python-docs-fa/library/difflib.html at gh-pages · python/python-docs-fa

History

1281 lines (1175 loc) · 128 KB

Raw

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

217

218

219

220

221

222

223

224

225

226

227

228

229

230

231

232

233

234

235

236

237

238

239

240

241

242

243

244

245

246

247

248

249

250

251

252

253

254

255

256

257

258

259

260

261

262

263

264

265

266

267

268

269

270

271

272

273

274

275

276

277

278

279

280

281

282

283

284

285

286

287

288

289

290

291

292

293

294

295

296

297

298

299

300

301

302

303

304

305

306

307

308

309

310

311

312

313

314

315

316

317

318

319

320

321

322

323

324

325

326

327

328

329

330

331

332

333

334

335

336

337

338

339

340

341

342

343

344

345

346

347

348

349

350

351

352

353

354

355

356

357

358

359

360

361

362

363

364

365

366

367

368

369

370

371

372

373

374

375

376

377

378

379

380

381

382

383

384

385

386

387

388

389

390

391

392

393

394

395

396

397

398

399

400

401

402

403

404

405

406

407

408

409

410

411

412

413

414

415

416

417

418

419

420

421

422

423

424

425

426

427

428

429

430

431

432

433

434

435

436

437

438

439

440

441

442

443

444

445

446

447

448

449

450

451

452

453

454

455

456

457

458

459

460

461

462

463

464

465

466

467

468

469

470

471

472

473

474

475

476

477

478

479

480

481

482

483

484

485

486

487

488

489

490

491

492

493

494

495

496

497

498

499

500

501

502

503

504

505

506

507

508

509

510

511

512

513

514

515

516

517

518

519

520

521

522

523

524

525

526

527

528

529

530

531

532

533

534

535

536

537

538

539

540

541

542

543

544

545

546

547

548

549

550

551

552

553

554

555

556

557

558

559

560

561

562

563

564

565

566

567

568

569

570

571

572

573

574

575

576

577

578

579

580

581

582

583

584

585

586

587

588

589

590

591

592

593

594

595

596

597

598

599

600

601

602

603

604

605

606

607

608

609

610

611

612

613

614

615

616

617

618

619

620

621

622

623

624

625

626

627

628

629

630

631

632

633

634

635

636

637

638

639

640

641

642

643

644

645

646

647

648

649

650

651

652

653

654

655

656

657

658

659

660

661

662

663

664

665

666

667

668

669

670

671

672

673

674

675

676

677

678

679

680

681

682

683

684

685

686

687

688

689

690

691

692

693

694

695

696

697

698

699

700

701

702

703

704

705

706

707

708

709

710

711

712

713

714

715

716

717

718

719

720

721

722

723

724

725

726

727

728

729

730

731

732

733

734

735

736

737

738

739

740

741

742

743

744

745

746

747

748

749

750

751

752

753

754

755

756

757

758

759

760

761

762

763

764

765

766

767

768

769

770

771

772

773

774

775

776

777

778

779

780

781

782

783

784

785

786

787

788

789

790

791

792

793

794

795

796

797

798

799

800

801

802

803

804

805

806

807

808

809

810

811

812

813

814

815

816

817

818

819

820

821

822

823

824

825

826

827

828

829

830

831

832

833

834

835

836

837

838

839

840

841

842

843

844

845

846

847

848

849

850

851

852

853

854

855

856

857

858

859

860

861

862

863

864

865

866

867

868

869

870

871

872

873

874

875

876

877

878

879

880

881

882

883

884

885

886

887

888

889

890

891

892

893

894

895

896

897

898

899

900

901

902

903

904

905

906

907

908

909

910

911

912

913

914

915

916

917

918

919

920

921

922

923

924

925

926

927

928

929

930

931

932

933

934

935

936

937

938

939

940

941

942

943

944

945

946

947

948

949

950

951

952

953

954

955

956

957

958

959

960

961

962

963

964

965

966

967

968

969

970

971

972

973

974

975

976

977

978

979

980

981

982

983

984

985

986

987

988

989

990

991

992

993

994

995

996

997

998

999

1000

<!DOCTYPE html>

<head>

<title>difflib --- Helpers for computing deltas — مستندات Python3.14.6</title><meta name="viewport" content="width=device-width, initial-scale=1.0">

title="جستجو در مستندات Python3.14.6"

href="../_static/opensearch.xml"/>

<style>

@media only screen {

table.full-width-table {

width: 100%;

}

</style>

</head>

<body>

<input type="checkbox" id="menuToggler" class="toggler__input" aria-controls="navigation"

aria-pressed="false" aria-expanded="false" role="button" aria-label="Menu">

</label>

</a>

</svg>

</form>

</nav>

Theme

<option value="light">Light</option>

</select>

</label>

<div>

<h3><a href="../contents.html">فهرست عناوین</a></h3>

<ul>

<li><a class="reference internal" href="#"><code class="xref py py-mod docutils literal notranslate">difflib</code> --- Helpers for computing deltas</a><ul>

<li><a class="reference internal" href="#sequencematcher-objects">SequenceMatcher objects</a></li>

<li><a class="reference internal" href="#sequencematcher-examples">SequenceMatcher examples</a></li>

<li><a class="reference internal" href="#differ-objects">Differ objects</a></li>

<li><a class="reference internal" href="#differ-example">Differ example</a></li>

<li><a class="reference internal" href="#a-command-line-interface-to-difflib">A command-line interface to difflib</a></li>

<li><a class="reference internal" href="#ndiff-example">ndiff example</a></li>

</ul>

</li>

</ul>

</div>

<div>

<h4>موضوع قبلی</h4>

<a href="re.html"

title="فصل قبلی"><code class="xref py py-mod docutils literal notranslate">re</code> --- Regular expression operations</a>

</div>

<div>

<h4>موضوع بعدی</h4>

<a href="textwrap.html"

title="فصل بعدی"><code class="xref py py-mod docutils literal notranslate">textwrap</code> --- Text wrapping and filling</a>

</div>

document.addEventListener('DOMContentLoaded', () => {

const title = document.querySelector('meta[property="og:title"]').content;

const elements = document.querySelectorAll('.improvepage');

const pageurl = window.location.href.split('?')[0];

elements.forEach(element => {

const url = new URL(element.href.split('?')[0].replace("-nojs", ""));

url.searchParams.set('pagetitle', title);

url.searchParams.set('pageurl', pageurl);

url.searchParams.set('pagesource', "library/difflib.rst");

element.href = url.toString();

});

