Last active
March 29, 2017 18:03
-
-
Save edouard-lopez/fcbb2b026d7f25786d914c54103ba208 to your computer and use it in GitHub Desktop.
Filter codepoint from raw Unihan database
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/usr/bin/env awk | |
| BEGIN { | |
| split(toggleValues, boundaries, ",") | |
| start=0 | |
| end=start+1 | |
| } | |
| /U\+/ && /kMandarin/ { | |
| row = toHex($1); | |
| if (toHex(boundaries[start]) <= row && row <= toHex(boundaries[end])) print $1"\t"$3 | |
| if (row >= toHex(boundaries[end])) {start+=2; end=start+1} | |
| } | |
| function toHex(field) { return strtonum("0x" substr(field, 3)) }; |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| toggleValues="U+4E00,U+9FFF,U+3400,U+4DBF,U+20000,U+2A6DF,U+2A700,U+2B73F,U+2B740,U+2B81F,U+2B820,U+2CEAF,U+F900,U+FAFF" | |
| awk -f src/chinese.awk \ | |
| -v toggleValues="$toggleValues" src/Unihan_Readings.txt | |
| > src/codepoint-ruby.tsv |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment