-
Notifications
You must be signed in to change notification settings - Fork 24
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
1 changed file
with
79 additions
and
79 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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,4 +1,4 @@ | ||
| #!/usr/bin/python | ||
| #!/usr/bin/env python3 | ||
| # -*- coding: utf-8 -*- | ||
|
|
||
| # Copyright 2008 - 2015 Harri Pitkänen ([email protected]) | ||
|
|
@@ -21,7 +21,7 @@ | |
| # Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA | ||
|
|
||
| import codecs | ||
| from commands import getoutput | ||
| from subprocess import getoutput | ||
| from subprocess import Popen, PIPE | ||
| from os import access, F_OK | ||
| from os import waitpid | ||
|
|
@@ -32,105 +32,105 @@ def runCmd(cmd): | |
| p = Popen(cmd, shell=True) | ||
| sts = waitpid(p.pid, 0) | ||
| if sts[1] != 0: | ||
| print u"Error while executing command: " + cmd | ||
| print("Error while executing command: " + cmd) | ||
| exit(1) | ||
|
|
||
| def indexHeader(indexFile): | ||
| indexFile.write(u"<html><head><title>Voikon sanastoja</title>") | ||
| indexFile.write(u"<style type='text/css'>") | ||
| indexFile.write(u".small {font-size:0.8em; font-style:italic;}") | ||
| indexFile.write(u"table {border-collapse:collapse;}") | ||
| indexFile.write(u"table td {border:1px solid black;}") | ||
| indexFile.write(u"</style></head>") | ||
| indexFile.write(u"<body><h1>Voikon sanastoja (sanastoformaatin versio 5)</h1>") | ||
| indexFile.write(u"<p>Tämä sivu ja sivulla olevat Voikon sanaston versiot ") | ||
| indexFile.write(u"on generoitu automaattisesti ohjelmalla <kbd>voikko-build-dicts</kbd>. ") | ||
| indexFile.write(u"<strong>Sanastoformaatti 5 toimii libvoikon version 4.0 ja uudempien kanssa.</strong></p>") | ||
| indexFile.write("<html><head><title>Voikon sanastoja</title>") | ||
| indexFile.write("<style type='text/css'>") | ||
| indexFile.write(".small {font-size:0.8em; font-style:italic;}") | ||
| indexFile.write("table {border-collapse:collapse;}") | ||
| indexFile.write("table td {border:1px solid black;}") | ||
| indexFile.write("</style></head>") | ||
| indexFile.write("<body><h1>Voikon sanastoja (sanastoformaatin versio 5)</h1>") | ||
| indexFile.write("<p>Tämä sivu ja sivulla olevat Voikon sanaston versiot ") | ||
| indexFile.write("on generoitu automaattisesti ohjelmalla <kbd>voikko-build-dicts</kbd>. ") | ||
| indexFile.write("<strong>Sanastoformaatti 5 toimii libvoikon version 4.0 ja uudempien kanssa.</strong></p>") | ||
|
|
||
| def indexDict(indexFile, dict): | ||
| indexFile.write(u"<tr><td>Tunniste: <kbd>" + dict.variant + "</kbd><br />") | ||
| indexFile.write(u"Sisältö: <kbd>" + dict.nameFi + "</kbd></br />") | ||
| indexFile.write(u"Sanatietueita Joukahaisesta: <kbd>" + `dict.wordRecords` + "</kbd></td>") | ||
| dictFile = u"dict" + dict.idSuffix + ".zip" | ||
| indexFile.write(u"<td><a href='" + dictFile + "'>" + dictFile + "</a></td></tr>") | ||
| indexFile.write("<tr><td>Tunniste: <kbd>" + dict.variant + "</kbd><br />") | ||
| indexFile.write("Sisältö: <kbd>" + dict.nameFi + "</kbd></br />") | ||
| indexFile.write("Sanatietueita Joukahaisesta: <kbd>" + repr(dict.wordRecords) + "</kbd></td>") | ||
| dictFile = "dict" + dict.idSuffix + ".zip" | ||
| indexFile.write("<td><a href='" + dictFile + "'>" + dictFile + "</a></td></tr>") | ||
|
|
||
| def indexFooter(indexFile): | ||
| indexFile.write(u"</body></html>") | ||
| indexFile.write("</body></html>") | ||
|
|
||
| # === Define dictionary properties === | ||
|
|
||
| class Voikkodict: | ||
| idSuffix = u"" | ||
| variant = u"" | ||
| nameFi = u"" | ||
| nameEn = u"" | ||
| smOptions = u"" | ||
| idSuffix = "" | ||
| variant = "" | ||
| nameFi = "" | ||
| nameEn = "" | ||
| smOptions = "" | ||
| wordRecords = 0 | ||
|
|
||
| allDicts = [] | ||
|
|
||
| d = Voikkodict() | ||
| d.idSuffix = u"" | ||
| d.variant = u"standard" | ||
| d.nameFi = u"suomi (perussanasto)" | ||
| d.nameEn = u"Finnish (basic vocabulary)" | ||
| d.smOptions = u"" | ||
| d.idSuffix = "" | ||
| d.variant = "standard" | ||
| d.nameFi = "suomi (perussanasto)" | ||
| d.nameEn = "Finnish (basic vocabulary)" | ||
| d.smOptions = "" | ||
| allDicts.append(d) | ||
|
|
||
| d = Voikkodict() | ||
| d.idSuffix = u"-erityis" | ||
| d.variant = u"science" | ||
| d.nameFi = u"suomi (matematiikan, fysiikan, kemian, biologian, maantieteen, geologian, lääketieteen, kasvatustieteen ja tietotekniikan sanastot)" | ||
| d.nameEn = u"Finnish (scientific vocabulary)" | ||
| d.smOptions = u'GENLEX_OPTS="--extra-usage=it,medicine,science,nature,education"' | ||
| d.idSuffix = "-erityis" | ||
| d.variant = "science" | ||
| d.nameFi = "suomi (matematiikan, fysiikan, kemian, biologian, maantieteen, geologian, lääketieteen, kasvatustieteen ja tietotekniikan sanastot)" | ||
| d.nameEn = "Finnish (scientific vocabulary)" | ||
| d.smOptions = 'GENLEX_OPTS="--extra-usage=it,medicine,science,nature,education"' | ||
| allDicts.append(d) | ||
|
|
||
| d = Voikkodict() | ||
| d.idSuffix = u"-murre" | ||
| d.variant = u"dialects" | ||
| d.nameFi = u"suomi (murteellisten, vanhojen ja harvinaisten sanojen sanasto)" | ||
| d.nameEn = u"Finnish (dialects)" | ||
| d.smOptions = u'GENLEX_OPTS="--style=dialect,old,international,foreign,inappropriate --min-frequency=10" VANHAT_MUODOT=yes' | ||
| d.idSuffix = "-murre" | ||
| d.variant = "dialects" | ||
| d.nameFi = "suomi (murteellisten, vanhojen ja harvinaisten sanojen sanasto)" | ||
| d.nameEn = "Finnish (dialects)" | ||
| d.smOptions = 'GENLEX_OPTS="--style=dialect,old,international,foreign,inappropriate --min-frequency=10" VANHAT_MUODOT=yes' | ||
| allDicts.append(d) | ||
|
|
||
| d = Voikkodict() | ||
| d.idSuffix = u"-kasvatus" | ||
| d.variant = u"education" | ||
| d.nameFi = u"suomi (kasvatustieteen sanasto)" | ||
| d.nameEn = u"Finnish (education vocabulary)" | ||
| d.smOptions = u'GENLEX_OPTS="--extra-usage=education"' | ||
| d.idSuffix = "-kasvatus" | ||
| d.variant = "education" | ||
| d.nameFi = "suomi (kasvatustieteen sanasto)" | ||
| d.nameEn = "Finnish (education vocabulary)" | ||
| d.smOptions = 'GENLEX_OPTS="--extra-usage=education"' | ||
| allDicts.append(d) | ||
|
|
||
| d = Voikkodict() | ||
| d.idSuffix = u"-laaketiede" | ||
| d.variant = u"medicine" | ||
| d.nameFi = u"suomi (matematiikan, fysiikan, kemian, biologian, maantieteen, geologian ja lääketieteen sanastot)" | ||
| d.nameEn = u"Finnish (medical vocabulary)" | ||
| d.smOptions = u'GENLEX_OPTS="--extra-usage=medicine,science,nature"' | ||
| d.idSuffix = "-laaketiede" | ||
| d.variant = "medicine" | ||
| d.nameFi = "suomi (matematiikan, fysiikan, kemian, biologian, maantieteen, geologian ja lääketieteen sanastot)" | ||
| d.nameEn = "Finnish (medical vocabulary)" | ||
| d.smOptions = 'GENLEX_OPTS="--extra-usage=medicine,science,nature"' | ||
| allDicts.append(d) | ||
|
|
||
| d = Voikkodict() | ||
| d.idSuffix = u"-po" | ||
| d.variant = u"po" | ||
| d.nameFi = u"suomi (po-tiedostojen oikolukusanasto)" | ||
| d.nameEn = u"Finnish (po file spelling vocabulary)" | ||
| d.smOptions = u'GENLEX_OPTS="--extra-usage=it,science"' | ||
| d.idSuffix = "-po" | ||
| d.variant = "po" | ||
| d.nameFi = "suomi (po-tiedostojen oikolukusanasto)" | ||
| d.nameEn = "Finnish (po file spelling vocabulary)" | ||
| d.smOptions = 'GENLEX_OPTS="--extra-usage=it,science"' | ||
| allDicts.append(d) | ||
|
|
||
| d = Voikkodict() | ||
| d.idSuffix = u"-morpho" | ||
| d.variant = u"morpho" | ||
| d.nameFi = u"suomi, erittäin laaja sanasto (mukana myös morfologisessa analyysissä tarvittava lisäinformaatio)" | ||
| d.nameEn = u"Finnish, very extensive vocabulary (with additional information needed in morphological analysis)" | ||
| d.smOptions = u'GENLEX_OPTS="--extra-usage=it,science,nature,medicine,education,orgname --style=dialect,old,international,foreign,inappropriate --min-frequency=10" VANHAT_MUODOT=yes VOIKKO_DEBUG=yes' | ||
| d.idSuffix = "-morpho" | ||
| d.variant = "morpho" | ||
| d.nameFi = "suomi, erittäin laaja sanasto (mukana myös morfologisessa analyysissä tarvittava lisäinformaatio)" | ||
| d.nameEn = "Finnish, very extensive vocabulary (with additional information needed in morphological analysis)" | ||
| d.smOptions = 'GENLEX_OPTS="--extra-usage=it,science,nature,medicine,education,orgname --style=dialect,old,international,foreign,inappropriate --min-frequency=10" VANHAT_MUODOT=yes VOIKKO_DEBUG=yes' | ||
| allDicts.append(d) | ||
|
|
||
| d = Voikkodict() | ||
| d.idSuffix = u"-morphoid" | ||
| d.variant = u"morphoid" | ||
| d.nameFi = u"suomi, erittäin laaja sanasto (mukana myös morfologisessa analyysissä tarvittava lisäinformaatio ja linkitys Joukahaiseen)" | ||
| d.nameEn = u"Finnish, very extensive vocabulary (with additional information needed in morphological analysis and links to Joukahainen)" | ||
| d.smOptions = u'GENLEX_OPTS="--extra-usage=it,science,nature,medicine,education,orgname --style=dialect,old,international,foreign,inappropriate --min-frequency=10 --sourceid" VANHAT_MUODOT=yes VOIKKO_DEBUG=yes' | ||
| d.idSuffix = "-morphoid" | ||
| d.variant = "morphoid" | ||
| d.nameFi = "suomi, erittäin laaja sanasto (mukana myös morfologisessa analyysissä tarvittava lisäinformaatio ja linkitys Joukahaiseen)" | ||
| d.nameEn = "Finnish, very extensive vocabulary (with additional information needed in morphological analysis and links to Joukahainen)" | ||
| d.smOptions = 'GENLEX_OPTS="--extra-usage=it,science,nature,medicine,education,orgname --style=dialect,old,international,foreign,inappropriate --min-frequency=10 --sourceid" VANHAT_MUODOT=yes VOIKKO_DEBUG=yes' | ||