</script>

<li><a href="../bugs.html">گزارش یک اشکال</a></li>

<li><a class="improvepage" href="../improve-page-nojs.html">بهبود این صفحه</a></li>

<li>

<a href="https://github.com/python/cpython/blob/main/Doc/library/difflib.rst?plain=1"

rel="nofollow">نمایش منبع

</a>

</li>

<li>

<a href="https://github.com/python/python-docs-fa/blob/3.14/library/difflib.po?plain=1"

rel="nofollow">نمایش منبع ترجمه</a>

</li>

</ul>

</div>

</nav>

</div>

<h3>ناوبری</h3>

<ul>

<a href="../genindex.html" title="فهرست کلی"

accesskey="I">فهرست</a></li>

<a href="../py-modindex.html" title="نمایه ی ماژول های پایتون"

>ماژول ها</a> |</li>

<a href="textwrap.html" title="textwrap --- Text wrapping and filling"

accesskey="N">بعدی</a> |</li>

<a href="re.html" title="re --- Regular expression operations"

accesskey="P">قبلی</a> |</li>

<li><a href="https://www.python.org/">Python</a> »</li>

</li>

<li>

</li>

<a href="../index.html">3.14.6 Documentation</a> »

</li>

<li class="nav-item nav-item-1"><a href="index.html" >The Python Standard Library</a> »</li>

<li class="nav-item nav-item-2"><a href="text.html" accesskey="U">Text Processing Services</a> »</li>

<li class="nav-item nav-item-this"><a href=""><code class="xref py py-mod docutils literal notranslate">difflib</code> --- Helpers for computing deltas</a></li>

</form>

</div>

</li>

Theme

<option value="light">Light</option>

</select>

</label> |</li>

</ul>

</div>

<h1><code class="xref py py-mod docutils literal notranslate">difflib</code> --- Helpers for computing deltas<a class="headerlink" href="#module-difflib" title="Link to this heading">¶</a></h1>

Source code: <a class="extlink-source reference external" href="https://github.com/python/cpython/tree/3.14/Lib/difflib.py">Lib/difflib.py</a>

This module provides classes and functions for comparing sequences. It

can be used for example, for comparing files, and can produce information

about file differences in various formats, including HTML and context and unified

diffs. For comparing directories and files, see also, the <a class="reference internal" href="filecmp.html#module-filecmp" title="filecmp: Compare files efficiently."><code class="xref py py-mod docutils literal notranslate">filecmp</code></a> module.

<dd>This is a flexible class for comparing pairs of sequences of any type, so long

as the sequence elements are <a class="reference internal" href="../glossary.html#term-hashable">hashable</a>. The basic algorithm predates, and is a

little fancier than, an algorithm published in the late 1980's by Ratcliff and

Obershelp under the hyperbolic name "gestalt pattern matching." The idea is to

find the longest contiguous matching subsequence that contains no "junk"

elements; these "junk" elements are ones that are uninteresting in some

sense, such as blank lines or whitespace. (Handling junk is an

extension to the Ratcliff and Obershelp algorithm.) The same

idea is then applied recursively to the pieces of the sequences to the left and

to the right of the matching subsequence. This does not yield minimal edit

sequences, but does tend to yield matches that "look right" to people.

Timing: The basic Ratcliff-Obershelp algorithm is cubic time in the worst

case and quadratic time in the expected case. <a class="reference internal" href="#difflib.SequenceMatcher" title="difflib.SequenceMatcher"><code class="xref py py-class docutils literal notranslate">SequenceMatcher</code></a> is

quadratic time for the worst case and has expected-case behavior dependent in a

complicated way on how many elements the sequences have in common; best case

time is linear.

Automatic junk heuristic: <a class="reference internal" href="#difflib.SequenceMatcher" title="difflib.SequenceMatcher"><code class="xref py py-class docutils literal notranslate">SequenceMatcher</code></a> supports a heuristic that

automatically treats certain sequence items as junk. The heuristic counts how many

times each individual item appears in the sequence. If an item's duplicates (after

the first one) account for more than 1% of the sequence and the sequence is at least

200 items long, this item is marked as "popular" and is treated as junk for

the purpose of sequence matching. This heuristic can be turned off by setting

the <code class="docutils literal notranslate">autojunk</code> argument to <code class="docutils literal notranslate">False</code> when creating the <code class="xref py py-class docutils literal notranslate">SequenceMatcher</code>.

تغییر داده شده در نسخه 3.2: Added the autojunk parameter.

</div>

</dd></dl>

<dd>This is a class for comparing sequences of lines of text, and producing

human-readable differences or deltas. Differ uses <a class="reference internal" href="#difflib.SequenceMatcher" title="difflib.SequenceMatcher"><code class="xref py py-class docutils literal notranslate">SequenceMatcher</code></a>

both to compare sequences of lines, and to compare sequences of characters

within similar (near-matching) lines.

Each line of a <code class="xref py py-class docutils literal notranslate">Differ</code> delta begins with a two-letter code:

<thead>

<th class="head">Meaning</th>

</tr>

</thead>

<tbody>

<td>line unique to sequence 1</td>

</tr>

<td>line unique to sequence 2</td>

</tr>

<td>line common to both sequences</td>

</tr>

<td>line not present in either input sequence</td>

</tr>

</tbody>

</table>

Lines beginning with '<code class="docutils literal notranslate">?</code>' attempt to guide the eye to intraline differences,

and were not present in either input sequence. These lines can be confusing if

the sequences contain whitespace characters, such as spaces, tabs or line breaks.

</dd></dl>

<dd>This class can be used to create an HTML table (or a complete HTML file

containing the table) showing a side by side, line by line comparison of text

with inter-line and intra-line change highlights. The table can be generated in

either full or contextual difference mode.

The constructor for this class is:

__init__(tabsize=8, wrapcolumn=None, linejunk=None, charjunk=IS_CHARACTER_JUNK)<a class="headerlink" href="#difflib.HtmlDiff.__init__" title="Link to this definition">¶</a></dt>

<dd>Initializes instance of <code class="xref py py-class docutils literal notranslate">HtmlDiff</code>.

tabsize is an optional keyword argument to specify tab stop spacing and

defaults to <code class="docutils literal notranslate">8</code>.

wrapcolumn is an optional keyword to specify column number where lines are

broken and wrapped, defaults to <code class="docutils literal notranslate">None</code> where lines are not wrapped.

linejunk and charjunk are optional keyword arguments passed into <a class="reference internal" href="#difflib.ndiff" title="difflib.ndiff"><code class="xref py py-func docutils literal notranslate">ndiff()</code></a>

(used by <code class="xref py py-class docutils literal notranslate">HtmlDiff</code> to generate the side by side HTML differences). See

<code class="xref py py-func docutils literal notranslate">ndiff()</code> documentation for argument default values and descriptions.

