From 5a2baae7b396f0926116967ca9492f74aae77fc7 Mon Sep 17 00:00:00 2001
From: Paul Eggert <eggert@cs.ucla.edu>
Date: Mon, 19 Jun 2006 20:33:13 +0000
Subject: [PATCH 1/1] * bootstrap (TP_URL, WGET_COMMAND): New vars.
 (get_translations): New function, which uses HTML scraping to deduce
 locations of latest translations. Use this function to grab both bison and
 bison-runtime .po files. Don't bother priming the pump for the runtime-po
 domain any more, as it's now translated better than bison is.

---
 ChangeLog | 15 +++++++++++
 bootstrap | 78 +++++++++++++++++++++++++------------------------------
 2 files changed, 51 insertions(+), 42 deletions(-)

diff --git a/ChangeLog b/ChangeLog
index e4baf83f..a7022679 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,18 @@
+2006-06-19  Paul Eggert  <eggert@cs.ucla.edu>
+
+	The Translation Project changed its way of publishing translations
+	to maintainers.  I haven't received any responses to my request
+	for supporting the old way, or for documenting the new way.  I
+	have modified 'bootstrap' to use screen scraping
+	(in this case, HTML scraping).  This is unreliable and inelegant,
+	but I don't see any better way.  Yuck.
+	* bootstrap (TP_URL, WGET_COMMAND): New vars.
+	(get_translations): New function, which uses HTML scraping to
+	deduce locations of latest translations.
+	Use this function to grab both bison and bison-runtime .po files.
+	Don't bother priming the pump for the runtime-po domain any more,
+	as it's now translated better than bison is.
+
 2006-06-19  Akim Demaille  <akim@epita.fr>
 
 	* src/scan-gram.l: No longer "parse" things after `%union' until
diff --git a/bootstrap b/bootstrap
index a52c233e..1ed1cd13 100755
--- a/bootstrap
+++ b/bootstrap
@@ -23,6 +23,9 @@
 
 package=bison
 
+# Translation Project URL, for the registry of all projects.
+TP_URL='http://www.iro.umontreal.ca/translation/registry.cgi?domain='
+
 # Ensure file names are sorted consistently across platforms;
 # e.g., m4/ulonglong_gl.m4 should follow m4/ulonglong.m4.
 # Also, ensure diagnostics are in English, e.g., "wget --help" below.
@@ -168,6 +171,34 @@ sed '
 
 # Get translations.
 
+get_translations() {
+  subdir=$1
+  domain=$2
+
+  echo "$0: getting translations into $subdir for $domain..."
+  (cd $subdir && rm -f dummy `ls | sed -n '/\.gmo$/p; /\.po/p'`) &&
+
+  $WGET_COMMAND -O "$subdir/$domain.html" "$TP_URL$domain" &&
+
+  sed -n 's|.*"http://[^"]*/translation/teams/PO/\([^/"]*\)/'"$domain"'-\([^/"]*\)\.[^."]*\.po".*|\1.\2|p' <"$subdir/$domain.html" |
+  sort -k 1,1 -k 2,2n -k2,2 -k3,3n -k3,3 -k4,4n -k4,4 -k5,5n -k5.5 |
+  awk -F. '
+    { if (lang && $1 != lang) print lang, ver }
+    { lang = $1; ver = substr($0, index($0, ".") + 1) }
+    END { if (lang) print lang, ver }
+  ' | awk -v domain="$domain" -v subdir="$subdir" '
+    {
+      lang = $1
+      ver = $2
+      urlfmt = ""
+      printf "$WGET_COMMAND -O %s/%s.po 'http://www.iro.umontreal.ca/translation/teams/PO/%s/%s-%s.%s.po' &&\n", subdir, lang, lang, domain, ver, lang
+    }
+    END { print ":" }
+  ' | sh &&
+  ls "$subdir"/*.po | sed 's|.*/||; s|\.po$||' >"$subdir/LINGUAS" &&
+  rm "$subdir/$domain.html"
+}
+
 case $SKIP_PO in
 '')
   case `wget --help` in
@@ -179,51 +210,14 @@ case $SKIP_PO in
     no_cache='';;
   esac
 
-  echo "$0: getting translations into po (please ignore the robots.txt ERROR 404)..."
-  (cd po &&
-   rm -f dummy `ls | sed -n '/\.gmo$/p; /\.po/p'` &&
-   wget -nv -nd -r -l 1 -A .po $no_cache \
-     http://www.iro.umontreal.ca/translation/maint/$package/ &&
-   ls *.po | sed 's/\.po$//' >LINGUAS
-  ) || exit
+  WGET_COMMAND="wget -nv $no_cache"
+  export WGET_COMMAND
+
+  get_translations po $package || exit
 
   case $package in
   bison)
-    echo "$0: getting translations into po (please ignore the robots.txt ERROR 404)..."
-    (cd runtime-po &&
-     rm -f dummy `ls | sed -n '/\.gmo$/p; /\.po$/p'` &&
-     wget -nv -nd -r -l 1 -A .po $no_cache \
-       http://www.iro.umontreal.ca/translation/maint/$package-runtime/ &&
-
-     # For translations that have not yet been upgraded to the new
-     # runtime-po domain, prime the pump by extracting the relevant
-     # strings from the obsolete translations.
-     # This code can be removed once the bison-runtime domain
-     # has been translated by each team.
-     for po in ../po/*.po; do
-       test -f "$po" || continue
-       runpo=`basename $po`
-       test -f $runpo || {
-	 msggrep -K \
-	     -e 'memory exhausted' \
-	     -e 'syntax error' \
-	     $po 2>/dev/null |
-	   sed '
-	     s/^#~ //
-	     /^msgid "syntax error; also memory exhausted"$/,/^$/d
-	     /^$/,${ /^#/d; }
-	   ' >$runpo-
-	 if cmp -s $runpo- $runpo; then
-	   rm $runpo-
-	 else
-	   mv $runpo- $runpo
-	 fi
-	 test -s $runpo || rm -f $runpo
-       } || exit
-     done &&
-
-     ls *.po | sed 's/\.po$//' >LINGUAS
-    ) || exit
+    get_translations runtime-po $package-runtime || exit
   esac;;
 esac
 
-- 
2.45.2