xls-rs 0.1.2

A powerful CLI tool and library for spreadsheet manipulation with pandas-style operations. Supports CSV, Excel (XLSX, XLS, ODS), Parquet, and Avro formats with formula evaluation, data transformation, and comprehensive analytics capabilities.
Documentation
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
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
//! CLI command definitions and handlers
//!
//! This module is organized into submodules for better maintainability:
//! - `commands/io`: File I/O commands (read, write, convert)
//! - `commands/transform`: Data transformation commands (sort, filter, etc.)
//! - `commands/pandas`: Pandas-style operations (head, tail, join, etc.)
//! - `commands/advanced`: Advanced features (validate, chart, batch, etc.)

pub mod commands;
pub mod format;
pub mod handler;
pub mod runtime;

use clap::{Parser, Subcommand};
use std::path::PathBuf;

pub use commands::CommandHandler;
pub use format::OutputFormat;
pub use handler::DefaultCommandHandler;

/// CLI structure
#[derive(Parser)]
#[command(name = "xls-rs")]
#[command(
    about = "A CLI tool for reading, writing, converting spreadsheet files with formula support",
    version = env!("CARGO_PKG_VERSION")
)]
pub struct Cli {
    /// Path to a config file (overrides discovery)
    #[arg(long)]
    pub config: Option<PathBuf>,

    /// Suppress non-data output (logs/progress)
    #[arg(long, default_value_t = false)]
    pub quiet: bool,

    /// Print additional debug output (logs/progress)
    #[arg(long, default_value_t = false)]
    pub verbose: bool,

    /// Allow overwriting output files
    #[arg(long, default_value_t = false)]
    pub overwrite: bool,

    #[command(subcommand)]
    pub command: Commands,
}

/// CLI commands
///
/// This enum represents all available commands in the xls-rs CLI.
/// Each command variant includes its specific parameters.
#[derive(Subcommand)]
pub enum Commands {
    /// Read data from a file and display it
    Read {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        sheet: Option<String>,
        #[arg(short, long)]
        range: Option<String>,
        /// If omitted, uses `default_format` from config (or csv).
        #[arg(short = 'f', long)]
        format: Option<OutputFormat>,
    },

    /// Write data to a file
    Write {
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        csv: Option<String>,
        #[arg(short, long)]
        sheet: Option<String>,
    },

    /// Convert between file formats
    Convert {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        sheet: Option<String>,
    },

    /// Apply formulas to a file
    Formula {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        formula: String,
        #[arg(short, long)]
        cell: String,
        #[arg(short, long)]
        sheet: Option<String>,
    },

    /// Start MCP server
    Serve,

    /// Sort data by column
    Sort {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        column: String,
        #[arg(short, long)]
        ascending: bool,
    },

    /// Filter rows by condition
    Filter {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short = 'w', long)]
        where_clause: String,
    },

    /// Find and replace values
    Replace {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        find: String,
        #[arg(short, long)]
        replace: String,
        #[arg(short, long)]
        column: Option<String>,
    },

    /// Remove duplicate rows
    Dedupe {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        columns: Option<String>,
    },

    /// Transpose data (rows to columns)
    Transpose {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
    },

    /// Append data to existing file
    Append {
        #[arg(short, long)]
        source: String,
        #[arg(short, long)]
        target: String,
    },

    /// List sheets in Excel file
    Sheets {
        #[arg(short, long)]
        input: String,
    },

    /// Read all sheets from Excel file
    ReadAll {
        #[arg(short, long)]
        input: String,
        /// If omitted, uses `default_format` from config (or csv).
        #[arg(short = 'f', long)]
        format: Option<OutputFormat>,
    },

    /// Write data to specific cell range
    WriteRange {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        start: String,
    },

    /// Select specific columns
    Select {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        columns: String,
    },

    /// Show first N rows
    Head {
        #[arg(short, long)]
        input: String,
        #[arg(short = 'n', long, default_value = "10")]
        n: usize,
        #[arg(short = 'f', long, default_value = "csv")]
        format: OutputFormat,
    },