</dd></dl>

The following methods are public:

make_file(fromlines, tolines, fromdesc='', todesc='', context=False, numlines=5, <abbr title="Keyword-only parameters separator (PEP 3102)">*</abbr>, charset='utf-8')<a class="headerlink" href="#difflib.HtmlDiff.make_file" title="Link to this definition">¶</a></dt>

<dd>Compares fromlines and tolines (lists of strings) and returns a string which

is a complete HTML file containing a table showing line by line differences with

inter-line and intra-line changes highlighted.

fromdesc and todesc are optional keyword arguments to specify from/to file

column header strings (both default to an empty string).

context and numlines are both optional keyword arguments. Set context to

<code class="docutils literal notranslate">True</code> when contextual differences are to be shown, else the default is

<code class="docutils literal notranslate">False</code> to show the full files. numlines defaults to <code class="docutils literal notranslate">5</code>. When context

is <code class="docutils literal notranslate">True</code> numlines controls the number of context lines which surround the

difference highlights. When context is <code class="docutils literal notranslate">False</code> numlines controls the

number of lines which are shown before a difference highlight when using the

"next" hyperlinks (setting to zero would cause the "next" hyperlinks to place

the next difference highlight at the top of the browser without any leading

context).

توجه

fromdesc and todesc are interpreted as unescaped HTML and should be

properly escaped while receiving input from untrusted sources.

</div>

تغییر داده شده در نسخه 3.5: charset keyword-only argument was added. The default charset of

HTML document changed from <code class="docutils literal notranslate">'ISO-8859-1'</code> to <code class="docutils literal notranslate">'utf-8'</code>.

</div>

</dd></dl>

make_table(fromlines, tolines, fromdesc='', todesc='', context=False, numlines=5)<a class="headerlink" href="#difflib.HtmlDiff.make_table" title="Link to this definition">¶</a></dt>

<dd>Compares fromlines and tolines (lists of strings) and returns a string which

is a complete HTML table showing line by line differences with inter-line and

intra-line changes highlighted.

The arguments for this method are the same as those for the <a class="reference internal" href="#difflib.HtmlDiff.make_file" title="difflib.HtmlDiff.make_file"><code class="xref py py-meth docutils literal notranslate">make_file()</code></a>

method.

</dd></dl>

difflib.context_diff(a, b, fromfile='', tofile='', fromfiledate='', tofiledate='', n=3, lineterm='\n')<a class="headerlink" href="#difflib.context_diff" title="Link to this definition">¶</a></dt>

<dd>Compare a and b (lists of strings); return a delta (a <a class="reference internal" href="../glossary.html#term-generator">generator</a>

generating the delta lines) in context diff format.

Context diffs are a compact way of showing just the lines that have changed plus

a few lines of context. The changes are shown in a before/after style. The

number of context lines is set by n which defaults to three.

By default, the diff control lines (those with <code class="docutils literal notranslate">***</code> or <code class="docutils literal notranslate">---</code>) are created

with a trailing newline. This is helpful so that inputs created from

<a class="reference internal" href="io.html#io.IOBase.readlines" title="io.IOBase.readlines"><code class="xref py py-func docutils literal notranslate">io.IOBase.readlines()</code></a> result in diffs that are suitable for use with

<a class="reference internal" href="io.html#io.IOBase.writelines" title="io.IOBase.writelines"><code class="xref py py-func docutils literal notranslate">io.IOBase.writelines()</code></a> since both the inputs and outputs have trailing

newlines.

For inputs that do not have trailing newlines, set the lineterm argument to

<code class="docutils literal notranslate">""</code> so that the output will be uniformly newline free.

The context diff format normally has a header for filenames and modification

times. Any or all of these may be specified using strings for fromfile,

tofile, fromfiledate, and tofiledate. The modification times are normally

expressed in the ISO 8601 format. If not specified, the

strings default to blanks.

<div class="doctest highlight-default notranslate"><div class="highlight"><pre>>>> import sys

>>> from difflib import *

>>> s1 = ['bacon\n', 'eggs\n', 'ham\n', 'guido\n']

>>> s2 = ['python\n', 'eggy\n', 'hamster\n', 'guido\n']

>>> sys.stdout.writelines(context_diff(s1, s2, fromfile='before.py',

... tofile='after.py'))

*** before.py

--- after.py

***************

*** 1,4 ****

! bacon

! eggs

! ham

guido

--- 1,4 ----

! python

! eggy

! hamster

guido

</pre></div>

</div>

See <a class="reference internal" href="#difflib-interface">A command-line interface to difflib</a> for a more detailed example.

</dd></dl>

difflib.get_close_matches(word, possibilities, n=3, cutoff=0.6)<a class="headerlink" href="#difflib.get_close_matches" title="Link to this definition">¶</a></dt>

<dd>Return a list of the best "good enough" matches. word is a sequence for which

close matches are desired (typically a string), and possibilities is a list of

sequences against which to match word (typically a list of strings).

Optional argument n (default <code class="docutils literal notranslate">3</code>) is the maximum number of close matches to

return; n must be greater than <code class="docutils literal notranslate">0</code>.

Optional argument cutoff (default <code class="docutils literal notranslate">0.6</code>) is a float in the range [0, 1].

Possibilities that don't score at least that similar to word are ignored.

The best (no more than n) matches among the possibilities are returned in a

list, sorted by similarity score, most similar first.

<div class="doctest highlight-default notranslate"><div class="highlight"><pre>>>> get_close_matches('appel', ['ape', 'apple', 'peach', 'puppy'])

['apple', 'ape']

>>> import keyword

>>> get_close_matches('wheel', keyword.kwlist)

['while']

>>> get_close_matches('pineapple', keyword.kwlist)

[]

>>> get_close_matches('accept', keyword.kwlist)

['except']

</pre></div>

</div>

</dd></dl>

difflib.ndiff(a, b, linejunk=None, charjunk=IS_CHARACTER_JUNK)<a class="headerlink" href="#difflib.ndiff" title="Link to this definition">¶</a></dt>

<dd>Compare a and b (lists of strings); return a <a class="reference internal" href="#difflib.Differ" title="difflib.Differ"><code class="xref py py-class docutils literal notranslate">Differ</code></a>-style

delta (a <a class="reference internal" href="../glossary.html#term-generator">generator</a> generating the delta lines).

