-
Notifications
You must be signed in to change notification settings - Fork 73
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
4 changed files
with
127 additions
and
96 deletions.
There are no files selected for viewing
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
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,23 @@ | ||
| #!/bin/env groovy | ||
|
|
||
| package org.dict_uk.check; | ||
|
|
||
| def dictDir = new File("data/dict") | ||
|
|
||
| def files = dictDir.listFiles().findAll { it.name =~ /.*anim.*\.lst/ } | ||
|
|
||
| assert files | ||
|
|
||
| def lines = files.collect { File f -> | ||
| f.readLines() | ||
| .findAll { it =~ /^[А-ЯІЇЄҐ]'?[а-яіїєґ](?!.*\/adj)/ && ! (it =~ /[.\/]<|-(фонд|фест)/) } | ||
| } | ||
| .flatten() | ||
| .grep { it } | ||
|
|
||
| java.text.Collator coll = java.text.Collator.getInstance(new Locale("uk", "UA")); | ||
| coll.setStrength(java.text.Collator.IDENTICAL) | ||
| coll.setDecomposition(java.text.Collator.NO_DECOMPOSITION) | ||
|
|
||
| println lines.toSorted(coll).join("\n") | ||
| println "Found ${lines.size()} suspicious anim" |
48 changes: 48 additions & 0 deletions
48
src/test/groovy/org/dict_uk/check/CheckReplacements.groovy
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,48 @@ | ||
| #!/bin/env groovy | ||
|
|
||
| package org.dict_uk.check; | ||
|
|
||
| def dictDir = new File("data/dict") | ||
|
|
||
| def files = dictDir.listFiles().findAll { it.name.endsWith('.lst') || it.name.endsWith('replace.txt') } | ||
|
|
||
| assert files | ||
|
|
||
| def replWords = files.collect { it.text.split("\n") } \ | ||
| .flatten() \ | ||
| .findAll { it.contains(" #> ") } | ||
| .collect { | ||
| def replStr = it.split(" #> ")[1].trim() | ||
| def replItems = replStr.split(/\|/) | ||
| if( replItems.size() > 5 && false ) | ||
| println "WARNING: Too many replacements ${replItems.size()} > 5 for\n\t$it" | ||
|
|
||
| def repls = replStr.split(/[;, \|]+/) | ||
| def word = it.split(' ', 2)[0] | ||
| if( word in repls && ! (it =~ /(?iu) - [а-яіїєґ].* #> /) ) { | ||
| println "WARNING: Replacement is same as word: $word:\n\t$it" | ||
| } | ||
|
|
||
| def dups = replItems.countBy{it}.grep{it.value > 1}.collect{it.key} | ||
| if( dups ) { | ||
| println "WARNING: Duplicate replacements: $dups:\n\t$it" | ||
| } | ||
|
|
||
| repls | ||
| } | ||
| .flatten() | ||
| .collect { it.replaceAll(/[()]/, '').replaceFirst(/-таки$/, '') } | ||
| .findAll { it =~ /[а-яіїєґ]/ } | ||
| .unique().sort() | ||
|
|
||
| def spellWords = new File("out/words_spell.txt").text.split('\n') | ||
| spellWords += new File("data/dict/slang.lst").text.split('\n').collect{ it.replaceFirst(/ .*/, '') } | ||
| spellWords += new File("data/dict/arch.lst").text.split('\n').collect{ it.replaceFirst(/ .*/, '') } | ||
|
|
||
| println "Unique replacement words: ${replWords.size()}" | ||
|
|
||
| replWords.removeAll(spellWords) | ||
|
|
||
|
|
||
| println "Unknown:\n" + replWords.join("\n") | ||
| println "Total uknown: ${replWords.size()}" |
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,40 @@ | ||
| #!/bin/env groovy | ||
|
|
||
| package org.dict_uk.check; | ||
|
|
||
| def dictDir = new File("data/dict") | ||
|
|
||
| def files = dictDir.listFiles().findAll { it.name.endsWith('.lst') } | ||
|
|
||
| assert files | ||
|
|
||
| def xps = [:].withDefault{ [] } | ||
|
|
||
| def lines = files.collect { it.readLines() }.flatten() \ | ||
| .collect { it.replaceFirst(/#.*/, '') } | ||
| .findAll{ it.contains(":xp") \ | ||
| && ! it.startsWith("+cs") && ! it.startsWith('#') \ | ||
| && ! (it =~ /verb(?!.*inf)|noun(?!.*(:[mnf]:v_naz|:p:v_naz:ns))/) } | ||
| .collect { it | ||
| it.replaceAll(/^([^ ]+)\h.*?(:xp.).*/, '$1 $2') | ||
| } | ||
|
|
||
| lines.each{ | ||
| def (base, xp) = it.split(/ /) | ||
| xps[base] << xp | ||
| } | ||
|
|
||
| xps.each { k,v -> v.sort() } | ||
|
|
||
| xps.each { k,v -> | ||
| if( v[0] != ':xp1' ) println "out of order: $k: $v" | ||
| else if( v.size() == 1 ) println "single: $k: $v" | ||
| else { | ||
| def dups = v.countBy{it}.grep{it.value > 1}.collect{it.key} | ||
| if( dups ) println "dups: $k: $dups" | ||
| } | ||
| } | ||
|
|
||
| // java.text.Collator coll = java.text.Collator.getInstance(new Locale("uk", "UA")); | ||
| // coll.setStrength(java.text.Collator.IDENTICAL) | ||
| // coll.setDecomposition(java.text.Collator.NO_DECOMPOSITION) |