    /// Show last N rows
    Tail {
        #[arg(short, long)]
        input: String,
        #[arg(short = 'n', long, default_value = "10")]
        n: usize,
        #[arg(short = 'f', long, default_value = "csv")]
        format: OutputFormat,
    },

    /// Sample random rows
    Sample {
        #[arg(short, long)]
        input: String,
        #[arg(short = 'n', long, default_value = "10")]
        n: usize,
        #[arg(short, long)]
        seed: Option<u64>,
        #[arg(short = 'f', long, default_value = "csv")]
        format: OutputFormat,
    },

    /// Show descriptive statistics
    Describe {
        #[arg(short, long)]
        input: String,
        #[arg(short = 'f', long, default_value = "csv")]
        format: OutputFormat,
    },

    /// Count unique values in column
    ValueCounts {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        column: String,
    },

    /// Calculate correlation matrix
    Corr {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        columns: Option<String>,
    },

    /// Group by column with aggregation
    Groupby {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        by: String,
        #[arg(short, long)]
        agg: String,
    },

    /// Join/merge two files
    Join {
        #[arg(short, long)]
        left: String,
        #[arg(short, long)]
        right: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        on: String,
        #[arg(short, long)]
        how: String,
    },

    /// Concatenate multiple files
    Concat {
        #[arg(short, long)]
        inputs: String,
        #[arg(short, long)]
        output: String,
    },

    /// Add computed column
    Mutate {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        column: String,
        #[arg(short, long)]
        formula: String,
    },

    /// Rename columns
    Rename {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        from: String,
        #[arg(short, long)]
        to: String,
    },

    /// Drop columns
    Drop {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        columns: String,
    },

    /// Fill missing values
    Fillna {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        value: String,
        #[arg(short, long)]
        columns: Option<String>,
    },

    /// Drop rows with missing values
    Dropna {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
    },

    /// Show column data types
    Dtypes {
        #[arg(short, long)]
        input: String,
    },

    /// Cast column types
    Astype {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        column: String,
        #[arg(short = 't', long)]
        target_type: String,
    },

    /// Get unique values
    Unique {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        column: String,
    },

    /// Show dataset info
    Info {
        #[arg(short, long)]
        input: String,
    },

    /// Clip values to range
    Clip {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        column: String,
        #[arg(short, long)]
        min: String,
        #[arg(short, long)]
        max: String,
    },

    /// Normalize column (0-1)
    Normalize {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        column: String,
    },

    /// Standardize column to z-scores (mean 0, std 1) for ML / statistics
    Zscore {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        column: String,
    },

    /// Query with SQL-like syntax
    Query {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short = 'w', long)]
        where_clause: String,
    },

    /// Create pivot table
    Pivot {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        index: String,
        #[arg(short, long)]
        columns: String,
        #[arg(short, long)]
        values: String,
        #[arg(short, long)]
        agg: String,
    },

    /// Rolling window mean or sum on a column (data rows ordered top to bottom)
    Rolling {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        column: String,
        #[arg(short, long)]
        window: usize,
        /// Aggregation: `mean`, `sum`, `avg` (same as mean)
        #[arg(long, default_value = "mean")]
        agg: String,
        /// Name for the new column (default: `{column}_roll{window}_{mean|sum}`)
        #[arg(long)]
        name: Option<String>,
    },

    /// Crosstab counts for two categorical columns
    Crosstab {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        rows: String,
        #[arg(short, long)]
        cols: String,
    },

    /// Melt / unpivot to long form (id columns + variable + value)
    Melt {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        /// Comma-separated id column names
        #[arg(long)]
        id_vars: String,
        /// Comma-separated value column names (omit to use all other columns)
        #[arg(long)]
        value_vars: Option<String>,
    },

    /// Parse and convert dates
    ParseDate {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        column: String,
        #[arg(short, long)]
        from_format: String,
        #[arg(short, long)]
        to_format: String,
    },

    /// Filter by regex pattern
    RegexFilter {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        column: String,
        #[arg(short, long)]
        pattern: String,
    },

    /// Replace by regex pattern
    RegexReplace {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        column: String,
        #[arg(short, long)]
        pattern: String,
        #[arg(short, long)]
        replacement: String,
    },