Optional keyword parameters linejunk and charjunk are filtering functions

(or <code class="docutils literal notranslate">None</code>):

linejunk: A function that accepts a single string argument, and returns

true if the string is junk, or false if not. The default is <code class="docutils literal notranslate">None</code>. There

is also a module-level function <a class="reference internal" href="#difflib.IS_LINE_JUNK" title="difflib.IS_LINE_JUNK"><code class="xref py py-func docutils literal notranslate">IS_LINE_JUNK()</code></a>, which filters out lines

without visible characters, except for at most one hash character (<code class="docutils literal notranslate">'#'</code>)

-- however the underlying <a class="reference internal" href="#difflib.SequenceMatcher" title="difflib.SequenceMatcher"><code class="xref py py-class docutils literal notranslate">SequenceMatcher</code></a> class does a dynamic

analysis of which lines are so frequent as to constitute noise, and this

usually works better than using this function.

charjunk: A function that accepts a character (a string of length 1), and

returns if the character is junk, or false if not. The default is module-level

function <a class="reference internal" href="#difflib.IS_CHARACTER_JUNK" title="difflib.IS_CHARACTER_JUNK"><code class="xref py py-func docutils literal notranslate">IS_CHARACTER_JUNK()</code></a>, which filters out whitespace characters (a

blank or tab; it's a bad idea to include newline in this!).

<div class="doctest highlight-default notranslate"><div class="highlight"><pre>>>> diff = ndiff('one\ntwo\nthree\n'.splitlines(keepends=True),

... 'ore\ntree\nemu\n'.splitlines(keepends=True))

>>> print(''.join(diff), end="")

- one

? ^

+ ore

? ^

- two

- three

? -

+ tree

+ emu

</pre></div>

</div>

</dd></dl>

difflib.restore(sequence, which)<a class="headerlink" href="#difflib.restore" title="Link to this definition">¶</a></dt>

<dd>Return one of the two sequences that generated a delta.

Given a sequence produced by <a class="reference internal" href="#difflib.Differ.compare" title="difflib.Differ.compare"><code class="xref py py-meth docutils literal notranslate">Differ.compare()</code></a> or <a class="reference internal" href="#difflib.ndiff" title="difflib.ndiff"><code class="xref py py-func docutils literal notranslate">ndiff()</code></a>, extract

lines originating from file 1 or 2 (parameter which), stripping off line

prefixes.

Example:

>>> diff = list(diff) # materialize the generated delta into a list

>>> print(''.join(restore(diff, 1)), end="")

one

two

three

>>> print(''.join(restore(diff, 2)), end="")

ore

tree

emu

</pre></div>

</div>

</dd></dl>

difflib.unified_diff(a, b, fromfile='', tofile='', fromfiledate='', tofiledate='', n=3, lineterm='\n')<a class="headerlink" href="#difflib.unified_diff" title="Link to this definition">¶</a></dt>

generating the delta lines) in unified diff format.

Unified diffs are a compact way of showing just the lines that have changed plus

a few lines of context. The changes are shown in an inline style (instead of

separate before/after blocks). The number of context lines is set by n which

defaults to three.

By default, the diff control lines (those with <code class="docutils literal notranslate">---</code>, <code class="docutils literal notranslate">+++</code>, or <code class="docutils literal notranslate">@@</code>) are

created with a trailing newline. This is helpful so that inputs created from

newlines.

For inputs that do not have trailing newlines, set the lineterm argument to

<code class="docutils literal notranslate">""</code> so that the output will be uniformly newline free.

The unified diff format normally has a header for filenames and modification

times. Any or all of these may be specified using strings for fromfile,

tofile, fromfiledate, and tofiledate. The modification times are normally

expressed in the ISO 8601 format. If not specified, the

strings default to blanks.

<div class="doctest highlight-default notranslate"><div class="highlight"><pre>>>> s1 = ['bacon\n', 'eggs\n', 'ham\n', 'guido\n']

>>> sys.stdout.writelines(unified_diff(s1, s2, fromfile='before.py', tofile='after.py'))

--- before.py

+++ after.py

@@ -1,4 +1,4 @@

-bacon

-eggs

-ham

+python

+eggy

+hamster

guido

</pre></div>

</div>

See <a class="reference internal" href="#difflib-interface">A command-line interface to difflib</a> for a more detailed example.

</dd></dl>

difflib.diff_bytes(dfunc, a, b, fromfile=b'', tofile=b'', fromfiledate=b'', tofiledate=b'', n=3, lineterm=b'\n')<a class="headerlink" href="#difflib.diff_bytes" title="Link to this definition">¶</a></dt>

<dd>Compare a and b (lists of bytes objects) using dfunc; yield a

sequence of delta lines (also bytes) in the format returned by dfunc.

dfunc must be a callable, typically either <a class="reference internal" href="#difflib.unified_diff" title="difflib.unified_diff"><code class="xref py py-func docutils literal notranslate">unified_diff()</code></a> or

<a class="reference internal" href="#difflib.context_diff" title="difflib.context_diff"><code class="xref py py-func docutils literal notranslate">context_diff()</code></a>.

Allows you to compare data with unknown or inconsistent encoding. All

inputs except n must be bytes objects, not str. Works by losslessly

converting all inputs (except n) to str, and calling <code class="docutils literal notranslate">dfunc(a, b,

fromfile, tofile, fromfiledate, tofiledate, n, lineterm)</code>. The output of

dfunc is then converted back to bytes, so the delta lines that you

receive have the same unknown/inconsistent encodings as a and b.

Added in version 3.5.

</div>

</dd></dl>

difflib.IS_LINE_JUNK(line)<a class="headerlink" href="#difflib.IS_LINE_JUNK" title="Link to this definition">¶</a></dt>

<dd>Return <code class="docutils literal notranslate">True</code> for ignorable lines. The line line is ignorable if line is

blank or contains a single <code class="docutils literal notranslate">'#'</code>, otherwise it is not ignorable. Used as a

default for parameter linejunk in <a class="reference internal" href="#difflib.ndiff" title="difflib.ndiff"><code class="xref py py-func docutils literal notranslate">ndiff()</code></a> in older versions.

</dd></dl>

difflib.IS_CHARACTER_JUNK(ch)<a class="headerlink" href="#difflib.IS_CHARACTER_JUNK" title="Link to this definition">¶</a></dt>

<dd>Return <code class="docutils literal notranslate">True</code> for ignorable characters. The character ch is ignorable if ch

is a space or tab, otherwise it is not ignorable. Used as a default for

parameter charjunk in <a class="reference internal" href="#difflib.ndiff" title="difflib.ndiff"><code class="xref py py-func docutils literal notranslate">ndiff()</code></a>.

