mirror of https://github.com/apache/lucene.git
LUCENE-2517: improve changes-to-html
git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@960374 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Michael McCandless
parent
e6e18a81f6
commit
0e631b8031
|
|
@ -23,17 +23,17 @@ Changes in backwards compatibility policy
|
|||
|
||||
- Directory.copy/Directory.copyTo now copies all files (not just
|
||||
index files), since what is and isn't and index file is now
|
||||
dependent on the codecs used. (Mike McCandless)
|
||||
dependent on the codecs used.
|
||||
|
||||
- UnicodeUtil now uses BytesRef for UTF-8 output, and some method
|
||||
signatures have changed to CharSequence. These are internal APIs
|
||||
and subject to change suddenly. (Robert Muir, Mike McCandless)
|
||||
and subject to change suddenly.
|
||||
|
||||
- Positional queries (PhraseQuery, *SpanQuery) will now throw an
|
||||
exception if use them on a field that omits positions during
|
||||
indexing (previously they silently returned no results).
|
||||
|
||||
- FieldCache.(Byte,Short,Int,Long,Float,Double}Parser's API has
|
||||
- FieldCache.{Byte,Short,Int,Long,Float,Double}Parser's API has
|
||||
changed -- each parse method now takes a BytesRef instead of a
|
||||
String. If you have an existing Parser, a simple way to fix it is
|
||||
invoke BytesRef.utf8ToString, and pass that String to your
|
||||
|
|
@ -57,6 +57,8 @@ Changes in backwards compatibility policy
|
|||
an IllegalArgumentException, because the NTS does not support
|
||||
TermAttribute/CharTermAttribute. If you want to further filter
|
||||
or attach Payloads to NTS, use the new NumericTermAttribute.
|
||||
|
||||
(Mike McCandless, Robert Muir, Uwe Schindler, Mark Miller, Michael Busch)
|
||||
|
||||
* LUCENE-2386: IndexWriter no longer performs an empty commit upon new index
|
||||
creation. Previously, if you passed an empty Directory and set OpenMode to
|
||||
|
|
@ -119,7 +121,7 @@ New features
|
|||
|
||||
* LUCENE-1990: Adds internal packed ints implementation, to be used
|
||||
for more efficient storage of int arrays when the values are
|
||||
bounded, for example for storing the terms dict index Toke Toke
|
||||
bounded, for example for storing the terms dict index (Toke
|
||||
Eskildsen via Mike McCandless)
|
||||
|
||||
* LUCENE-2321: Cutover to a more RAM efficient packed-ints based
|
||||
|
|
@ -215,7 +217,8 @@ Changes in backwards compatibility policy
|
|||
the IndexWriter for a MergePolicy exactly once. You can change references to
|
||||
'writer' from <code>writer.doXYZ()</code> to <code>writer.get().doXYZ()</code>
|
||||
(it is also advisable to add an <code>assert writer != null;</code> before you
|
||||
access the wrapped IndexWriter.
|
||||
access the wrapped IndexWriter.)
|
||||
|
||||
In addition, MergePolicy only exposes a default constructor, and the one that
|
||||
took IndexWriter as argument has been removed from all MergePolicy extensions.
|
||||
(Shai Erera via Mike McCandless)
|
||||
|
|
@ -265,6 +268,7 @@ Changes in runtime behavior
|
|||
invokes a merge on the incoming and target segments, but instead copies the
|
||||
segments to the target index. You can call maybeMerge or optimize after this
|
||||
method completes, if you need to.
|
||||
|
||||
In addition, Directory.copyTo* were removed in favor of copy which takes the
|
||||
target Directory, source and target files as arguments, and copies the source
|
||||
file to the target Directory under the target file name. (Shai Erera)
|
||||
|
|
@ -353,9 +357,9 @@ API Changes
|
|||
next commit). (Shai Erera)
|
||||
|
||||
* LUCENE-2455: IndexWriter.addIndexesNoOptimize was renamed to addIndexes.
|
||||
IndexFileNames.segmentFileName now takes another parameter to accomodate
|
||||
IndexFileNames.segmentFileName now takes another parameter to accommodate
|
||||
custom file names. You should use this method to name all your files.
