officemd_cli 0.1.7

CLI for OfficeMD document extraction and markdown rendering
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
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
use std::process::Command;

use insta_cmd::{assert_cmd_snapshot, get_cargo_bin};

fn cli() -> Command {
    Command::new(get_cargo_bin("officemd"))
}

fn bind_common_filters() -> insta::internals::SettingsBindDropGuard {
    let mut settings = insta::Settings::clone_current();
    settings.add_filter(r"\bofficemd\.exe\b", "officemd");
    settings.add_filter(r"(?m)[ \t]+$", "");
    settings.bind_to_scope()
}

#[test]
fn top_level_help_snapshot() {
    let _guard = bind_common_filters();
    assert_cmd_snapshot!(
        cli().arg("--help"),
        @r###"
    success: true
    exit_code: 0
    ----- stdout -----
    Fast Office document extraction for LLMs and agents

    Usage: officemd [OPTIONS] [COMMAND]

    Commands:
      markdown  Extract markdown, print to stdout
      render    Extract markdown, render to terminal with ANSI formatting
      diff      Diff markdown output of two documents
      convert   Convert a document file to an output file
      stream    Stream output to stdout from a file path or stdin
      inspect   Inspect document metadata without full content rendering
      create    Create an Office document from markdown input
      help      Print this message or the help of the given subcommand(s)

    Options:
          --help-tree [<DEPTH>]  Show commands and options in a tree format. Depth 1 shows commands only, depth 2 includes arguments and options
      -h, --help                 Print help
      -V, --version              Print version

    ----- stderr -----
    "###,
    );
}

#[test]
fn markdown_help_snapshot() {
    let _guard = bind_common_filters();
    assert_cmd_snapshot!(
        cli().args(["markdown", "--help"]),
        @r#"
    success: true
    exit_code: 0
    ----- stdout -----
    Extract markdown, print to stdout

    Usage: officemd markdown [OPTIONS] <FILE>

    Arguments:
      <FILE>  Path to an input document

    Options:
          --format <FORMAT>
              Explicitly set the document format [possible values: docx, xlsx, csv, pptx, pdf]
          --output-format <OUTPUT_FORMAT>
              Output format: markdown (default) or json [possible values: markdown, json]
          --pretty
              Pretty-print JSON output
          --sheets <SHEETS>
              Filter XLSX sheets by name or 1-based index (comma-separated)
          --pages <PAGES>
              Select PDF pages/PPTX slides or XLSX/CSV sheet indices (e.g. "1,3-5")
          --slides <SLIDES>
              Filter PPTX slides by number or range (e.g. "1-3,5")
          --force
              Force extraction even for scanned/image-based PDFs
          --help-tree [<DEPTH>]
              Show commands and options in a tree format. Depth 1 shows commands only, depth 2 includes arguments and options
          --style-aware
              Use style-aware cell values for XLSX
          --streaming
              Use streaming row parser for XLSX
          --include-document-properties
              Include document properties in markdown output
          --no-headers-footers
              Omit DOCX header/footer sections from markdown output
          --no-formulas
              Omit XLSX formula footnotes from markdown output
          --no-frontmatter
              Omit the leading `<!-- officemd: ... -->` frontmatter comment
          --no-first-row-header
              Use synthetic Col1/Col2 headers instead of first data row
          --markdown-style <MARKDOWN_STYLE>
              Markdown style profile [default: compact] [possible values: compact, human]
      -h, --help
              Print help

    ----- stderr -----
    "#,
    );
}

#[test]
fn render_help_snapshot() {
    let _guard = bind_common_filters();
    assert_cmd_snapshot!(
        cli().args(["render", "--help"]),
        @r#"
    success: true
    exit_code: 0
    ----- stdout -----
    Extract markdown, render to terminal with ANSI formatting

    Usage: officemd render [OPTIONS] <FILE>

    Arguments:
      <FILE>  Path to an input document

    Options:
          --format <FORMAT>
              Explicitly set the document format [possible values: docx, xlsx, csv, pptx, pdf]
          --output-format <OUTPUT_FORMAT>
              Output format: markdown (default) or json [possible values: markdown, json]
          --pretty
              Pretty-print JSON output
          --sheets <SHEETS>
              Filter XLSX sheets by name or 1-based index (comma-separated)
          --pages <PAGES>
              Select PDF pages/PPTX slides or XLSX/CSV sheet indices (e.g. "1,3-5")
          --slides <SLIDES>
              Filter PPTX slides by number or range (e.g. "1-3,5")
          --force
              Force extraction even for scanned/image-based PDFs
          --help-tree [<DEPTH>]
              Show commands and options in a tree format. Depth 1 shows commands only, depth 2 includes arguments and options
          --style-aware
              Use style-aware cell values for XLSX
          --streaming
              Use streaming row parser for XLSX
          --include-document-properties
              Include document properties in markdown output
          --no-headers-footers
              Omit DOCX header/footer sections from markdown output
          --no-formulas
              Omit XLSX formula footnotes from markdown output
          --no-frontmatter
              Omit the leading `<!-- officemd: ... -->` frontmatter comment
          --no-first-row-header
              Use synthetic Col1/Col2 headers instead of first data row
          --markdown-style <MARKDOWN_STYLE>
              Markdown style profile [default: compact] [possible values: compact, human]
      -h, --help
              Print help