</dd></dl>

همچنین ملاحظه نمائید

<dt><a class="reference external" href="https://jacobfilipp.com/DrDobbs/articles/DDJ/1988/8807/8807c/8807c.htm">Pattern Matching: The Gestalt Approach</a></dt><dd>Discussion of a similar algorithm by John W. Ratcliff and D. E. Metzener. This

was published in Dr. Dobb's Journal in July, 1988.

</dd>

</dl>

</div>

<h2>SequenceMatcher objects<a class="headerlink" href="#sequencematcher-objects" title="Link to this heading">¶</a></h2>

The <a class="reference internal" href="#difflib.SequenceMatcher" title="difflib.SequenceMatcher"><code class="xref py py-class docutils literal notranslate">SequenceMatcher</code></a> class has this constructor:

class difflib.SequenceMatcher(isjunk=None, a='', b='', autojunk=True)<a class="headerlink" href="#difflib.SequenceMatcher" title="Link to this definition">¶</a></dt>

<dd>Optional argument isjunk must be <code class="docutils literal notranslate">None</code> (the default) or a one-argument

function that takes a sequence element and returns true if and only if the

element is "junk" and should be ignored. Passing <code class="docutils literal notranslate">None</code> for isjunk is

equivalent to passing <code class="docutils literal notranslate">lambda x: False</code>; in other words, no elements are ignored.

For example, pass:

<div class="highlight-python3 notranslate"><div class="highlight"><pre>lambda x: x in " \t"

</pre></div>

</div>

if you're comparing lines as sequences of characters, and don't want to synch up

on blanks or hard tabs.

The optional arguments a and b are sequences to be compared; both default to

empty strings. The elements of both sequences must be <a class="reference internal" href="../glossary.html#term-hashable">hashable</a>.

The optional argument autojunk can be used to disable the automatic junk

heuristic.

تغییر داده شده در نسخه 3.2: Added the autojunk parameter.

</div>

SequenceMatcher objects get three data attributes: bjunk is the

set of elements of b for which isjunk is <code class="docutils literal notranslate">True</code>; bpopular is the set of

non-junk elements considered popular by the heuristic (if it is not

disabled); b2j is a dict mapping the remaining elements of b to a list

of positions where they occur. All three are reset whenever b is reset

with <a class="reference internal" href="#difflib.SequenceMatcher.set_seqs" title="difflib.SequenceMatcher.set_seqs"><code class="xref py py-meth docutils literal notranslate">set_seqs()</code></a> or <a class="reference internal" href="#difflib.SequenceMatcher.set_seq2" title="difflib.SequenceMatcher.set_seq2"><code class="xref py py-meth docutils literal notranslate">set_seq2()</code></a>.

Added in version 3.2: The bjunk and bpopular attributes.

</div>

<code class="xref py py-class docutils literal notranslate">SequenceMatcher</code> objects have the following methods:

set_seqs(a, b)<a class="headerlink" href="#difflib.SequenceMatcher.set_seqs" title="Link to this definition">¶</a></dt>

<dd>Set the two sequences to be compared.

</dd></dl>

<code class="xref py py-class docutils literal notranslate">SequenceMatcher</code> computes and caches detailed information about the

second sequence, so if you want to compare one sequence against many

sequences, use <a class="reference internal" href="#difflib.SequenceMatcher.set_seq2" title="difflib.SequenceMatcher.set_seq2"><code class="xref py py-meth docutils literal notranslate">set_seq2()</code></a> to set the commonly used sequence once and

call <a class="reference internal" href="#difflib.SequenceMatcher.set_seq1" title="difflib.SequenceMatcher.set_seq1"><code class="xref py py-meth docutils literal notranslate">set_seq1()</code></a> repeatedly, once for each of the other sequences.

set_seq1(a)<a class="headerlink" href="#difflib.SequenceMatcher.set_seq1" title="Link to this definition">¶</a></dt>

<dd>Set the first sequence to be compared. The second sequence to be compared

is not changed.

</dd></dl>

set_seq2(b)<a class="headerlink" href="#difflib.SequenceMatcher.set_seq2" title="Link to this definition">¶</a></dt>

<dd>Set the second sequence to be compared. The first sequence to be compared

is not changed.

</dd></dl>

find_longest_match(alo=0, ahi=None, blo=0, bhi=None)<a class="headerlink" href="#difflib.SequenceMatcher.find_longest_match" title="Link to this definition">¶</a></dt>

<dd>Find longest matching block in <code class="docutils literal notranslate">a[alo:ahi]</code> and <code class="docutils literal notranslate">b[blo:bhi]</code>.

If isjunk was omitted or <code class="docutils literal notranslate">None</code>, <code class="xref py py-meth docutils literal notranslate">find_longest_match()</code> returns

<code class="docutils literal notranslate">(i, j, k)</code> such that <code class="docutils literal notranslate">a[i:i+k]</code> is equal to <code class="docutils literal notranslate">b[j:j+k]</code>, where <code class="docutils literal notranslate">alo

<= i <= i+k <= ahi</code> and <code class="docutils literal notranslate">blo <= j <= j+k <= bhi</code>. For all <code class="docutils literal notranslate">(i', j',

k')</code> meeting those conditions, the additional conditions <code class="docutils literal notranslate">k >= k'</code>, <code class="docutils literal notranslate">i

<= i'</code>, and if <code class="docutils literal notranslate">i == i'</code>, <code class="docutils literal notranslate">j <= j'</code> are also met. In other words, of

all maximal matching blocks, return one that starts earliest in a, and

of all those maximal matching blocks that start earliest in a, return

the one that starts earliest in b.

<div class="doctest highlight-default notranslate"><div class="highlight"><pre>>>> s = SequenceMatcher(None, " abcd", "abcd abcd")

>>> s.find_longest_match(0, 5, 0, 9)

Match(a=0, b=4, size=5)

</pre></div>

</div>

If isjunk was provided, first the longest matching block is determined

as above, but with the additional restriction that no junk element appears

in the block. Then that block is extended as far as possible by matching

(only) junk elements on both sides. So the resulting block never matches

on junk except as identical junk happens to be adjacent to an interesting

match.

Here's the same example as before, but considering blanks to be junk. That

prevents <code class="docutils literal notranslate">' abcd'</code> from matching the <code class="docutils literal notranslate">' abcd'</code> at the tail end of the

second sequence directly. Instead only the <code class="docutils literal notranslate">'abcd'</code> can match, and

matches the leftmost <code class="docutils literal notranslate">'abcd'</code> in the second sequence:

<div class="doctest highlight-default notranslate"><div class="highlight"><pre>>>> s = SequenceMatcher(lambda x: x==" ", " abcd", "abcd abcd")

Match(a=1, b=0, size=4)

</pre></div>

</div>

If no blocks match, this returns <code class="docutils literal notranslate">(alo, blo, 0)</code>.

