1 | ###########################################################################
|
---|
2 | #
|
---|
3 | # SourceCodePlugin.pm -- source code plugin
|
---|
4 | #
|
---|
5 | # A component of the Greenstone digital library software
|
---|
6 | # from the New Zealand Digital Library Project at the
|
---|
7 | # University of Waikato, New Zealand.
|
---|
8 | #
|
---|
9 | # Copyright (C) 1999 New Zealand Digital Library Project
|
---|
10 | #
|
---|
11 | # This program is free software; you can redistribute it and/or modify
|
---|
12 | # it under the terms of the GNU General Public License as published by
|
---|
13 | # the Free Software Foundation; either version 2 of the License, or
|
---|
14 | # (at your option) any later version.
|
---|
15 | #
|
---|
16 | # This program is distributed in the hope that it will be useful,
|
---|
17 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
18 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
19 | # GNU General Public License for more details.
|
---|
20 | #
|
---|
21 | # You should have received a copy of the GNU General Public License
|
---|
22 | # along with this program; if not, write to the Free Software
|
---|
23 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
24 | #
|
---|
25 | ###########################################################################
|
---|
26 | # John McPherson Nov 2000
|
---|
27 | # originally based on TEXTPlug
|
---|
28 |
|
---|
29 | # filename is currently used for Title ( optionally minus some prefix )
|
---|
30 |
|
---|
31 | # Current languages:
|
---|
32 | # text: READMEs/Makefiles
|
---|
33 | # C/C++ (currently extracts #include statements and C++ class decls)
|
---|
34 | # Perl (currently only done as text)
|
---|
35 | # Shell (currently only done as text)
|
---|
36 |
|
---|
37 | package SourceCodePlugin;
|
---|
38 |
|
---|
39 | use ReadTextFile;
|
---|
40 |
|
---|
41 | use strict;
|
---|
42 | no strict 'refs'; # allow filehandles to be variables and viceversa
|
---|
43 |
|
---|
44 | sub BEGIN {
|
---|
45 | @SourceCodePlugin::ISA = ('ReadTextFile');
|
---|
46 | }
|
---|
47 |
|
---|
48 | my $arguments =
|
---|
49 | [ { 'name' => "process_exp",
|
---|
50 | 'desc' => "{BasePlugin.process_exp}",
|
---|
51 | 'type' => "regexp",
|
---|
52 | 'deft' => &get_default_process_exp(),
|
---|
53 | 'reqd' => "no" } ,
|
---|
54 | { 'name' => "block_exp",
|
---|
55 | 'desc' => "{BasePlugin.block_exp}",
|
---|
56 | 'type' => "regexp",
|
---|
57 | 'deft' => &get_default_block_exp(),
|
---|
58 | 'reqd' => "no" },
|
---|
59 | { 'name' => "remove_prefix",
|
---|
60 | 'desc' => "{SourceCodePlugin.remove_prefix}",
|
---|
61 | 'type' => "regexp",
|
---|
62 | 'deft' => "^.*[/\\]",
|
---|
63 | 'reqd' => "no" } ];
|
---|
64 |
|
---|
65 | my $options = { 'name' => "SourceCodePlugin",
|
---|
66 | 'desc' => "{SourceCodePlugin.desc}",
|
---|
67 | 'abstract' => "no",
|
---|
68 | 'inherits' => "yes",
|
---|
69 | 'args' => $arguments };
|
---|
70 |
|
---|
71 |
|
---|
72 | sub new {
|
---|
73 | my ($class) = shift (@_);
|
---|
74 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
---|
75 | push(@$pluginlist, $class);
|
---|
76 |
|
---|
77 | push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});
|
---|
78 | push(@{$hashArgOptLists->{"OptList"}},$options);
|
---|
79 |
|
---|
80 | my $self = new ReadTextFile($pluginlist, $inputargs, $hashArgOptLists);
|
---|
81 |
|
---|
82 | return bless $self, $class;
|
---|
83 | }
|
---|
84 |
|
---|
85 | sub get_default_block_exp {
|
---|
86 | my $self = shift (@_);
|
---|
87 |
|
---|
88 | return q^(?i)\.(o|obj|a|so|dll)$^;
|
---|
89 | }
|
---|
90 |
|
---|
91 | sub get_default_process_exp {
|
---|
92 | my $self = shift (@_);
|
---|
93 |
|
---|
94 | return q^(Makefile.*|README.*|(?i)\.(c|cc|cpp|C|h|hpp|pl|pm|sh))$^;
|
---|
95 | }
|
---|
96 |
|
---|
97 |
|
---|
98 |
|
---|
99 | # do plugin specific processing of doc_obj
|
---|
100 | sub process {
|
---|
101 | my $self = shift (@_);
|
---|
102 | my ($textref, $pluginfo, $base_dir, $file, $metadata, $doc_obj, $gli) = @_;
|
---|
103 | my $outhandle = $self->{'outhandle'};
|
---|
104 |
|
---|
105 | my $cursection = $doc_obj->get_top_section();
|
---|
106 |
|
---|
107 | my $filetype="text"; # Makefiles, READMEs, ...