| allDicts.append(d) | ||
|
|
||
| WORK_DIR = "build-v5" | ||
|
|
@@ -181,13 +181,13 @@ if access(oxtdir + OXT_DESCRIPTION, F_OK): | |
| descIn = codecs.open(oxtdir + OXT_DESCRIPTION, "r", "UTF-8") | ||
| descOut = codecs.open(oxtdir + OXT_DESCRIPTION + ".new", "w", "UTF-8") | ||
| line = descIn.readline() | ||
| while (line != u""): | ||
| while (line != ""): | ||
| descOut.write(line) | ||
| if (line.find(u"<display-name>") >= 0): | ||
| if (line.find("<display-name>") >= 0): | ||
| descIn.readline() | ||
| descOut.write(u' <name lang="en-US">Voikko - %s</name>\n' % dict.nameEn) | ||
| descOut.write(' <name lang="en-US">Voikko - %s</name>\n' % dict.nameEn) | ||
| descIn.readline() | ||
| descOut.write(u' <name lang="fi">Voikko - %s</name>\n' % dict.nameFi) | ||
| descOut.write(' <name lang="fi">Voikko - %s</name>\n' % dict.nameFi) | ||
| line = descIn.readline() | ||
| descIn.close() | ||
| descOut.close() | ||
|
|
@@ -196,35 +196,35 @@ if access(oxtdir + OXT_DESCRIPTION, F_OK): | |
|
|
||
| # === Phase 3: build zip packages === | ||
|
|
||
| indexFile.write(u"<h2>Sanastot</h2>") | ||
| indexFile.write(u"<table>") | ||
| indexFile.write("<h2>Sanastot</h2>") | ||
| indexFile.write("<table>") | ||
| for dict in allDicts: | ||
| dirName = WORK_DIR + '/' + DICT_DIR_PREFIX + dict.idSuffix | ||
| zipFile = DICT_DIR_PREFIX + dict.idSuffix + '.zip' | ||
| runCmd('cd ' + dirName + ' && zip -r ../' + zipFile + ' *') | ||
| indexDict(indexFile, dict) | ||
| indexFile.write(u"</table>") | ||
| indexFile.write("</table>") | ||
|
|
||
| # === Phase 4: build source package === | ||
|
|
||
| runCmd('make clean') | ||
| runCmd('make dist-gzip SM_VERSION=snapshot') | ||
| runCmd('cp voikko-fi-snapshot.tar.gz ' + WORK_DIR) | ||
| runCmd('make clean SM_VERSION=snapshot') | ||
| indexFile.write(u"<h2>Lähdekoodi</h2>") | ||
| indexFile.write(u"<p><a href='voikko-fi-snapshot.tar.gz'>voikko-fi-snapshot.tar.gz</a></p>") | ||
| indexFile.write("<h2>Lähdekoodi</h2>") | ||
| indexFile.write("<p><a href='voikko-fi-snapshot.tar.gz'>voikko-fi-snapshot.tar.gz</a></p>") | ||
|
|
||
| # === Finalisation === | ||
|
|
||
| indexFile.write(u"<h2>Lähdekoodin versiotiedot</h2><pre>") | ||
| indexFile.write("<h2>Lähdekoodin versiotiedot</h2><pre>") | ||
| out = getoutput("git log --format=short HEAD^1..HEAD") | ||
| indexFile.write(unicode(out, "UTF-8")) | ||
| indexFile.write(u"</pre><p>Viimeisin päivitys Joukahaisesta") | ||
| indexFile.write(out) | ||
| indexFile.write("</pre><p>Viimeisin päivitys Joukahaisesta") | ||
| out = getoutput("grep 'Time of generation:' vocabulary/joukahainen.xml | sed -e 's/T.*on://'") | ||
| indexFile.write(out) | ||
| indexFile.write(u"</p>") | ||
| indexFile.write("</p>") | ||
| endTime = datetime.now() | ||
| indexFile.write(u"<p class='small'>Generointi valmis " + endTime.isoformat() + u"<br />") | ||
| indexFile.write(u"Aikaa kului " + `(endTime - startTime).seconds` + u" sekuntia</p>") | ||
| indexFile.write("<p class='small'>Generointi valmis " + endTime.isoformat() + "<br />") | ||
| indexFile.write("Aikaa kului " + repr((endTime - startTime).seconds) + " sekuntia</p>") | ||
| indexFooter(indexFile) | ||
| indexFile.close() | ||