    ----- stderr -----
    "#,
    );
}

#[test]
fn diff_help_snapshot() {
    let _guard = bind_common_filters();
    assert_cmd_snapshot!(
        cli().args(["diff", "--help"]),
        @r#"
    success: true
    exit_code: 0
    ----- stdout -----
    Diff markdown output of two documents

    Usage: officemd diff [OPTIONS] <FILE_A> <FILE_B>

    Arguments:
      <FILE_A>  Path to first input document
      <FILE_B>  Path to second input document

    Options:
          --format <FORMAT>
              Explicitly set the document format [possible values: docx, xlsx, csv, pptx, pdf]
          --output-format <OUTPUT_FORMAT>
              Output format: markdown (default) or json [possible values: markdown, json]
          --pretty
              Pretty-print JSON output
          --sheets <SHEETS>
              Filter XLSX sheets by name or 1-based index (comma-separated)
          --pages <PAGES>
              Select PDF pages/PPTX slides or XLSX/CSV sheet indices (e.g. "1,3-5")
          --slides <SLIDES>
              Filter PPTX slides by number or range (e.g. "1-3,5")
          --force
              Force extraction even for scanned/image-based PDFs
          --help-tree [<DEPTH>]
              Show commands and options in a tree format. Depth 1 shows commands only, depth 2 includes arguments and options
          --style-aware
              Use style-aware cell values for XLSX
          --streaming
              Use streaming row parser for XLSX
          --include-document-properties
              Include document properties in markdown output
          --no-headers-footers
              Omit DOCX header/footer sections from markdown output
          --no-formulas
              Omit XLSX formula footnotes from markdown output
          --no-frontmatter
              Omit the leading `<!-- officemd: ... -->` frontmatter comment
          --no-first-row-header
              Use synthetic Col1/Col2 headers instead of first data row
          --markdown-style <MARKDOWN_STYLE>
              Markdown style profile [default: compact] [possible values: compact, human]
      -h, --help
              Print help

    ----- stderr -----
    "#,
    );
}

#[test]
fn convert_help_snapshot() {
    let _guard = bind_common_filters();
    assert_cmd_snapshot!(
        cli().args(["convert", "--help"]),
        @r#"
    success: true
    exit_code: 0
    ----- stdout -----
    Convert a document file to an output file

    Usage: officemd convert [OPTIONS] <INPUT>

    Arguments:
      <INPUT>  Input document path (.docx/.xlsx/.csv/.pptx/.pdf)

    Options:
      -o, --output <OUTPUT>
              Output file path. Defaults to <input>.md or <input>.json
          --format <FORMAT>
              Explicitly set the document format [possible values: docx, xlsx, csv, pptx, pdf]
          --output-format <OUTPUT_FORMAT>
              Output format: markdown (default) or json [possible values: markdown, json]
          --pretty
              Pretty-print JSON output
          --sheets <SHEETS>
              Filter XLSX sheets by name or 1-based index (comma-separated)
          --pages <PAGES>
              Select PDF pages/PPTX slides or XLSX/CSV sheet indices (e.g. "1,3-5")
          --slides <SLIDES>
              Filter PPTX slides by number or range (e.g. "1-3,5")
          --force
              Force extraction even for scanned/image-based PDFs
          --help-tree [<DEPTH>]
              Show commands and options in a tree format. Depth 1 shows commands only, depth 2 includes arguments and options
          --style-aware
              Use style-aware cell values for XLSX
          --streaming
              Use streaming row parser for XLSX
          --include-document-properties
              Include document properties in markdown output
          --no-headers-footers
              Omit DOCX header/footer sections from markdown output
          --no-formulas
              Omit XLSX formula footnotes from markdown output
          --no-frontmatter
              Omit the leading `<!-- officemd: ... -->` frontmatter comment
          --no-first-row-header
              Use synthetic Col1/Col2 headers instead of first data row
          --markdown-style <MARKDOWN_STYLE>
              Markdown style profile [default: compact] [possible values: compact, human]
      -h, --help
              Print help

    ----- stderr -----
    "#,
    );
}

#[test]
fn stream_help_snapshot() {
    let _guard = bind_common_filters();
    assert_cmd_snapshot!(
        cli().args(["stream", "--help"]),
        @r#"
    success: true
    exit_code: 0
    ----- stdout -----
    Stream output to stdout from a file path or stdin