|
---|
108 | if ($file =~ /\.(cc|h|cpp|C)$/) {$filetype="C++";} # assume all .h files...
|
---|
109 | elsif ($file =~ /\.c$/) {$filetype="C";}
|
---|
110 | elsif ($file =~ /\.p(l|m)$/) {$filetype="perl";}
|
---|
111 | elsif ($file =~ /\.sh$/) {$filetype="sh";}
|
---|
112 |
|
---|
113 | # modify '<' and '>' for GML... (even though inside <pre> tags!!)
|
---|
114 | $$textref =~ s/</</g;
|
---|
115 | $$textref =~ s/>/>/g;
|
---|
116 | $$textref =~ s/_/_/g;
|
---|
117 | # try _escape_text($text) from doc.pm....
|
---|
118 |
|
---|
119 | # don't want mg to turn escape chars into actual values
|
---|
120 | $$textref =~ s/\\/\\\\/g;
|
---|
121 |
|
---|
122 | # use filename (minus any prefix) as the title.
|
---|
123 | my $title;
|
---|
124 | if ($self->{'remove_prefix' ne ""}) {
|
---|
125 | ($title = $file) =~ s/^$self->{'remove_prefix'}//;
|
---|
126 | } else {
|
---|
127 | ($title = $file) =~ s@^.*[/\\]@@; # remove pathname by default
|
---|
128 | }
|
---|
129 | $doc_obj->add_utf8_metadata ($cursection, "Title", $title);
|
---|
130 | $doc_obj->add_metadata ($cursection, "FileFormat", "SRC");
|
---|
131 |
|
---|
132 | # remove the gsdl prefix from the filename
|
---|
133 | my $relative_filename=$file;
|
---|
134 | $relative_filename =~ s@^.*?gsdl[/\\]@@;
|
---|
135 | $doc_obj->add_utf8_metadata ($cursection, "filename", $relative_filename);
|
---|
136 |
|
---|
137 | # class information from .h and .cc and .C and .cpp files
|
---|
138 | if ($filetype eq "C++")
|
---|
139 | {
|
---|
140 | process_c_plus_plus($textref,$pluginfo, $base_dir,
|
---|
141 | $file, $metadata, $doc_obj);
|
---|
142 | } elsif ($filetype eq "C")
|
---|
143 | {
|
---|
144 | get_includes_metadata($textref, $doc_obj);
|
---|
145 | }
|
---|
146 |
|
---|
147 |
|
---|
148 | # default operation...
|
---|
149 | # insert preformat tags and add text to document object
|
---|
150 | $doc_obj->add_utf8_text($cursection, "<pre>\n$$textref\n</pre>");
|
---|
151 |
|
---|
152 | return 1;
|
---|
153 | }
|
---|
154 |
|
---|
155 |
|
---|
156 |
|
---|
157 |
|
---|
158 | sub get_includes_metadata {
|
---|
159 | my ($textref, $doc_obj) = @_;
|
---|
160 |
|
---|
161 | my $topsection = $doc_obj->get_top_section();
|
---|
162 |
|
---|
163 | # Get '#include' directives for metadata
|
---|
164 | if ($$textref !~ /\#\s*include\b/) {
|
---|
165 | return;
|
---|
166 | }
|
---|
167 |
|
---|
168 | my @includes =
|
---|
169 | ($$textref =~ m/^\s*\#\s*include\s*(?:\"|<)(.*?)(?:\"|>)/mg);
|
---|
170 |
|
---|
171 | my $incs_done_ref=$doc_obj->get_metadata($topsection, "includes");
|
---|
172 | my @incs_done;
|
---|
173 | if (defined($incs_done_ref)) {
|
---|
174 | @incs_done=@$incs_done_ref;
|
---|
175 | } else {
|
---|
176 | @incs_done=();
|
---|
177 | }
|
---|
178 |
|
---|
179 | foreach my $inc (@includes) {
|
---|
180 | # add entries, but only if they don't already exist
|
---|
181 | if (!join('', map {$_ eq "$inc"?1:""} @incs_done)) {
|
---|
182 | push @incs_done, $inc;
|
---|
183 | $doc_obj->add_utf8_metadata($topsection, "includes", $inc);
|
---|
184 | }
|
---|
185 | }
|
---|
186 | }
|
---|
187 |
|
---|
188 |
|
---|
189 |
|
---|
190 | sub process_c_plus_plus {
|
---|
191 | my ($textref, $pluginfo, $base_dir, $file, $metadata, $doc_obj) = @_;
|
---|
192 |
|
---|
193 | my $topsection = $doc_obj->get_top_section();
|
---|
194 |
|
---|
195 |
|
---|
196 | # Check for include metadata
|
---|
197 | get_includes_metadata($textref, $doc_obj);
|
---|
198 |
|
---|
199 |
|
---|
200 |
|
---|
201 | # Get class declarations (but not forward declarations...) as metadata
|
---|
202 | if ($$textref =~ /\bclass\b/ ) {
|
---|
203 | my $classnames=$$textref;
|
---|
204 |
|
---|
205 | # remove commented lines
|
---|
206 | $classnames =~ s@/\*.*?\*/@@sg;
|
---|
207 | $classnames =~ s@//.*$@@mg;
|
---|
208 | while ($classnames =~ /\bclass\b/) {
|
---|
209 |
|
---|
210 | # delete all lines up to the next "class"
|
---|
211 | while ($classnames !~ /^[^\n]*\bclass\b[^\n]*\n/)
|
---|
212 | {$classnames =~ s/.*\n//;}
|
---|
213 |
|
---|
214 | # $classnames =~ s/^([^c][^l])*(.)?$//mg; # delete unneccessary lines
|
---|
215 |
|
---|
216 | # get the line including the next "class" and remove it from
|
---|
217 | # our tmp text.
|
---|
218 | $classnames =~ s/^(.*\bclass\b.*)$//m;
|
---|
219 |
|
---|
220 | # don't index if merely a reference/fwd decl. of another class
|
---|
221 | if ($1 !~ /(friend\Wclass)|(class\W\w+\W?\;)|(\/\/.*class)/) {
|
---|
222 | # $1 is still the whole line - eg:
|
---|
223 | # "class StaffSystem: public BaseStaffSystem"
|
---|
224 | my $wholeline=$1;
|
---|
225 | my $classname=$1;
|
---|
226 | $classname =~ s/.*class\W(\w+).*/$1/;
|
---|
227 | my $classes=$doc_obj->get_metadata($topsection, "class");
|
---|
228 | foreach my $elem (@$classes) {
|
---|
229 | if ("$elem" eq "$classname") {goto class_done;}
|
---|
230 | }
|
---|
231 | $doc_obj->add_utf8_metadata($topsection, "class", $classname);
|
---|
232 | class_done:
|
---|
233 | $doc_obj->add_utf8_metadata($topsection, "classdecl", $wholeline);
|
---|
234 | }
|
---|
235 | }
|
---|
236 | } # end of "class"
|
---|
237 |
|
---|
238 | return 1;
|
---|
239 | }
|
---|
240 |
|
---|
241 | 1;
|
---|
242 |
|
---|