-
Notifications
You must be signed in to change notification settings - Fork 16
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #155 from ichsteffen/feature-alphabetical-order
Script to create structure for alphabetical order of terms in non-English version
- Loading branch information
Showing
6 changed files
with
175 additions
and
32 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
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
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 +1,164 @@ | ||
| import static groovy.io.FileType.FILES | ||
| import java.util.regex.Matcher | ||
|
|
||
| class Term { | ||
| String term | ||
| String captionEN | ||
| String captionDE | ||
| String includeFragment | ||
|
|
||
| Term(String term, String captionEN, String captionDE, String includeFragment) { | ||
| this.term = term | ||
| this.captionEN = captionEN | ||
| this.captionDE = captionDE | ||
| this.includeFragment = includeFragment | ||
| } | ||
| } | ||
|
|
||
| /** This task collects all term captions and creates language dependent alphabetically ordered structure file | ||
| * | ||
| * Overall approach: | ||
| * 1. collect all terms to include into structure file | ||
| * 1.1. traverse all ascii doc files inside /docs/1-terms/ | ||
| * 1.2. for each term file: | ||
| * 1.2.1 extract term-anchor and language specific caption | ||
| * 1.2.2 create Term-Object with language specific captions and ascii doc fragment to include | ||
| * 1.2.3 add Term-Object into terms set | ||
| * 1.3. add "Letter Captions" as Term-Object into terms set (ascii doc fragment is level-2 caption with Letter) | ||
| * 2. create language specific structure file (loop for each language supported) | ||
| * 2.1. sort terms set language specific | ||
| * 2.2. create structure file "0-structure-<<language-code>> in directory /docs/1-terms | ||
| * | ||
| * Details about 1.2.1: Extraction of term-anchor and language specific caption | ||
| * 1.2.1.1 term-anchor | ||
| * Each term file has a term-anchor at the files head, e.g. '[#term-blackbox]' | ||
| * So the first match of regex '[#.*?]' contains the term-anchor. | ||
| * To be a bit more gentle, any characters before and after the anchor can be conceivable and allowed. | ||
| * To make matching non-greed, add ? | ||
| * This results in .*?[#.*?].*? | ||
| * To make the term as group 1 add brackets, .*?([#.*?]).*? | ||
| * | ||
| * 1.2.1.2 language specific caption | ||
| * Language specific captions are the first level-3 caption within the specific language block | ||
| * // tag::EN[] | ||
| * ... | ||
| * ==== Black Box | ||
| * ... | ||
| * // end::EN[] | ||
| * | ||
| * To find this block with one regex, regex evaluation must be multi-line, dot-match-all, case-insensitiv (?msi) | ||
| * | ||
| * Regex for language specific start tag: 'TAG::'+languageCode+'\\[\\]' | ||
| * Regex for caption (line starting '^' with '====' and any character '.*' until the first '?' end of line '$'): (^====.*?$) | ||
| * Regex for language specific end tag: 'END::'+languageCode+'\\[\\]' | ||
| * Regex for anything but as little as possible until the next part matchs: '.*?' | ||
| * | ||
| * Combination of this regex into one: | ||
| * <start tag> <anything but non greedy> <caption> <anything but non greedy> <end tag> | ||
| * results into | ||
| * '(?msi)TAG::'+languageCode+'\\[\\].*?(^====.*?$).*?END::'+languageCode+'\\[\\]' | ||
| * | ||
| * To execute this task, start gradle as follows: | ||
