.\" Automatically generated by Pod::Man 4.14 (Pod::Simple 3.43)
.\"
.\" Standard preamble:
.\" ========================================================================
.de Sp \" Vertical space (when we can't use .PP)
.if t .sp .5v
.if n .sp
..
.de Vb \" Begin verbatim text
.ft CW
.nf
.ne \\$1
..
.de Ve \" End verbatim text
.ft R
.fi
..
.\" Set up some character translations and predefined strings.  \*(-- will
.\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left
.\" double quote, and \*(R" will give a right double quote.  \*(C+ will
.\" give a nicer C++.  Capital omega is used to do unbreakable dashes and
.\" therefore won't be available.  \*(C` and \*(C' expand to `' in nroff,
.\" nothing in troff, for use with C<>.
.tr \(*W-
.ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p'
.ie n \{\
.    ds -- \(*W-
.    ds PI pi
.    if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch
.    if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\"  diablo 12 pitch
.    ds L" ""
.    ds R" ""
.    ds C` ""
.    ds C' ""
'br\}
.el\{\
.    ds -- \|\(em\|
.    ds PI \(*p
.    ds L" ``
.    ds R" ''
.    ds C`
.    ds C'
'br\}
.\"
.\" Escape single quotes in literal strings from groff's Unicode transform.
.ie \n(.g .ds Aq \(aq
.el       .ds Aq '
.\"
.\" If the F register is >0, we'll generate index entries on stderr for
.\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index
.\" entries marked with X<> in POD.  Of course, you'll have to process the
.\" output yourself in some meaningful fashion.
.\"
.\" Avoid warning from groff about undefined register 'F'.
.de IX
..
.nr rF 0
.if \n(.g .if rF .nr rF 1
.if (\n(rF:(\n(.g==0)) \{\
.    if \nF \{\
.        de IX
.        tm Index:\\$1\t\\n%\t"\\$2"
..
.        if !\nF==2 \{\
.            nr % 0
.            nr F 2
.        \}
.    \}
.\}
.rr rF
.\"
.\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2).
.\" Fear.  Run.  Save yourself.  No user-serviceable parts.
.    \" fudge factors for nroff and troff
.if n \{\
.    ds #H 0
.    ds #V .8m
.    ds #F .3m
.    ds #[ \f1
.    ds #] \fP
.\}
.if t \{\
.    ds #H ((1u-(\\\\n(.fu%2u))*.13m)
.    ds #V .6m
.    ds #F 0
.    ds #[ \&
.    ds #] \&
.\}
.    \" simple accents for nroff and troff
.if n \{\
.    ds ' \&
.    ds ` \&
.    ds ^ \&
.    ds , \&
.    ds ~ ~
.    ds /
.\}
.if t \{\
.    ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u"
.    ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u'
.    ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u'
.    ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u'
.    ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u'
.    ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u'
.\}
.    \" troff and (daisy-wheel) nroff accents
.ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V'
.ds 8 \h'\*(#H'\(*b\h'-\*(#H'
.ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#]
.ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H'
.ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u'
.ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#]
.ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#]
.ds ae a\h'-(\w'a'u*4/10)'e
.ds Ae A\h'-(\w'A'u*4/10)'E
.    \" corrections for vroff
.if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u'
.if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u'
.    \" for low resolution devices (crt and lpr)
.if \n(.H>23 .if \n(.V>19 \
\{\
.    ds : e
.    ds 8 ss
.    ds o a
.    ds d- d\h'-1'\(ga
.    ds D- D\h'-1'\(hy
.    ds th \o'bp'
.    ds Th \o'LP'
.    ds ae ae
.    ds Ae AE
.\}
.rm #[ #] #H #V #F C
.\" ========================================================================
.\"
.IX Title "Text::WordDiff 3pm"
.TH Text::WordDiff 3pm "2022-12-12" "perl v5.36.0" "User Contributed Perl Documentation"
.\" For nroff, turn off justification.  Always turn off hyphenation; it makes
.\" way too many mistakes in technical documents.
