kreuzberg 4.0.0.pre.rc.29 → 4.0.0.rc1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/.gitignore +0 -6
- data/.rubocop.yaml +534 -1
- data/Gemfile +2 -1
- data/Gemfile.lock +28 -116
- data/README.md +269 -629
- data/Rakefile +0 -9
- data/Steepfile +4 -8
- data/examples/async_patterns.rb +58 -1
- data/ext/kreuzberg_rb/extconf.rb +5 -35
- data/ext/kreuzberg_rb/native/Cargo.toml +16 -55
- data/ext/kreuzberg_rb/native/build.rs +14 -12
- data/ext/kreuzberg_rb/native/include/ieeefp.h +1 -1
- data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +1 -1
- data/ext/kreuzberg_rb/native/include/strings.h +2 -2
- data/ext/kreuzberg_rb/native/include/unistd.h +1 -1
- data/ext/kreuzberg_rb/native/src/lib.rs +34 -897
- data/extconf.rb +6 -38
- data/kreuzberg.gemspec +20 -114
- data/lib/kreuzberg/api_proxy.rb +18 -2
- data/lib/kreuzberg/cache_api.rb +0 -22
- data/lib/kreuzberg/cli.rb +10 -2
- data/lib/kreuzberg/cli_proxy.rb +10 -0
- data/lib/kreuzberg/config.rb +22 -274
- data/lib/kreuzberg/errors.rb +7 -73
- data/lib/kreuzberg/extraction_api.rb +8 -237
- data/lib/kreuzberg/mcp_proxy.rb +11 -2
- data/lib/kreuzberg/ocr_backend_protocol.rb +73 -0
- data/lib/kreuzberg/post_processor_protocol.rb +71 -0
- data/lib/kreuzberg/result.rb +33 -151
- data/lib/kreuzberg/setup_lib_path.rb +2 -22
- data/lib/kreuzberg/validator_protocol.rb +73 -0
- data/lib/kreuzberg/version.rb +1 -1
- data/lib/kreuzberg.rb +13 -27
- data/pkg/kreuzberg-4.0.0.rc1.gem +0 -0
- data/sig/kreuzberg.rbs +12 -105
- data/spec/binding/cache_spec.rb +22 -22
- data/spec/binding/cli_proxy_spec.rb +4 -2
- data/spec/binding/cli_spec.rb +11 -12
- data/spec/binding/config_spec.rb +0 -74
- data/spec/binding/config_validation_spec.rb +6 -100
- data/spec/binding/error_handling_spec.rb +97 -283
- data/spec/binding/plugins/ocr_backend_spec.rb +8 -8
- data/spec/binding/plugins/postprocessor_spec.rb +11 -11
- data/spec/binding/plugins/validator_spec.rb +13 -12
- data/spec/examples.txt +104 -0
- data/spec/fixtures/config.toml +1 -0
- data/spec/fixtures/config.yaml +1 -0
- data/spec/fixtures/invalid_config.toml +1 -0
- data/spec/smoke/package_spec.rb +3 -2
- data/spec/spec_helper.rb +3 -1
- data/vendor/kreuzberg/Cargo.toml +67 -192
- data/vendor/kreuzberg/README.md +9 -97
- data/vendor/kreuzberg/build.rs +194 -516
- data/vendor/kreuzberg/src/api/handlers.rs +9 -130
- data/vendor/kreuzberg/src/api/mod.rs +3 -18
- data/vendor/kreuzberg/src/api/server.rs +71 -236
- data/vendor/kreuzberg/src/api/types.rs +7 -43
- data/vendor/kreuzberg/src/bin/profile_extract.rs +455 -0
- data/vendor/kreuzberg/src/cache/mod.rs +3 -27
- data/vendor/kreuzberg/src/chunking/mod.rs +79 -1705
- data/vendor/kreuzberg/src/core/batch_mode.rs +0 -60
- data/vendor/kreuzberg/src/core/config.rs +23 -905
- data/vendor/kreuzberg/src/core/extractor.rs +106 -403
- data/vendor/kreuzberg/src/core/io.rs +2 -4
- data/vendor/kreuzberg/src/core/mime.rs +12 -2
- data/vendor/kreuzberg/src/core/mod.rs +3 -22
- data/vendor/kreuzberg/src/core/pipeline.rs +78 -395
- data/vendor/kreuzberg/src/embeddings.rs +21 -169
- data/vendor/kreuzberg/src/error.rs +2 -2
- data/vendor/kreuzberg/src/extraction/archive.rs +31 -36
- data/vendor/kreuzberg/src/extraction/docx.rs +1 -365
- data/vendor/kreuzberg/src/extraction/email.rs +11 -12
- data/vendor/kreuzberg/src/extraction/excel.rs +129 -138
- data/vendor/kreuzberg/src/extraction/html.rs +170 -1447
- data/vendor/kreuzberg/src/extraction/image.rs +14 -138
- data/vendor/kreuzberg/src/extraction/libreoffice.rs +3 -13
- data/vendor/kreuzberg/src/extraction/mod.rs +5 -21
- data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +0 -2
