F": 0x280B,
+ "G": 0x281b,
+ "H": 0x2813,
+ "I": 0x280a,
+ "J": 0x281a,
+ "K": 0x2805,
+ "L": 0x2807,
+ "M": 0x280d,
+ "N": 0x281d,
+ "Ñ": 0x283b,
+ "O": 0x2815,
+ "P": 0x280f,
+ "Q": 0x281f,
+ "R": 0x2817,
+ "S": 0x280e,
+ "T": 0x281e,
+ "U": 0x2825,
+ "V": 0x2827,
+ "W": 0x283a,
+ "X": 0x282d,
+ "Y": 0x283d,
+ "Z": 0x2835,
+}
+
+ES_SIGNS = {
+ "ª": 0x2801, # ordinal (feminine) -> same as A
+ "º": 0x2815, # ordinal (masculine) -> same as O
+ "&": 0x282f,
+ ".": 0x2804,
+ ",": 0x2802,
+ ":": 0x2812,
+ ";": 0x2806,
+ "¿": 0x2822,
+ "?": 0x2822,
+ "¡": 0x2816,
+ "!": 0x2816,
+ '"': 0x2826,
+ "(": 0x2823,
+ ")": 0x281c,
+ "-": 0x2824,
+ "*": 0x2814,
+ "=": 0x2836,
+ "÷": 0x2832,
+ "+": 0x2816,
+ "@": 0x2810,
+ " ": 0x2800, # braille space
+}
+
+ES_PREFIXES = {
+ chr(15): 0x2828, # uppercase prefix: https://codepoints.net/U+000F
+}
+
+ES_ACCENT_MARKS = {
+ "Á": 0x2837,
+ "É": 0x282e,
+ "Í": 0x280c,
+ "Ó": 0x282c,
+ "Ú": 0x283e,
+ "Ü": 0x2833,
+}
+
+ES_COMBINATIONS = {
+ # signs
+ "%": (0x2838, 0x2834),
+ "‰": (0x2838, 0x2834, 0x2834), # per mile
+ "©": (0x2823, 0x2828, 0x2809, 0x281c),
+ "®": (0x2823, 0x2828, 0x2817, 0x281c),
+ "℗": (0x2823, 0x2828, 0x280f, 0x281c),
+ "🄯": (0x2823, 0x2828, 0x2807, 0x281c),
+ "/": (0x2820, 0x2802),
+ "\\": (0x2810, 0x2804),
+ "<": (0x2810, 0x2805),
+ ">": (0x2828, 0x2802),
+ "|": (0x2838, 0x2807),
+ "{": (0x2810, 0x2807),
+ "}": (0x2838, 0x2802),
+ "—": (0x2824, 0x2824),
+
+ # currencies
+ "€": (0x2838, 0x2811),
+ "$": (0x2838, 0x280e),
+ "¢": (0x2818, 0x2809),
+ "£": (0x2810, 0x282e),
+ "¥": (0x2838, 0x283d),
+ "￥": (0x2838, 0x283d),
+}
+
+CA_ACCENT_MARKS = {
+ "É": 0x283f,
+ "Í": 0x280c,
+ "Ó": 0x282a,
+ "Ú": 0x283e,
+ "À": 0x2837,
+ "È": 0x282e,
+ "Ò": 0x282c,
+ "Ï": 0x283b,
+ "Ü": 0x2833,
+ "Ç": 0x282f,
+}
+
+# END: UTILITIES
+
+# ---------------------------------
+
+# LOCALE FUNCTIONS
+
 def en_char_map(char):
  # https://en.wikipedia.org/wiki/Braille_ASCII#Braille_ASCII_values
  try:
- mapint = ("A1B'K2L@CIF/MSP\"E3H9O6R^DJG>NTQ,"
- "*5<-U8V.%[$+X!&;:4\\0Z7(_?W]#Y)=").index(char.upper())
+ mapint = EN_ASCII.index(char.upper())
  except ValueError:
  return char
- return chr(mapint + 0x2801)
+ return chr(mapint + 0x2800)
 