| * './gradlew -q sortTermsAlphabetically' | ||
| * | ||
| */ | ||
| task sortTermsAlphabetically( | ||
| description: 'collect terms and create an alphabetically ordered structure', | ||
| group: 'isaqb-glossary' | ||
| ) { | ||
| doLast { | ||
| println "start task sortTermsAlphabetically" | ||
| logger.lifecycle("start task sortTermsAlphabetically") | ||
| def terms = createTermsContent() | ||
|
|
||
| sortTermsEN(terms) | ||
| writeTermsStructure(terms, "EN") | ||
|
|
||
| sortTermsDE(terms) | ||
| writeTermsStructure(terms, "DE") | ||
|
|
||
| logger.lifecycle("done task sortTermsAlphabetically") | ||
| println "done task sortTermsAlphabetically" | ||
| } | ||
|
|
||
| ext.createTermsContent = { | ||
| def terms = collectTerms() | ||
| List alphabet = ('A'..'Z').collect { it } | ||
| alphabet.each( | ||
| letter -> terms.add(new Term(/==== $letter/, /==== $letter/, /==== $letter/, /=== $letter/)) | ||
| ) | ||
| return terms | ||
| } | ||
|
|
||
| ext.collectTerms = { | ||
| def termsFolder = new File(projectDir, '/docs/1-terms') | ||
| def terms = [] | ||
|
|
||
| termsFolder.traverse(type: FILES) { file -> | ||
|
|
||
| if (file.name ==~ 'term.*[.](ad|adoc|asciidoc)$') { | ||
| logger.debug( "Learning term from file: " + file.getAbsolutePath() ) | ||
| def content = file.text | ||
|
|
||
| def term | ||
| def refPath = termsFolder.toPath().relativize( file.toPath() ).toFile() | ||
| def includeFragment = "include::${refPath}[{include_configuration}]"; | ||
| def caption_EN | ||
| def caption_DE | ||
|
|
||
| if (content =~ ~/.*?(\[#.*?\]).*?/) { | ||
| term = Matcher.lastMatcher[0][1] | ||
| } else { | ||
| term = refPath; | ||
| } | ||
| def languageCode; | ||
| languageCode = 'EN' | ||
| if (content =~ ~('(?msi)TAG::'+languageCode+'\\[\\].*?(^====.*?$).*?END::'+languageCode+'\\[\\]') ) { | ||
| def caption = Matcher.lastMatcher[0][1]; | ||
| caption_EN = caption.replaceAll('\\s{2,}', ' ') // shrink multiple spaces into one | ||
| } else { | ||
| caption_EN = "==== $term (EN)"; | ||
| } | ||
| languageCode = 'DE' | ||
| if (content =~ ~('(?msi)TAG::'+languageCode+'\\[\\].*?(^====.*?$).*?END::'+languageCode+'\\[\\]') ) { | ||
| def caption = Matcher.lastMatcher[0][1]; | ||
| caption_DE = caption.replaceAll('\\s{2,}', ' ') // shrink multiple spaces into one | ||
| } else { | ||
| caption_DE = "==== $term (DE)" | ||
| } | ||
|
|
||
| logger.debug( "TERM $term EN $caption_EN DE $caption_DE $includeFragment" ) | ||
| terms.add(new Term(term, caption_EN, caption_DE, includeFragment)) | ||
| } | ||
| } | ||
|
|
||
| return terms | ||
| } | ||
| } | ||
|
|
||
| ext.sortTermsEN = { terms -> | ||
| terms.sort { a, b -> | ||
| a.captionEN.compareToIgnoreCase(b.captionEN) | ||
| } | ||
| } | ||
|
|
||
| ext.sortTermsDE = { terms -> | ||
| terms.sort { a, b -> | ||
| a.captionDE.compareToIgnoreCase(b.captionDE) | ||
| } | ||
| } | ||
|
|
||
| ext.writeTermsStructure = { terms, languageCode -> | ||
| def termsFolder = new File(projectDir, '/docs/1-terms') | ||
| def outFile = new File(termsFolder, "/0-structure-${languageCode}.adoc") | ||
| logger.debug( "Structure file: " + outFile.getAbsolutePath() ) | ||
|
|
||
| outFile.createNewFile() | ||
|
|
||
| outFile.withWriter('UTF-8') { writer -> | ||
| writer.writeLine("// This file is autogenerated by task sortTermAlphabetically - please do not modify manually!\n") | ||
| terms.each( | ||
| term -> writer.writeLine(term.includeFragment) | ||
| ) | ||
| } | ||
| } |