blob: 08f62202fa6cc8b4b7b61a861f16575a7612d96d [file] [log] [blame]
Show [[:block=tamil:] & [:age=3.2:] - [:age=3.1:]]
Show [[:block=tamil:] & [:age=4.0:] - [:age=3.2:]]
Show [[:block=tamil:] & [:age=4.1:] - [:age=4.0:]]
Show [[:block=tamil:] & [:age=5.0:] - [:age=4.1:]]
Stop
Show [[:NFKCQuickCheck=No:] & [$gc:Lm]]
Stop
[$Name: $gc:Sk]
[$Name: $gc:Lm]
Show [[$whitespace] - [$gc:zs]]
Show [[$gc:zs] - [$whitespace]]
Let $letter = [$gc:Lu $gc:Ll $gc:Lt $gc:Lo $gc:Lm];
Let $number = [$gc:Nd $gc:Nl $gc:No]
Let $mark = [$gc:mn $gc:me $gc:mc]
Let $LMN = [$letter $number $mark]
Let $gcAllPunctuation = [$gc:Open_Punctuation $gc:Close_Punctuation $gc:Dash_Punctuation $gc:Connector_Punctuation $gc:Other_Punctuation $gc:Initial_Punctuation $gc:Final_Punctuation]
Let $gcAllSymbols = [$gc:Currency_Symbol $gc:Modifier_Symbol $gc:Math_Symbol $gc:Other_Symbol]
Let $nfc = [^$NFC_Quick_Check:No]
Show $nfc
Show [$alphabetic - [$mark $letter $number]]
Let $oldCJK = [\u1100-\u11FF \u3040-\u30FF \u3130-\u318F \u31F0-\u31FF \u3400-\u4DBF \u4E00-\u9FFF \uAC00-\uD7AF \uF900-\uFAFF \uFF65-\uFFDC]
Show [$oldCJK & $gc:cn]
Let $fixedOld = [$oldCJK-$gc:cn]
#List the non-alphabetic old items
#Show [$oldCJK-$gc:cn-$alphabetic]
#Check for differences
#Test $fixedOld = $trialNew
#ShowEach $mark
Let $uax29_outliers = [\u3031-\u3035 \u309B-\u309C \u30A0 \u30FC \uFF70 \uFF9E-\uFF9F]
Let $other_outliers = [\u3099-\u309A \u3006 \u303C \u302A-\u302E \u302F \U000E0100-\U000E01EF]
# ==========================================
# Outliers from UAX29
Show $uax29_outliers
# Additional outliers
Show $other_outliers
# Take the 5 CJK scripts
Let $trialScripts = [$script:hani $script:hang $script:kana $script:hira $script:bopo]
# Remove the non-LMN
Let $trialNewBase = [$trialScripts & $LMN]
# Add the outliers
Let $trialNew = [$trialNewBase $uax29_outliers $other_outliers]
# Show our result
Show $trialNew
# As a double-check, show script characters we're tossing
Show [$trialScripts - $trialNew]
# Compare snippets stuff
Let $guessClose = [$lb:QU $lb:Close_Punctuation]
Let $__closing_punc = ["')>\]`\}\u00AB\u00BB\u2018\u2019\u201C\u201D\u2039\u203A\u207E\u208E\u27E7\u27E9\u27EB\u2984\u2986\u2988\u298A\u298C\u298E\u2990\u2992\u2994\u2996\u2998\u29D9\u29DB\u29FD\u3009\u300B\u300D\u300F\u3011\u3015\u3017\u3019\u301B\u301E\u301F\uFD3F\uFE42\uFE44\uFE5A\uFE5C\uFF02\uFF07\uFF09\uFF3D\uFF5D\uFF63]
$guessClose = $__closing_punc
Let $guessClose = [$gc:pf $gc:pe $gc:pi]
$guessClose = $__closing_punc
Let $guessTerm = [$sb:aterm $sb:sterm]
$guessTerm = [? ? !?? ? ? ? ? ??? ? ? ? ? ? ? ? .?? � ? ? ? ? ? ? ? ?? ? ? ? ? ? ? ?]
Let $__issymotherr = [\u00A6\u00A7\u06FD\u06FE\u0F01-\u0F03\u0F13-\u0F17\u0F1A-\u0F1F\u0FBE-\u0FC5\u0FC7-\u0FCC\u2100\u2101\u2104-\u2106\u2108\u2109\u2117\u2118\u211E-\u2121\u2195-\u2199\u219C-\u219F\u21A1\u21A2\u21A4\u21A5\u21A7-\u21AD\u21AF-\u21CD\u21D0\u21D1\u21D5-\u21F3\u2300-\u2307\u230C-\u231F\u2322-\u2328\u232B-\u237B\u237D-\u239A\u2400-\u2426\u2440-\u244A\u249C-\u24E9\u2500-\u25B6\u25B8-\u25C0\u25C2-\u25F7\u2600-\u2613\u2619-\u266E\u2670\u2671\u2701-\u2704\u2706-\u2709\u270C-\u2727\u2729-\u274B\u274F-\u2752\u2758-\u275E\u2761-\u2794\u2798-\u27AF\u27B1-\u27BE\u2800-\u28FF\u2E80-\u2E99\u2E9B-\u2EF3\u2F00-\u2FD5\u2FF0-\u2FFB\u3012\u3013\u3036\u3037\u303E\u303F\u3190\u3191\u3196-\u319F\u3200-\u321C\u322A-\u3243\u3260-\u327B\u328A-\u32B0\u32C0-\u32CB\u32D0-\u32FE\u3300-\u3376\u337B-\u33DD\u33E0-\u33FE\uA490-\uA4A1\uA4A4-\uA4B3\uA4B5-\uA4C0\uA4C2-\uA4C4\uFFED\uFFEE\uFFFC\uFFFD]
Let $__issymothers = [\u00B6\u0482\u06E9\u09FA\u0B70\u0F34\u0F36\u0F38\u0FCF\u2114\u2123\u2125\u2127\u2129\u212E\u2132\u213A\u21D3\u220E\u2617\u274D\u2756\u3004\u3020\u327F\uA4C6\uFFE4\uFFE8]
Let $symOther = [$__issymotherr $__issymothers]
$symOther = $gcAllSymbols
[$symOther & $nfc] = [$gcAllSymbols & $nfc]