.if n .ad l
.nh
.SH "Name"
.IX Header "Name"
Text::WordDiff \- Track changes between documents
.SH "Synopsis"
.IX Header "Synopsis"
.Vb 1
\&    use Text::WordDiff;
\&
\&    my $diff = word_diff \*(Aqfile1.txt\*(Aq, \*(Aqfile2.txt\*(Aq, { STYLE => \*(AqHTML\*(Aq };
\&    my $diff = word_diff \e$string1,   \e$string2,   { STYLE => \*(AqANSIColor\*(Aq };
\&    my $diff = word_diff \e*FH1,       \e*FH2;       \e%options;
\&    my $diff = word_diff \e&reader1,   \e&reader2;
\&    my $diff = word_diff \e@records1,  \e@records2;
\&
\&    # May also mix input types:
\&    my $diff = word_diff \e@records1,  \*(Aqfile_B.txt\*(Aq;
.Ve
.SH "Description"
.IX Header "Description"
This module is a variation on the lovely Text::Diff module.
Rather than generating traditional line-oriented diffs, however, it generates
word-oriented diffs. This can be useful for tracking changes in narrative
documents or documents with very long lines. To diff source code, one is still
best off using Text::Diff. But if you want to see how a short
story changed from one version to the next, this module will do the job very
nicely.
.SS "What is a Word?"
.IX Subsection "What is a Word?"
I'm glad you asked! Well, sort of. It's a really hard question to answer. I
consulted a number of sources, but really just did my best to punt on the
question by reformulating it as, \*(L"How do I split text up into individual
words?\*(R" The short answer is to split on word boundaries. However, every word
has two boundaries, one at the beginning and one at the end. So splitting on
\&\f(CW\*(C`/\eb/\*(C'\fR didn't work so well. What I really wanted to do was to split on the
\&\fIbeginning\fR of every word. Fortunately, _Mastering Regular Expressions_ has a
recipe for that: \f(CW\*(C`/(?<!\ew)(?=\ew)/\*(C'\fR. I've borrowed this regular expression
for use in Perls before 5.6.x, but go for the Unicode variant in 5.6.0 and
newer: \f(CW\*(C`/(?<!\ep{IsWord})(?=\ep{IsWord})/\*(C'\fR. Adding some additional controls
for punctuation and control characters, this sentence, for example, would be
split up into the following tokens:
.PP
.Vb 10
\&  my @words = (
\&      "Adding ",
\&      "some ",
\&      "additional ",
\&      "controls",
\&      "\en",
\&      "for ",
\&      "punctuation ",
\&      "and ",
\&      "control ",
\&      "characters",
\&      ", ",
\&      "this ",
\&      "sentence",
\&      ", ",
\&      "for ",
\&      "example",
\&      ", ",
\&      "would ",
\&      "be",
\&      "\en",
\&      "split ",
\&      "up ",
\&      "into ",
\&      "the ",
\&      "following ",
\&      "tokens",
\&      ":",
\&  );
.Ve
.PP
So it's not just comparing words, but word-like tokens and control/punctuation
tokens. This makes sense to me, at least, as the diff is between these tokens,
and thus leads to a nice word-and-space-and-punctuation type diff. It's not
unlike what a word processor might do (although a lot of them are
character-based, but that seemed a bit extreme\*(--feel free to dupe this module
into Text::CharDiff!).
.PP
Now, I acknowledge that there are localization issues with this approach. In
particular, it will fail with Chinese, Japanese, and Korean text, as these
languages don't put non-word characters between words. Ideally, Test::WordDiff
would then split on every character (since a single character often equals a
word), but such is not the case when the \f(CW\*(C`utf8\*(C'\fR flag is set on a string.
For example, This simple script:
.PP
.Vb 6
\&  use strict;
\&  use utf8;
\&  use Data::Dumper;
\&  my $string = \*(AqXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX\*(Aq;
\&  my @tokens = split /(?<!\ep{IsWord})(?=\ep{IsWord})/msx, $string;
\&  print Dumper \e@tokens;
.Ve
.PP
Outputs:
.PP
.Vb 3
\&  $VAR1 = [
\&            "\ex{bf08}\ex{bf09}\ex{bf18}\ex{bf19}\ex{bf1b}\ex{bf1c}\ex{bf1d}\ex{bf40}\ex{bf41}\ex{bf44}\ex{bf48}\ex{bf50}\ex{bf51}\ex{bf55}\ex{bf94}\ex{bfb0}\ex{bfc5}\ex{bfcc}\ex{bfcd}\ex{bfd0}\ex{bfd4}\ex{bfdc}\ex{bfdf}\ex{bfe1}\ex{c03c}\ex{c051}\ex{c058}\ex{c05c}\ex{c060}\ex{c068}\ex{c069}\ex{c090}"
\&          ];
.Ve
.PP
Not so useful. It seems to be less of a problem if the \f(CW\*(C`use utf8;\*(C'\fR line is
commented out, in which case we get:
.PP
.Vb 10
\&  $VAR1 = [
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(Aq?\*(Aq,
\&            \*(Aq?X\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq,
\&            \*(AqX\*(Aq
\&          ];
.Ve
.PP
Someone whose more familiar with non-space-using languages will have to
explain to me how I might be able to duplicate this pattern within the scope
of \f(CW\*(C`use utf8;\*(C'\fR, seing as it may very well be important to have it on in order
to ensure proper character semantics.