 def es_char_map(char):
- # https://sid.usal.es/idocs/F8/FDO12069/signografiabasica.pdf
+ """Spanish/Galician/Euskera chars mappers.
+
+ Source: https://sid.usal.es/idocs/F8/FDO12069/signografiabasica.pdf
+ """
  if char.isnumeric():
  # numeric prefix + number
- return "".join([
- chr(0x283c),
- chr({
- "1": 0x2801,
- "2": 0x2803,
- "3": 0x2809,
- "4": 0x2819,
- "5": 0x2811,
- "6": 0x280B,
- "7": 0x281b,
- "8": 0x2813,
- "9": 0x280a,
- "0": 0x281a,
- }[char]),
- ])
+ return "".join([chr(0x283c), chr(ES_NUMBERS[char])])
  try:
- bchar = chr({
- # letters
- "A": 0x2801,
- "ª": 0x2801, # ordinal (feminine)
- "B": 0x2803,
- "C": 0x2809,
- "D": 0x2819,
- "E": 0x2811,
- "F": 0x280B,
- "G": 0x281b,
- "H": 0x2813,
- "I": 0x280a,
- "J": 0x281a,
- "K": 0x2805,
- "L": 0x2807,
- "M": 0x280d,
- "N": 0x281d,
- "Ñ": 0x283b,
- "O": 0x2815,
- "º": 0x2815, # ordinal (masculine)
- "P": 0x280f,
- "Q": 0x281f,
- "R": 0x2817,
- "S": 0x280e,
- "T": 0x281e,
- "U": 0x2825,
- "V": 0x2827,
- "W": 0x283a,
- "X": 0x282d,
- "Y": 0x283d,
- "Z": 0x2835,
- "Á": 0x2837,
- "É": 0x282e,
- "Í": 0x280c,
- "Ó": 0x282c,
- "Ú": 0x283e,
- "Ü": 0x2833,
-
- # signs
- "&": 0x282f,
- ".": 0x2804,
- ",": 0x2802,
- ":": 0x2812,
- ";": 0x2806,
- "¿": 0x2822,
- "?": 0x2822,
- "¡": 0x2816,
- "!": 0x2816,
- '"': 0x2826,
- "(": 0x2823,
- ")": 0x281c,
- "-": 0x2824,
- "*": 0x2814,
- "=": 0x2836,
- "÷": 0x2832,
- "+": 0x2816,
- "@": 0x2810,
- " ": 0x2800, # braille space
-
- # prefixes
- chr(15): 0x2828, # uppercase prefix: https://codepoints.net/U+000F
- "#": 0x283c, # numerical prefix
- }[char.upper()])
+ bcharint = {
+ **ES_LETTERS,
+ **ES_ACCENT_MARKS,
+ **ES_SIGNS,
+ **ES_PREFIXES,
+ }[char.upper()]
  except KeyError:
  try:
  # combinations
- return {
- "%": chr(0x2838) + chr(0x2834),
- "‰": chr(0x2838) + chr(0x2834) + chr(0x2834), # per mile
- "©": chr(0x2823) + chr(0x2828) + chr(0x2809) + chr(0x281c),
- "®": chr(0x2823) + chr(0x2828) + chr(0x2817) + chr(0x281c),
- "℗": chr(0x2823) + chr(0x2828) + chr(0x280f) + chr(0x281c),
- "🄯": chr(0x2823) + chr(0x2828) + chr(0x2807) + chr(0x281c),
- "/": chr(0x2820) + chr(0x2802),
- "\\": chr(0x2810) + chr(0x2804),
- "<": chr(0x2810) + chr(0x2805),
- ">": chr(0x2828) + chr(0x2802),
- "|": chr(0x2838) + chr(0x2807),
- "{": chr(0x2810) + chr(0x2807),
- "}": chr(0x2838) + chr(0x2802),
- "—": chr(0x2824) + chr(0x2824),
-
- # currencies
- "€": chr(0x2838) + chr(0x2811),
- "$": chr(0x2838) + chr(0x280e),
- "¢": chr(0x2818) + chr(0x2809),
- "£": chr(0x2810) + chr(0x282e),
- "¥": chr(0x2838) + chr(0x283d),
- "￥": chr(0x2838) + chr(0x283d),
- }[char]
+ return "".join([chr(num) for num in ES_COMBINATIONS[char]])
  except KeyError:
  return char
  else:
  # if uppercase, add uppercase prefix before letter
- return "".join([chr(0x2828) if char.isupper() else '', bchar])
+ if char.isupper():
+ return "".join([chr(0x2828), chr(bcharint)])
+ return chr(bcharint)
+
+def ca_char_map(char):
+ """Catalan/Valencian chars mappers. Uses the same implementation as
+ Spanish but different accent marks.
+
+ Source: https://sid.usal.es/idocs/F8/FDO12069/signografiabasica.pdf
+ """
+ if char.isnumeric():
+ # numeric prefix + number
+ return "".join([chr(0x283c), chr(ES_NUMBERS[char])])
+ try:
+ bcharint = {
+ **ES_LETTERS,
+ **CA_ACCENT_MARKS,
+ **ES_SIGNS,
+ **ES_PREFIXES,
+ }[char.upper()]
+ except KeyError:
+ try:
+ # combinations
+ return "".join([chr(num) for num in ES_COMBINATIONS[char]])
+ except KeyError:
+ return char
+ else:
+ # if uppercase, add uppercase prefix before letter
+ if char.isupper():
+ return "".join([chr(0x2828), chr(bcharint)])
+ return chr(bcharint)
+
+# END: LOCALE FUNCTIONS
 
 LOCALE_CHARMAPS = {
  "en": en_char_map,
  "es": es_char_map,
  "gl": es_char_map, # Galician uses Spanish alphabet
- "eu": es_char_map, # Euskera hasn't accent marks, so use Spanish alphabet
+ "eu": es_char_map, # Euskera hasn't accent marks but uses Spanish alphabet
+ "ca": ca_char_map, # Catalan/Valencian
 }
 
+# ---------------------------------
+
+# EXTENSION
+
 class BrailleL18n(inkex.TextExtension):
  """Convert to Braille giving a localized map of replacements."""
  def add_arguments(self, pars):