This method returns a <a class="reference internal" href="../glossary.html#term-named-tuple">named tuple</a> <code class="docutils literal notranslate">Match(a, b, size)</code>.

تغییر داده شده در نسخه 3.9: Added default arguments.

</div>

</dd></dl>

get_matching_blocks()<a class="headerlink" href="#difflib.SequenceMatcher.get_matching_blocks" title="Link to this definition">¶</a></dt>

<dd>Return list of triples describing non-overlapping matching subsequences.

Each triple is of the form <code class="docutils literal notranslate">(i, j, n)</code>,

and means that <code class="docutils literal notranslate">a[i:i+n] == b[j:j+n]</code>. The

triples are monotonically increasing in i and j.

The last triple is a dummy, and has the value <code class="docutils literal notranslate">(len(a), len(b), 0)</code>. It

is the only triple with <code class="docutils literal notranslate">n == 0</code>. If <code class="docutils literal notranslate">(i, j, n)</code> and <code class="docutils literal notranslate">(i', j', n')</code>

are adjacent triples in the list, and the second is not the last triple in

the list, then <code class="docutils literal notranslate">i+n < i'</code> or <code class="docutils literal notranslate">j+n < j'</code>; in other words, adjacent

triples always describe non-adjacent equal blocks.

<div class="highlight-pycon notranslate"><div class="highlight"><pre>>>> s = SequenceMatcher(None, "abxcd", "abcd")

>>> s.get_matching_blocks()

[Match(a=0, b=0, size=2), Match(a=3, b=2, size=2), Match(a=5, b=4, size=0)]

</pre></div>

</div>

</dd></dl>

get_opcodes()<a class="headerlink" href="#difflib.SequenceMatcher.get_opcodes" title="Link to this definition">¶</a></dt>

<dd>Return list of 5-tuples describing how to turn a into b. Each tuple is

of the form <code class="docutils literal notranslate">(tag, i1, i2, j1, j2)</code>. The first tuple has <code class="docutils literal notranslate">i1 == j1 ==

0</code>, and remaining tuples have i1 equal to the i2 from the preceding

tuple, and, likewise, j1 equal to the previous j2.

The tag values are strings, with these meanings:

<thead>

<tr class="row-odd"><th class="head">Value</th>

<th class="head">Meaning</th>

</tr>

</thead>

<tbody>

<tr class="row-even"><td><code class="docutils literal notranslate">'replace'</code></td>

<td><code class="docutils literal notranslate">a[i1:i2]</code> should be replaced by

</tr>

<tr class="row-odd"><td><code class="docutils literal notranslate">'delete'</code></td>

<td><code class="docutils literal notranslate">a[i1:i2]</code> should be deleted. Note that

</tr>

<tr class="row-even"><td><code class="docutils literal notranslate">'insert'</code></td>

<td><code class="docutils literal notranslate">b[j1:j2]</code> should be inserted at

<code class="docutils literal notranslate">a[i1:i1]</code>. Note that <code class="docutils literal notranslate">i1 == i2</code> in

this case.</td>

</tr>

<tr class="row-odd"><td><code class="docutils literal notranslate">'equal'</code></td>

<td><code class="docutils literal notranslate">a[i1:i2] == b[j1:j2]</code> (the sub-sequences

are equal).</td>

</tr>

</tbody>

</table>

For example:

<div class="highlight-python3 notranslate"><div class="highlight"><pre>>>> a = "qabxcd"

>>> b = "abycdf"

>>> s = SequenceMatcher(None, a, b)

>>> for tag, i1, i2, j1, j2 in s.get_opcodes():

... print('{:7} a[{}:{}] --> b[{}:{}] {!r:>8} --> {!r}'.format(

... tag, i1, i2, j1, j2, a[i1:i2], b[j1:j2]))

delete a[0:1] --> b[0:0] 'q' --> ''

equal a[1:3] --> b[0:2] 'ab' --> 'ab'

replace a[3:4] --> b[2:3] 'x' --> 'y'

equal a[4:6] --> b[3:5] 'cd' --> 'cd'

insert a[6:6] --> b[5:6] '' --> 'f'

</pre></div>

</div>

</dd></dl>

get_grouped_opcodes(n=3)<a class="headerlink" href="#difflib.SequenceMatcher.get_grouped_opcodes" title="Link to this definition">¶</a></dt>

<dd>Return a <a class="reference internal" href="../glossary.html#term-generator">generator</a> of groups with up to n lines of context.

Starting with the groups returned by <a class="reference internal" href="#difflib.SequenceMatcher.get_opcodes" title="difflib.SequenceMatcher.get_opcodes"><code class="xref py py-meth docutils literal notranslate">get_opcodes()</code></a>, this method

splits out smaller change clusters and eliminates intervening ranges which

have no changes.

The groups are returned in the same format as <a class="reference internal" href="#difflib.SequenceMatcher.get_opcodes" title="difflib.SequenceMatcher.get_opcodes"><code class="xref py py-meth docutils literal notranslate">get_opcodes()</code></a>.

</dd></dl>

ratio()<a class="headerlink" href="#difflib.SequenceMatcher.ratio" title="Link to this definition">¶</a></dt>

<dd>Return a measure of the sequences' similarity as a float in the range [0,

1].

Where T is the total number of elements in both sequences, and M is the

number of matches, this is 2.0*M / T. Note that this is <code class="docutils literal notranslate">1.0</code> if the

sequences are identical, and <code class="docutils literal notranslate">0.0</code> if they have nothing in common.

This is expensive to compute if <a class="reference internal" href="#difflib.SequenceMatcher.get_matching_blocks" title="difflib.SequenceMatcher.get_matching_blocks"><code class="xref py py-meth docutils literal notranslate">get_matching_blocks()</code></a> or

<a class="reference internal" href="#difflib.SequenceMatcher.get_opcodes" title="difflib.SequenceMatcher.get_opcodes"><code class="xref py py-meth docutils literal notranslate">get_opcodes()</code></a> hasn't already been called, in which case you may want

to try <a class="reference internal" href="#difflib.SequenceMatcher.quick_ratio" title="difflib.SequenceMatcher.quick_ratio"><code class="xref py py-meth docutils literal notranslate">quick_ratio()</code></a> or <a class="reference internal" href="#difflib.SequenceMatcher.real_quick_ratio" title="difflib.SequenceMatcher.real_quick_ratio"><code class="xref py py-meth docutils literal notranslate">real_quick_ratio()</code></a> first to get an

upper bound.

توجه

Caution: The result of a <code class="xref py py-meth docutils literal notranslate">ratio()</code> call may depend on the order of

the arguments. For instance:

<div class="highlight-python3 notranslate"><div class="highlight"><pre>>>> SequenceMatcher(None, 'tide', 'diet').ratio()

0.25

>>> SequenceMatcher(None, 'diet', 'tide').ratio()

0.5

</pre></div>

</div>

</dd></dl>

quick_ratio()<a class="headerlink" href="#difflib.SequenceMatcher.quick_ratio" title="Link to this definition">¶</a></dt>

<dd>Return an upper bound on <a class="reference internal" href="#difflib.SequenceMatcher.ratio" title="difflib.SequenceMatcher.ratio"><code class="xref py py-meth docutils literal notranslate">ratio()</code></a> relatively quickly.

</dd></dl>

real_quick_ratio()<a class="headerlink" href="#difflib.SequenceMatcher.real_quick_ratio" title="Link to this definition">¶</a></dt>

</dd></dl>

The three methods that return the ratio of matching to total characters can give

different results due to differing levels of approximation, although

<a class="reference internal" href="#difflib.SequenceMatcher.quick_ratio" title="difflib.SequenceMatcher.quick_ratio"><code class="xref py py-meth docutils literal notranslate">quick_ratio()</code></a> and <a class="reference internal" href="#difflib.SequenceMatcher.real_quick_ratio" title="difflib.SequenceMatcher.real_quick_ratio"><code class="xref py py-meth docutils literal notranslate">real_quick_ratio()</code></a>

are always at least as large as <a class="reference internal" href="#difflib.SequenceMatcher.ratio" title="difflib.SequenceMatcher.ratio"><code class="xref py py-meth docutils literal notranslate">ratio()</code></a>:

<div class="doctest highlight-default notranslate"><div class="highlight"><pre>>>> s = SequenceMatcher(None, "abcd", "bcde")

>>> s.ratio()

0.75

>>> s.quick_ratio()

0.75

>>> s.real_quick_ratio()

1.0

</pre></div>

</div>

</section>

<h2>SequenceMatcher examples<a class="headerlink" href="#sequencematcher-examples" title="Link to this heading">¶</a></h2>

This example compares two strings, considering blanks to be "junk":

<div class="doctest highlight-default notranslate"><div class="highlight"><pre>>>> s = SequenceMatcher(lambda x: x == " ",

... "private Thread currentThread;",

... "private volatile Thread currentThread;")

</pre></div>

</div>

<a class="reference internal" href="#difflib.SequenceMatcher.ratio" title="difflib.SequenceMatcher.ratio"><code class="xref py py-meth docutils literal notranslate">ratio()</code></a> returns a float in [0, 1], measuring the similarity of the

sequences. As a rule of thumb, a <code class="xref py py-meth docutils literal notranslate">ratio()</code> value over 0.6 means the

sequences are close matches:

<div class="doctest highlight-default notranslate"><div class="highlight"><pre>>>> print(round(s.ratio(), 3))

0.866

</pre></div>

</div>

If you're only interested in where the sequences match,

<a class="reference internal" href="#difflib.SequenceMatcher.get_matching_blocks" title="difflib.SequenceMatcher.get_matching_blocks"><code class="xref py py-meth docutils literal notranslate">get_matching_blocks()</code></a> is handy:

<div class="doctest highlight-default notranslate"><div class="highlight"><pre>>>> for block in s.get_matching_blocks():

... print("a[%d] and b[%d] match for %d elements" % block)

a[0] and b[0] match for 8 elements

a[8] and b[17] match for 21 elements

a[29] and b[38] match for 0 elements

</pre></div>

</div>

Note that the last tuple returned by <a class="reference internal" href="#difflib.SequenceMatcher.get_matching_blocks" title="difflib.SequenceMatcher.get_matching_blocks"><code class="xref py py-meth docutils literal notranslate">get_matching_blocks()</code></a>

is always a dummy, <code class="docutils literal notranslate">(len(a), len(b), 0)</code>, and this is the only case in which the last

tuple element (number of elements matched) is <code class="docutils literal notranslate">0</code>.

If you want to know how to change the first sequence into the second, use

<div class="doctest highlight-default notranslate"><div class="highlight"><pre>>>> for opcode in s.get_opcodes():

... print("%6s a[%d:%d] b[%d:%d]" % opcode)

equal a[0:8] b[0:8]

insert a[8:8] b[8:17]

equal a[8:29] b[17:38]

</pre></div>

</div>

همچنین ملاحظه نمائید

<li>The <a class="reference internal" href="#difflib.get_close_matches" title="difflib.get_close_matches"><code class="xref py py-func docutils literal notranslate">get_close_matches()</code></a> function in this module which shows how

simple code building on <a class="reference internal" href="#difflib.SequenceMatcher" title="difflib.SequenceMatcher"><code class="xref py py-class docutils literal notranslate">SequenceMatcher</code></a> can be used to do useful

work.</li>

<li><a class="reference external" href="https://code.activestate.com/recipes/576729-simple-version-control/">Simple version control recipe</a> for a small application

built with <a class="reference internal" href="#difflib.SequenceMatcher" title="difflib.SequenceMatcher"><code class="xref py py-class docutils literal notranslate">SequenceMatcher</code></a>.</li>

</ul>

</div>

</section>

<h2>Differ objects<a class="headerlink" href="#differ-objects" title="Link to this heading">¶</a></h2>

Note that <a class="reference internal" href="#difflib.Differ" title="difflib.Differ"><code class="xref py py-class docutils literal notranslate">Differ</code></a>-generated deltas make no claim to be minimal

diffs. To the contrary, minimal diffs are often counter-intuitive, because they

synch up anywhere possible, sometimes accidental matches 100 pages apart.

Restricting synch points to contiguous matches preserves some notion of

locality, at the occasional cost of producing a longer diff.

The <a class="reference internal" href="#difflib.Differ" title="difflib.Differ"><code class="xref py py-class docutils literal notranslate">Differ</code></a> class has this constructor:

<dd>Optional keyword parameters linejunk and charjunk are for filter functions

(or <code class="docutils literal notranslate">None</code>):

linejunk: A function that accepts a single string argument, and returns true

if the string is junk. The default is <code class="docutils literal notranslate">None</code>, meaning that no line is

considered junk.

charjunk: A function that accepts a single character argument (a string of

length 1), and returns true if the character is junk. The default is <code class="docutils literal notranslate">None</code>,

meaning that no character is considered junk.