    Usage: officemd stream [OPTIONS] [INPUT]

    Arguments:
      [INPUT]  Input path or '-' for stdin [default: -]

    Options:
          --format <FORMAT>
              Explicitly set the document format [possible values: docx, xlsx, csv, pptx, pdf]
          --output-format <OUTPUT_FORMAT>
              Output format: markdown (default) or json [possible values: markdown, json]
          --pretty
              Pretty-print JSON output
          --sheets <SHEETS>
              Filter XLSX sheets by name or 1-based index (comma-separated)
          --pages <PAGES>
              Select PDF pages/PPTX slides or XLSX/CSV sheet indices (e.g. "1,3-5")
          --slides <SLIDES>
              Filter PPTX slides by number or range (e.g. "1-3,5")
          --force
              Force extraction even for scanned/image-based PDFs
          --help-tree [<DEPTH>]
              Show commands and options in a tree format. Depth 1 shows commands only, depth 2 includes arguments and options
          --style-aware
              Use style-aware cell values for XLSX
          --streaming
              Use streaming row parser for XLSX
          --include-document-properties
              Include document properties in markdown output
          --no-headers-footers
              Omit DOCX header/footer sections from markdown output
          --no-formulas
              Omit XLSX formula footnotes from markdown output
          --no-frontmatter
              Omit the leading `<!-- officemd: ... -->` frontmatter comment
          --no-first-row-header
              Use synthetic Col1/Col2 headers instead of first data row
          --markdown-style <MARKDOWN_STYLE>
              Markdown style profile [default: compact] [possible values: compact, human]
      -h, --help
              Print help

    ----- stderr -----
    "#,
    );
}

#[test]
fn inspect_help_snapshot() {
    let _guard = bind_common_filters();
    assert_cmd_snapshot!(
        cli().args(["inspect", "--help"]),
        @r#"
    success: true
    exit_code: 0
    ----- stdout -----
    Inspect document metadata without full content rendering

    Usage: officemd inspect [OPTIONS] <INPUT>

    Arguments:
      <INPUT>  Input document path (.docx/.xlsx/.csv/.pptx/.pdf)

    Options:
          --format <FORMAT>
              Explicitly set the document format [possible values: docx, xlsx, csv, pptx, pdf]
          --output-format <OUTPUT_FORMAT>
              Output format: markdown (default) or json [possible values: markdown, json]
          --pretty
              Pretty-print JSON output
          --sheets <SHEETS>
              Filter XLSX sheets by name or 1-based index (comma-separated)
          --pages <PAGES>
              Select PDF pages/PPTX slides or XLSX/CSV sheet indices (e.g. "1,3-5")
          --slides <SLIDES>
              Filter PPTX slides by number or range (e.g. "1-3,5")
          --force
              Force extraction even for scanned/image-based PDFs
          --help-tree [<DEPTH>]
              Show commands and options in a tree format. Depth 1 shows commands only, depth 2 includes arguments and options
          --style-aware
              Use style-aware cell values for XLSX
          --streaming
              Use streaming row parser for XLSX
          --include-document-properties
              Include document properties in markdown output
          --no-headers-footers
              Omit DOCX header/footer sections from markdown output
          --no-formulas
              Omit XLSX formula footnotes from markdown output
          --no-frontmatter
              Omit the leading `<!-- officemd: ... -->` frontmatter comment
          --no-first-row-header
              Use synthetic Col1/Col2 headers instead of first data row
          --markdown-style <MARKDOWN_STYLE>
              Markdown style profile [default: compact] [possible values: compact, human]
      -h, --help
              Print help

    ----- stderr -----
    "#,
    );
}

#[test]
fn create_help_snapshot() {
    let _guard = bind_common_filters();
    assert_cmd_snapshot!(
        cli().args(["create", "--help"]),
        @r###"
    success: true
    exit_code: 0
    ----- stdout -----
    Create an Office document from markdown input.

    Reads officemd-flavored markdown and generates a .docx, .xlsx, or .pptx file. The output format is detected from the file extension.

    Examples: officemd create report.docx < input.md officemd create data.xlsx --input table.md officemd create slides.pptx --input deck.md

    Usage: officemd create [OPTIONS] <OUTPUT>

    Arguments:
      <OUTPUT>
              Output file path (.docx, .xlsx, .pptx)

    Options:
      -i, --input <INPUT>
              Input markdown file, or '-' for stdin (default)

              [default: -]

          --help-tree [<DEPTH>]
              Show commands and options in a tree format. Depth 1 shows commands only, depth 2 includes arguments and options

      -h, --help
              Print help (see a summary with '-h')

    ----- stderr -----
    "###,
    );
}