.PP
However, if my word tokenization approach is just too naive, and you decide
that you need to take a different approach (maybe use
Lingua::ZH::Toke or similar module), you can still use
this module; you'll just have to tokenize your strings into words yourself,
and pass them to \fBword_diff()\fR as array references:
.PP
.Vb 1
\&  word_diff \e@my_words1, \e@my_words2;
.Ve
.SH "Options"
.IX Header "Options"
\&\fBword_diff()\fR takes two arguments from which to draw input and an optional hash
reference of options to control its output. The first two arguments contain
the data to be diffed, and each may be in the form of any of the following
(that is, they can be in two different formats):
.IP "\(bu" 4
String
.Sp
A bare scalar will be assumed to be a file name. The file will be opened and
split up into words. \fBword_diff()\fR will also \f(CW\*(C`stat\*(C'\fR the file to get the last
modified time for use in the header, unless the relevant option (\f(CW\*(C`MTIME_A\*(C'\fR or
\&\f(CW\*(C`MTIME_B\*(C'\fR) has been specified explicitly.
.IP "\(bu" 4
Scalar Reference
.Sp
A scalar reference will be assumed to refer to a string. That string will be
split up into words.
.IP "\(bu" 4
Array Reference
.Sp
An array reference will be assumed to be a list of words.
.IP "\(bu" 4
File Handle
.Sp
A glob or IO::Handle\-derived object will be read from and split up into
its constituent words.
.PP
The optional hash reference may contain the following options. Additional
options may be specified by the formattting class; see the specific class for
details.
.IP "\(bu" 4
\&\s-1STYLE\s0
.Sp
\&\*(L"ANSIColor\*(R", \*(L"\s-1HTML\*(R"\s0 or an object or class name for a class providing
\&\f(CW\*(C`file_header()\*(C'\fR, \f(CW\*(C`hunk_header()\*(C'\fR, \f(CW\*(C`same_items()\*(C'\fR, \f(CW\*(C`delete_items()\*(C'\fR,
\&\f(CW\*(C`insert_items()\*(C'\fR, \f(CW\*(C`hunk_footer()\*(C'\fR and \f(CW\*(C`file_footer()\*(C'\fR methods. Defaults to
\&\*(L"ANSIColor\*(R" for nice display of diffs in an \s-1ANSI\s0 Color-supporting terminal.
.Sp
If the package indicated by the \f(CW\*(C`STYLE\*(C'\fR has no \f(CW\*(C`new()\*(C'\fR method,
\&\f(CW\*(C`word_diff()\*(C'\fR will load it automatically (lazy loading). It will then
instantiate an object of that class, passing in the options hash reference
with which the formatting class can initialize the object.
.Sp
Styles may be specified as class names (\f(CW\*(C`STYLE => "My::Foo"\*(C'\fR), in which
case they will be instantiated by calling the \f(CW\*(C`new()\*(C'\fR construcctor and
passing in the options hash reference, or as objects (\f(CW\*(C`STYLE =>
My::Foo\->new\*(C'\fR).
.Sp
The simplest way to implement your own formatting style is to create a new
class that inherits from Text::WordDiff::Base, wherein the \f(CW\*(C`new()\*(C'\fR method is
already provided, and the \f(CW\*(C`file_header()\*(C'\fR returns a Unified diff-style
header. All of the other formatting methods simply return empty strings, and
are therefore ripe for overriding.
.IP "\(bu" 4
\&\s-1FILENAME_A, MTIME_A, FILENAME_B, MTIME_B\s0
.Sp
The name of the file and the modification time \*(L"files\*(R" in epoch seconds.
Unless a defined value is specified for these options, they will be filled in
for each file when \fBword_diff()\fR is passed a filename. If a filename is not
passed in and \f(CW\*(C`FILENAME_A\*(C'\fR and \f(CW\*(C`FILENAME_B\*(C'\fR are not defined, the header will
not be printed by the base formatting base class.
.IP "\(bu" 4
\&\s-1OUTPUT\s0
.Sp
The method by which diff output should be, well, \fIoutput\fR. Examples and their
equivalent subroutines:
.Sp
.Vb 4
\&    OUTPUT => \e*FOOHANDLE,   # like: sub { print FOOHANDLE shift() }
\&    OUTPUT => \e$output,      # like: sub { $output .= shift }
\&    OUTPUT => \e@output,      # like: sub { push @output, shift }
\&    OUTPUT => sub { $output .= shift },
.Ve
.Sp
If \f(CW\*(C`OUTPUT\*(C'\fR is not defined, \fBword_diff()\fR will simply return the diff as a
string. If \f(CW\*(C`OUTPUT\*(C'\fR is a code reference, it will be called once with the file
header, once for each hunk body, and once for each piece of content. If
\&\f(CW\*(C`OUTPUT\*(C'\fR is an IO::Handle\-derived object, output will be
sent to that handle.
.IP "\(bu" 4
\&\s-1FILENAME_PREFIX_A, FILENAME_PREFIX_B\s0
.Sp
The string to print before the filename in the header. Defaults are \f(CW"\-\-\-"\fR,
\&\f(CW"+++"\fR.
.IP "\(bu" 4
\&\s-1DIFF_OPTS\s0
.Sp
A hash reference to be passed as the options to \f(CW\*(C`Algorithm::Diff\->new\*(C'\fR.
See Algorithm::Diff for details on available options.
.SH "Formatting Classes"
.IX Header "Formatting Classes"
Text::WordDiff comes with two formatting classes:
.IP "Text::WordDiff::ANSIColor" 4
.IX Item "Text::WordDiff::ANSIColor"
This is the default formatting class. It emits a header and then the diff
content, with deleted text in bodfaced red and inserted text in boldfaced
green.
.IP "Text::WordDiff::HTML" 4
.IX Item "Text::WordDiff::HTML"
Specify \f(CW\*(C`STYLE => \*(AqHTML\*(Aq\*(C'\fR to take advantage of this formatting class. It
outputs the diff content as \s-1XHTML,\s0 with deleted text in \f(CW\*(C`<del>\*(C'\fR elements
and inserted text in \f(CW\*(C`<ins>\*(C'\fR elements.
.PP
To implement your own formatting class, simply inherit from
Text::WordDiff::Base and override its methods as necssary. By default,
only the \f(CW\*(C`file_header()\*(C'\fR formatting method returns a value. All others
simply return empty strings, and are therefore ripe for overriding:
.PP
.Vb 2
\&  package My::WordDiff::Format;
\&  use base \*(AqText::WordDiff::Base\*(Aq;
\&
\&  sub file_footer { return "End of diff\en"; }
.Ve
.PP
The methods supplied by the base class are:
.ie n .IP """new()""" 4
.el .IP "\f(CWnew()\fR" 4
.IX Item "new()"
Constructs and returns a new formatting object. It takes a single hash
reference as its argument, and uses it to construct the object. The nice thing
about this is that if you want to support other options in your formatting
class, you can just use them in the formatting object constructed by the
Text::WordDiff::Base class and document that they can be passed as
part of the options hash refernce to \fBword_diff()\fR.
.ie n .IP """file_header()""" 4
.el .IP "\f(CWfile_header()\fR" 4
.IX Item "file_header()"
Called once for a single call to \f(CW\*(C`word_diff()\*(C'\fR, this method outputs the
header for the whole diff. This is the only formatting method in the base
class that returns anything other than an empty string. It collects the
filenames from \f(CW\*(C`filname_a()\*(C'\fR and \f(CW\*(C`filename_b()\*(C'\fR and, if they're defined,
uses the relevant prefixes and modification times to return a unified
diff-style header.
.ie n .IP """hunk_header()""" 4
.el .IP "\f(CWhunk_header()\fR" 4
.IX Item "hunk_header()"
This method is called for each diff hunk. It should output any necessary
header for the hunk.
.ie n .IP """same_items()""" 4
.el .IP "\f(CWsame_items()\fR" 4
.IX Item "same_items()"
This method is called for items that have not changed between the two
sequnces being compared. The unchanged items will be passed as a
list to the method.
.ie n .IP """delete_items""" 4
.el .IP "\f(CWdelete_items\fR" 4
.IX Item "delete_items"
This method is called for items in the first sequence that are not present in
the second sequcne. The deleted items will be passed as a list to the method.
.ie n .IP """insert_items""" 4
.el .IP "\f(CWinsert_items\fR" 4
.IX Item "insert_items"
This method is called for items in the second sequence that are not present in
the first sequcne. The inserted items will be passed as a list to the method.
.ie n .IP """hunk_footer""" 4
.el .IP "\f(CWhunk_footer\fR" 4
.IX Item "hunk_footer"
This method is called at the end of a hunk. It should output any necessary
content to close out the hunk.
.ie n .IP """file_footer()""" 4
.el .IP "\f(CWfile_footer()\fR" 4
.IX Item "file_footer()"
This method is called once when the whole diff has been procssed. It should
output any necessary content to close out the diff file.
.ie n .IP """filename_a""" 4
.el .IP "\f(CWfilename_a\fR" 4
.IX Item "filename_a"
This accessor returns the value specified for the \f(CW\*(C`FILENAME_A\*(C'\fR option
to \fBword_diff()\fR.
.ie n .IP """filename_b""" 4
.el .IP "\f(CWfilename_b\fR" 4
.IX Item "filename_b"
This accessor returns the value specified for the \f(CW\*(C`FILENAME_B\*(C'\fR option
to \fBword_diff()\fR.
.ie n .IP """mtime_a""" 4
.el .IP "\f(CWmtime_a\fR" 4
.IX Item "mtime_a"
This accessor returns the value specified for the \f(CW\*(C`MTIME_A\*(C'\fR option to
\&\fBword_diff()\fR.
.ie n .IP """mtime_b""" 4
.el .IP "\f(CWmtime_b\fR" 4
.IX Item "mtime_b"
This accessor returns the value specified for the \f(CW\*(C`MTIME_B\*(C'\fR option to
\&\fBword_diff()\fR.
.ie n .IP """filename_prefix_a""" 4
.el .IP "\f(CWfilename_prefix_a\fR" 4
.IX Item "filename_prefix_a"
This accessor returns the value specified for the \f(CW\*(C`FILENAME_PREFIX_A\*(C'\fR option
to \fBword_diff()\fR.
.ie n .IP """filename_prefix_b""" 4
.el .IP "\f(CWfilename_prefix_b\fR" 4
.IX Item "filename_prefix_b"
This accessor returns the value specified for the \f(CW\*(C`FILENAME_PREFIX_B\*(C'\fR option
to \fBword_diff()\fR.
.SH "See Also"
.IX Header "See Also"
.IP "Text::Diff" 4
.IX Item "Text::Diff"
Inspired the interface and implementation of this module. Thanks Barry!
.IP "Text::ParagraphDiff" 4
.IX Item "Text::ParagraphDiff"
A module that attempts to diff paragraphs and the words in them.
.IP "Algorithm::Diff" 4
.IX Item "Algorithm::Diff"
The module that makes this all possible.
.SH "Support"
.IX Header "Support"
This module is stored in an open GitHub
repository <http://github.com/theory/text-worddiff/>. Feel free to fork and
contribute!
.PP
Please file bug reports via GitHub
Issues <http://github.com/theory/text-worddiff/issues/> or by sending mail to
bug\-Text\-WordDiff@rt.cpan.org <mailto:bug-Text-WordDiff@rt.cpan.org>.
.SH "Author"
.IX Header "Author"
David E. Wheeler <david@justatheory.com>
.PP
Currently maintained by the developers of The Perl Shop <tps@cpan.org>.
.SH "Copyright and License"
.IX Header "Copyright and License"
Copyright (c) 2005\-2011 David E. Wheeler. Some Rights Reserved.
.PP
This module is free software; you can redistribute it and/or modify it under
the same terms as Perl itself.