These junk-filtering functions speed up matching to find

differences and do not cause any differing lines or characters to

be ignored. Read the description of the

<a class="reference internal" href="#difflib.SequenceMatcher.find_longest_match" title="difflib.SequenceMatcher.find_longest_match"><code class="xref py py-meth docutils literal notranslate">find_longest_match()</code></a> method's isjunk

parameter for an explanation.

<a class="reference internal" href="#difflib.Differ" title="difflib.Differ"><code class="xref py py-class docutils literal notranslate">Differ</code></a> objects are used (deltas generated) via a single method:

compare(a, b)<a class="headerlink" href="#difflib.Differ.compare" title="Link to this definition">¶</a></dt>

<dd>Compare two sequences of lines, and generate the delta (a sequence of lines).

Each sequence must contain individual single-line strings ending with

newlines. Such sequences can be obtained from the

<a class="reference internal" href="io.html#io.IOBase.readlines" title="io.IOBase.readlines"><code class="xref py py-meth docutils literal notranslate">readlines()</code></a> method of file-like objects. The delta

generated also consists of newline-terminated strings, ready to be

printed as-is via the <a class="reference internal" href="io.html#io.IOBase.writelines" title="io.IOBase.writelines"><code class="xref py py-meth docutils literal notranslate">writelines()</code></a> method of a

file-like object.

</dd></dl>

</section>

<h2>Differ example<a class="headerlink" href="#differ-example" title="Link to this heading">¶</a></h2>

This example compares two texts. First we set up the texts, sequences of

individual single-line strings ending with newlines (such sequences can also be

obtained from the <a class="reference internal" href="io.html#io.IOBase.readlines" title="io.IOBase.readlines"><code class="xref py py-meth docutils literal notranslate">readlines()</code></a> method of file-like objects):

<div class="doctest highlight-default notranslate"><div class="highlight"><pre>>>> text1 = ''' 1. Beautiful is better than ugly.

... 2. Explicit is better than implicit.

... 3. Simple is better than complex.

... 4. Complex is better than complicated.

... '''.splitlines(keepends=True)

>>> len(text1)

4

>>> text1[0][-1]

'\n'

>>> text2 = ''' 1. Beautiful is better than ugly.

... 3. Simple is better than complex.

... 4. Complicated is better than complex.

... 5. Flat is better than nested.

</pre></div>

</div>

Next we instantiate a Differ object:

<div class="doctest highlight-default notranslate"><div class="highlight"><pre>>>> d = Differ()

</pre></div>

</div>

Note that when instantiating a <a class="reference internal" href="#difflib.Differ" title="difflib.Differ"><code class="xref py py-class docutils literal notranslate">Differ</code></a> object we may pass functions to

filter out line and character "junk." See the <a class="reference internal" href="#difflib.Differ" title="difflib.Differ"><code class="xref py py-meth docutils literal notranslate">Differ()</code></a> constructor for

details.

Finally, we compare the two:

<div class="doctest highlight-default notranslate"><div class="highlight"><pre>>>> result = list(d.compare(text1, text2))

</pre></div>

</div>

<code class="docutils literal notranslate">result</code> is a list of strings, so let's pretty-print it:

<div class="doctest highlight-default notranslate"><div class="highlight"><pre>>>> from pprint import pprint

>>> pprint(result)

[' 1. Beautiful is better than ugly.\n',

'- 2. Explicit is better than implicit.\n',

'- 3. Simple is better than complex.\n',

'+ 3. Simple is better than complex.\n',

'? ++\n',

'- 4. Complex is better than complicated.\n',

'? ^ ---- ^\n',

'+ 4. Complicated is better than complex.\n',

'? ++++ ^ ^\n',

'+ 5. Flat is better than nested.\n']

</pre></div>

</div>

As a single multi-line string it looks like this:

1. Beautiful is better than ugly.

- 2. Explicit is better than implicit.

- 3. Simple is better than complex.

+ 3. Simple is better than complex.

? ++

- 4. Complex is better than complicated.

? ^ ---- ^

+ 4. Complicated is better than complex.

? ++++ ^ ^

+ 5. Flat is better than nested.

</pre></div>

</div>

</section>

<h2>A command-line interface to difflib<a class="headerlink" href="#a-command-line-interface-to-difflib" title="Link to this heading">¶</a></h2>

This example shows how to use difflib to create a <code class="docutils literal notranslate">diff</code>-like utility.

<div class="highlight-python3 notranslate"><div class="highlight"><pre>""" Command-line interface to difflib.py providing diffs in four formats:

* ndiff: lists every line and highlights interline changes.

* context: highlights clusters of changes in a before/after format.

* unified: highlights clusters of changes in an inline format.

* html: generates side by side comparison with change highlights.

"""

import sys, os, difflib, argparse

import datetime as dt

def file_mtime(path):

t = dt.datetime.fromtimestamp(os.stat(path).st_mtime,

dt.timezone.utc)

return t.astimezone().isoformat()

def main():

parser = argparse.ArgumentParser()

parser.add_argument('-c', action='store_true', default=False,

help='Produce a context format diff (default)')

parser.add_argument('-u', action='store_true', default=False,

help='Produce a unified format diff')

parser.add_argument('-m', action='store_true', default=False,

help='Produce HTML side by side diff '

'(can use -c and -l in conjunction)')

parser.add_argument('-n', action='store_true', default=False,

help='Produce a ndiff format diff')

parser.add_argument('-l', '--lines', type=int, default=3,

help='Set number of context lines (default 3)')

parser.add_argument('fromfile')

parser.add_argument('tofile')

options = parser.parse_args()

n = options.lines

fromfile = options.fromfile

tofile = options.tofile

fromdate = file_mtime(fromfile)

todate = file_mtime(tofile)

with open(fromfile) as ff:

fromlines = ff.readlines()

with open(tofile) as tf:

tolines = tf.readlines()

if options.u:

diff = difflib.unified_diff(fromlines, tolines, fromfile, tofile, fromdate, todate, n=n)

elif options.n:

diff = difflib.ndiff(fromlines, tolines)

elif options.m:

diff = difflib.HtmlDiff().make_file(fromlines,tolines,fromfile,tofile,context=options.c,numlines=n)

else:

diff = difflib.context_diff(fromlines, tolines, fromfile, tofile, fromdate, todate, n=n)

View remainder of file in raw view

Navigation Menu

Uh oh!

Uh oh!

FilesExpand file tree

difflib.html

Latest commit

History

difflib.html

File metadata and controls