view doc/Makefile @ 29322:66dbdd3cc2b9 stable

bdiff: extend matches across popular lines

For very large diffs that have large numbers of identical lines (JSON
dumps) that also have large blocks of identical text, bdiff could become
confused about which block matches which because it can only match
very limited regions. The result is very large diffs for small sets of edits.

The earlier recursion rebalancing fix made this behavior more frequent because
it's now more prone to match block 1 to block 2. One frequent user of
large JSON files reported being unable to pass the resulting diffs
through their code review system.

Prior to this change, bdiff would calculate the length of a match at
(i, j) as 1 + length found at (i-1, j-1). With large number of popular
(ignored) lines, this often meant matches couldn't be extended
backwards at all and thus all matching regions were very small.
Disabling the popularity threshold is not an option because it brings
back quadratic behavior.

Instead, we extend a match backwards until we either found a previously
discovered match or we find a mismatching line. This thus successfully
bridges over any popular lines inside and before a matching region.
The larger regions then significant reduce the probability of confusion.

SOURCES=$(notdir $(wildcard ../mercurial/help/*.[0-9].txt))
MAN=$(SOURCES:%.txt=%)
HTML=$(SOURCES:%.txt=%.html)
GENDOC=gendoc.py ../mercurial/commands.py ../mercurial/help.py \
	../mercurial/help/*.txt ../hgext/*.py ../hgext/*/__init__.py
PREFIX=/usr/local
MANDIR=$(PREFIX)/share/man
INSTALL=install -c -m 644
PYTHON=python
RSTARGS=

export HGENCODING=UTF-8

all: man html

man: $(MAN)

html: $(HTML)

common.txt $(SOURCES) $(SOURCES:%.txt=%.gendoc.txt): $(GENDOC)
	${PYTHON} gendoc.py $(basename $@) > $@.tmp
	mv $@.tmp $@

%: %.txt %.gendoc.txt common.txt
	$(PYTHON) runrst hgmanpage $(RSTARGS) --halt warning \
	  --strip-elements-with-class htmlonly $*.txt $*

%.html: %.txt %.gendoc.txt common.txt
	$(PYTHON) runrst html $(RSTARGS) --halt warning \
	  --link-stylesheet --stylesheet-path style.css $*.txt $*.html

MANIFEST: man html
# tracked files are already in the main MANIFEST
	$(RM) $@
	for i in $(MAN) $(HTML); do \
	  echo "doc/$$i" >> $@ ; \
	done

install: man
	for i in $(MAN) ; do \
	  subdir=`echo $$i | sed -n 's/^.*\.\([0-9]\)$$/man\1/p'` ; \
	  mkdir -p $(DESTDIR)$(MANDIR)/$$subdir ; \
	  $(INSTALL) $$i $(DESTDIR)$(MANDIR)/$$subdir ; \
	done

clean:
	$(RM) $(MAN) $(HTML) common.txt $(SOURCES) $(SOURCES:%.txt=%.gendoc.txt) MANIFEST