@recaptime-dev's working patches + fork for Phorge, a community fork of Phabricator. (Upstream dev and stable branches are at upstream/main and upstream/stable respectively.)
hq.recaptime.dev/wiki/Phorge
phorge
phabricator
Detect copied code by own algorithm
Summary:
Required for D2321.
Deprecates D2320.
Uses algorithm described at D2320#16.
Complexity of this algorithm would be `O(N)` (`N` stands for number of lines) in most cases.
The worst case is `O(A*F)` (`A` stands for number of added lines, `F` for number of colliding lines) but it should be pretty rare. Real-world example is 100 modified files with moved license block (15 lines) in each. This will require 1500*100 comparisons because the algorithm will be trying to find the longest block in each file.
Test Plan:
`arc diff --only` on commit with copied code.
More tests on standalone algorithm.
Reviewers: epriestley
Reviewed By: epriestley
CC: aran, Koolvin
Differential Revision: https://secure.phabricator.com/D2333
+83
+66
src/applications/differential/storage/diff/DifferentialDiff.php
+66
src/applications/differential/storage/diff/DifferentialDiff.php
···
151
151
}
152
152
$diff->setLineCount($lines);
153
153
154
+
$diff->detectCopiedCode();
155
+
154
156
return $diff;
157
+
}
158
+
159
+
private function detectCopiedCode($min_width = 40, $min_lines = 3) {
160
+
$map = array();
161
+
$files = array();
162
+
foreach ($this->changesets as $changeset) {
163
+
$file = $changeset->getFilename();
164
+
foreach ($changeset->getHunks() as $hunk) {
165
+
$line = $hunk->getOldOffset();
166
+
foreach (explode("\n", $hunk->makeOldFile()) as $code) {
167
+
$files[$file][$line] = $code;
168
+
if (strlen($code) >= $min_width) {
169
+
$map[$code][] = array($file, $line);
170
+
}
171
+
$line++;
172
+
}
173
+
}
174
+
}
175
+
176
+
foreach ($this->changesets as $changeset) {
177
+
$copies = array();
178
+
foreach ($changeset->getHunks() as $hunk) {
179
+
$added = $hunk->getAddedLines();
180
+
for (reset($added); list($line, $code) = each($added); next($added)) {
181
+
if (isset($map[$code])) { // We found a long matching line.
182
+
$lengths = array();
183
+
$max_offsets = array();
184
+
foreach ($map[$code] as $val) { // Explore all candidates.
185
+
list($file, $orig_line) = $val;
186
+
$lengths["$orig_line:$file"] = 1;
187
+
// Search also backwards for short lines.
188
+
foreach (array(-1, 1) as $direction) {
189
+
$offset = $direction;
190
+
$orig_code = idx($files[$file], $orig_line + $offset);
191
+
while (!isset($copies[$line + $offset]) &&
192
+
isset($added[$line + $offset]) &&
193
+
$orig_code === $added[$line + $offset]) {
194
+
$lengths["$orig_line:$file"]++;
195
+
$offset += $direction;
196
+
}
197
+
}
198
+
// ($offset - 1) contains number of forward matching lines.
199
+
$max_offsets["$orig_line:$file"] = $offset - 1;
200
+
}
201
+
$length = max($lengths); // Choose longest candidate.
202
+
$val = array_search($length, $lengths);
203
+
$offset = $max_offsets[$val];
204
+
list($orig_line, $file) = explode(':', $val, 2);
205
+
$save_file = ($file == $changeset->getFilename() ? '' : $file);
206
+
for ($i = $length; $i--; ) {
207
+
$copies[$line + $offset - $i] = ($length < $min_lines
208
+
? array() // Ignore short blocks.
209
+
: array($save_file, $orig_line + $offset - $i));
210
+
}
211
+
for ($i = 0; $i < $offset; $i++) {
212
+
next($added);
213
+
}
214
+
}
215
+
}
216
+
}
217
+
$metadata = $changeset->getMetadata();
218
+
$metadata['copy:lines'] = array_filter($copies);
219
+
$changeset->setMetadata($metadata);
220
+
}
155
221
}
156
222
157
223
public function getDiffDict() {
+17
src/applications/differential/storage/hunk/DifferentialHunk.php
+17
src/applications/differential/storage/hunk/DifferentialHunk.php
···
25
25
protected $newOffset;
26
26
protected $newLen;
27
27
28
+
public function getAddedLines() {
29
+
$lines = array();
30
+
$n = $this->newOffset;
31
+
foreach (explode("\n", $this->changes) as $diff_line) {
32
+
if ($diff_line == '' || $diff_line[0] == '\\') {
33
+
continue;
34
+
}
35
+
if ($diff_line[0] == '+') {
36
+
$lines[$n] = substr($diff_line, 1);
37
+
}
38
+
if ($diff_line[0] != '-') {
39
+
$n++;
40
+
}
41
+
}
42
+
return $lines;
43
+
}
44
+
28
45
public function makeNewFile() {
29
46
return $this->makeContent($exclude = '-');
30
47
}