    /// Compare two datasets (diff)
    Diff {
        #[arg(short, long)]
        left: String,
        #[arg(short, long)]
        right: String,
        #[arg(short, long)]
        key: Option<String>,
    },

    /// Display ASCII histogram for numeric column
    Histogram {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        column: String,
        #[arg(short = 'n', long, default_value = "10")]
        bins: usize,
        #[arg(short, long, default_value = "40")]
        width: usize,
    },

    /// Export schema (column names and types) as JSON
    #[command(name = "schema")]
    Schema {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: Option<String>,
    },

    /// Generate SQL INSERT statements from data
    #[command(name = "to-sql")]
    ToSql {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        table: String,
        #[arg(short, long)]
        output: Option<String>,
        #[arg(short, long)]
        batch_size: Option<usize>,
    },

    /// Profile data quality
    Profile {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: Option<String>,
    },

    /// Validate data with rules
    Validate {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        rules: String,
        #[arg(short, long)]
        output: Option<String>,
        #[arg(short, long)]
        report: Option<String>,
    },

    /// Create chart from data
    Chart {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        chart_type: String,
        #[arg(short, long)]
        title: Option<String>,
        #[arg(short, long)]
        x_column: Option<String>,
        #[arg(short, long)]
        y_column: Option<String>,
    },

    /// Encrypt file
    Encrypt {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        algorithm: String,
        #[arg(short, long)]
        key_file: Option<String>,
    },

    /// Decrypt file
    Decrypt {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        key_file: Option<String>,
    },

    /// Batch process multiple files
    Batch {
        #[arg(short, long)]
        inputs: String,
        #[arg(short, long)]
        output_dir: String,
        #[arg(short, long)]
        operation: String,
        #[arg(short, long)]
        args: Vec<String>,
    },

    /// Run plugin function
    Plugin {
        #[arg(short, long)]
        function: String,
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        args: Vec<String>,
    },

    /// Stream process large file
    Stream {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(long, default_value_t = 1000)]
        chunk_size: usize,
    },

    /// Generate shell completions
    Completions {
        #[arg(short, long)]
        shell: String,
    },

    /// Generate deterministic example files under ./examples
    ExamplesGenerate,

    /// Watch file and re-run command on change
    #[cfg(feature = "watch")]
    Watch {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        command: String,
    },

    /// Initialize config file
    ConfigInit,

    /// Export styled Excel
    ExportStyled {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        style: Option<String>,
    },

    /// Add chart to Excel file
    AddChart {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        chart_type: String,
        #[arg(short, long)]
        title: Option<String>,
        #[arg(short, long)]
        category_column: Option<usize>,
        #[arg(short, long)]
        value_columns: Option<Vec<usize>>,
    },

    /// Add sparkline to Excel file
    AddSparkline {
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        data_range: String,
        #[arg(short, long)]
        sparkline_cell: String,
        #[arg(short, long)]
        sheet: Option<String>,
    },

    /// Add conditional formatting to Excel range
    ConditionalFormat {
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        range: String,
        #[arg(short, long)]
        condition: String,
        #[arg(short, long)]
        bg_color: Option<String>,
        #[arg(short, long)]
        font_color: Option<String>,
        #[arg(short = 'b', long)]
        bold: Option<bool>,
        #[arg(short, long)]
        sheet: Option<String>,
    },

    /// Apply formula to range in Excel file
    ApplyFormulaRange {
        #[arg(short, long)]
        input: String,
        #[arg(short, long)]
        output: String,
        #[arg(short, long)]
        formula: String,
        #[arg(short, long)]
        range: String,
        #[arg(short, long)]
        sheet: Option<String>,
    },

    /// List sheets in Google Sheets
    GSheetsList {
        #[arg(short, long)]
        spreadsheet: String,
    },

    /// Authorize Google Sheets access
    GSheetsAuth,

    /// Set default Google Sheets spreadsheet
    GSheetsSetDefault {
        #[arg(short, long)]
        spreadsheet: String,
    },
}

/// Execute a CLI command
///
/// This is the main entry point for command execution.
pub fn run(command: Commands) -> anyhow::Result<()> {
    let handler = DefaultCommandHandler::new();
    handler.handle(command)
}