|
||||
(Shai Erera)
|
||||
(Shai Erera)
|
||||
|
||||
* LUCENE-2481: SnapshotDeletionPolicy.snapshot() and release() were replaced
|
||||
with equivalent ones that take a String (id) as argument. You can pass
|
||||
|
|
|
|||
|
|
@ -62,8 +62,8 @@ for (my $line_num = 0 ; $line_num <= $#lines ; ++$line_num) {
|
|||
|
||||
if (/\s*===+\s*(.*?)\s*===+\s*/) { # New-style release headings
|
||||
$release = $1;
|
||||
$release =~ s/^release\s*//i; # Trim "Release " prefix
|
||||
($release, $relinfo) = ($release =~ /^(\d+(?:\.\d+)*|Trunk)\s*(.*)/i);
|
||||
$release =~ s/^(?:release|lucene)\s*//i; # Trim "Release " or "Lucene " prefix
|
||||
($release, $relinfo) = ($release =~ /^(\d+(?:\.(?:\d+|[xyz]))*|Trunk)\s*(.*)/i);
|
||||
$relinfo =~ s/\s*:\s*$//; # Trim trailing colon
|
||||
$relinfo =~ s/^\s*,\s*//; # Trim leading comma
|
||||
($reldate, $relinfo) = get_release_date($release, $relinfo);
|
||||
|
|
@ -164,6 +164,14 @@ for (my $line_num = 0 ; $line_num <= $#lines ; ++$line_num) {
|
|||
}
|
||||
}
|
||||
|
||||
# Recognize IDs of top level nodes of the most recent two releases,
|
||||
# escaping JavaScript regex metacharacters, e.g.: "^(?:trunk|2\\\\.4\\\\.0)"
|
||||
my $first_relid_regex = $first_relid;
|
||||
$first_relid_regex =~ s!([.+*?{}()|^$/\[\]\\])!\\\\\\\\$1!g;
|
||||
my $second_relid_regex = $second_relid;
|
||||
$second_relid_regex =~ s!([.+*?{}()|^$/\[\]\\])!\\\\\\\\$1!g;
|
||||
my $newer_version_regex = "^(?:$first_relid_regex|$second_relid_regex)";
|
||||
|
||||
#
|
||||
# Print HTML-ified version to STDOUT
|
||||
#
|
||||
|
|
@ -258,7 +266,7 @@ print<<"__HTML_HEADER__";
|
|||
|
||||
}
|
||||
|
||||
var newerRegex = new RegExp("^(?:trunk|2\\\\.4\\\\.0)");
|
||||
var newerRegex = new RegExp("$newer_version_regex");
|
||||
function isOlder(listId) {
|
||||
return ! newerRegex.test(listId);
|
||||
}
|
||||
|
|
@ -388,16 +396,21 @@ for my $rel (@releases) {
|
|||
|
||||
for my $itemnum (1..$#{$items}) {
|
||||
my $item = $items->[$itemnum];
|
||||
$item =~ s:&:&:g; # Escape HTML metachars,
|
||||
$item =~ s:<(?!/?code>):<:gi; # but leave <code> tags intact
|
||||
$item =~ s:(?<!code)>:>:gi; # and add <pre> tags so that
|
||||
$item =~ s:<code>:<code><pre>:gi; # whitespace is preserved in the
|
||||
$item =~ s:\s*</code>:</pre></code>:gi; # output.
|
||||
$item =~ s:&:&:g; # Escape HTML metachars, but leave
|
||||
$item =~ s:<(?!/?code>):<:gi; # <code> tags intact and add <pre>
|
||||
$item =~ s:(?<!code)>:>:gi; # wrappers for non-inline sections
|
||||
$item =~ s{((?:^|.*\n)\s*)<code>(?!</code>.+)(.+)</code>(?![ \t]*\S)}
|
||||
{
|
||||
my $prefix = $1;
|
||||
my $code = $2;
|
||||
$code =~ s/\s+$//;
|
||||
"$prefix<code><pre>$code</pre></code>"
|
||||
}gise;
|
||||
|
||||
# Put attributions on their own lines.
|
||||
# Check for trailing parenthesized attribution with no following period.
|
||||
# Exclude things like "(see #3 above)" and "(use the bug number instead of xxxx)"
|
||||
unless ($item =~ s:\s*(\((?!see #|use the bug number)[^)"]+?\))\s*$:\n<br /><span class="attrib">$1</span>:) {
|
||||
unless ($item =~ s:\s*(\((?!see #|use the bug number)[^()"]+?\))\s*$:\n<br /><span class="attrib">$1</span>:) {
|
||||
# If attribution is not found, then look for attribution with a
|
||||
# trailing period, but try not to include trailing parenthesized things
|
||||
# that are not attributions.
|
||||
|
|
@ -405,9 +418,9 @@ for my $rel (@releases) {
|
|||
# Rule of thumb: if a trailing parenthesized expression with a following
|
||||
# period does not contain "LUCENE-XXX", and it either has three or
|
||||
# fewer words or it includes the word "via" or the phrase "updates from",
|
||||
# then it is considered to be an attribution.
|
||||
# then it is considered to be an attribution.
|
||||
|
||||
$item =~ s{(\s*(\((?!see \#|use the bug number)[^)"]+?\)))
|
||||
$item =~ s{(\s*(\((?!see \#|use the bug number)[^()"]+?\)))
|
||||
((?:\.|(?i:\.?\s*Issue\s+\d{3,}|LUCENE-\d+)\.?)\s*)$}
|
||||
{
|
||||
my $subst = $1; # default: no change
|
||||
|
|
|
|||
Loading…
Reference in New Issue