- data/vendor/kreuzberg/src/extraction/pandoc/batch.rs +275 -0
- data/vendor/kreuzberg/src/extraction/pandoc/mime_types.rs +178 -0
- data/vendor/kreuzberg/src/extraction/pandoc/mod.rs +491 -0
- data/vendor/kreuzberg/src/extraction/pandoc/server.rs +496 -0
- data/vendor/kreuzberg/src/extraction/pandoc/subprocess.rs +1188 -0
- data/vendor/kreuzberg/src/extraction/pandoc/version.rs +162 -0
- data/vendor/kreuzberg/src/extraction/pptx.rs +94 -196
- data/vendor/kreuzberg/src/extraction/structured.rs +4 -5
- data/vendor/kreuzberg/src/extraction/table.rs +1 -2
- data/vendor/kreuzberg/src/extraction/text.rs +10 -18
- data/vendor/kreuzberg/src/extractors/archive.rs +0 -22
- data/vendor/kreuzberg/src/extractors/docx.rs +148 -69
- data/vendor/kreuzberg/src/extractors/email.rs +9 -37
- data/vendor/kreuzberg/src/extractors/excel.rs +40 -81
- data/vendor/kreuzberg/src/extractors/html.rs +173 -182
- data/vendor/kreuzberg/src/extractors/image.rs +8 -32
- data/vendor/kreuzberg/src/extractors/mod.rs +10 -171
- data/vendor/kreuzberg/src/extractors/pandoc.rs +201 -0
- data/vendor/kreuzberg/src/extractors/pdf.rs +64 -329
- data/vendor/kreuzberg/src/extractors/pptx.rs +34 -79
- data/vendor/kreuzberg/src/extractors/structured.rs +0 -16
- data/vendor/kreuzberg/src/extractors/text.rs +7 -30
- data/vendor/kreuzberg/src/extractors/xml.rs +8 -27
- data/vendor/kreuzberg/src/keywords/processor.rs +1 -9
- data/vendor/kreuzberg/src/keywords/rake.rs +1 -0
- data/vendor/kreuzberg/src/language_detection/mod.rs +51 -94
- data/vendor/kreuzberg/src/lib.rs +5 -17
- data/vendor/kreuzberg/src/mcp/mod.rs +1 -4
- data/vendor/kreuzberg/src/mcp/server.rs +21 -145
- data/vendor/kreuzberg/src/ocr/mod.rs +0 -2
- data/vendor/kreuzberg/src/ocr/processor.rs +8 -19
- data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +0 -2
- data/vendor/kreuzberg/src/pdf/error.rs +1 -93
- data/vendor/kreuzberg/src/pdf/metadata.rs +100 -263
- data/vendor/kreuzberg/src/pdf/mod.rs +2 -33
- data/vendor/kreuzberg/src/pdf/rendering.rs +12 -12
- data/vendor/kreuzberg/src/pdf/table.rs +64 -61
- data/vendor/kreuzberg/src/pdf/text.rs +24 -416
- data/vendor/kreuzberg/src/plugins/extractor.rs +8 -40
- data/vendor/kreuzberg/src/plugins/mod.rs +0 -3
- data/vendor/kreuzberg/src/plugins/ocr.rs +14 -22
- data/vendor/kreuzberg/src/plugins/processor.rs +1 -10
- data/vendor/kreuzberg/src/plugins/registry.rs +0 -15
- data/vendor/kreuzberg/src/plugins/validator.rs +8 -20
- data/vendor/kreuzberg/src/stopwords/mod.rs +2 -2
- data/vendor/kreuzberg/src/text/mod.rs +0 -8
- data/vendor/kreuzberg/src/text/quality.rs +15 -28
- data/vendor/kreuzberg/src/text/string_utils.rs +10 -22
- data/vendor/kreuzberg/src/text/token_reduction/core.rs +50 -86
- data/vendor/kreuzberg/src/text/token_reduction/filters.rs +16 -37
- data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +1 -2
- data/vendor/kreuzberg/src/types.rs +67 -907
- data/vendor/kreuzberg/src/utils/mod.rs +0 -14
- data/vendor/kreuzberg/src/utils/quality.rs +3 -12
- data/vendor/kreuzberg/tests/api_tests.rs +0 -506
- data/vendor/kreuzberg/tests/archive_integration.rs +0 -2
- data/vendor/kreuzberg/tests/batch_orchestration.rs +12 -57
- data/vendor/kreuzberg/tests/batch_processing.rs +8 -32
- data/vendor/kreuzberg/tests/chunking_offset_demo.rs +92 -0
- data/vendor/kreuzberg/tests/concurrency_stress.rs +8 -40
- data/vendor/kreuzberg/tests/config_features.rs +1 -33
- data/vendor/kreuzberg/tests/config_loading_tests.rs +39 -16
- data/vendor/kreuzberg/tests/core_integration.rs +9 -35
- data/vendor/kreuzberg/tests/csv_integration.rs +81 -71
- data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +25 -23
- data/vendor/kreuzberg/tests/email_integration.rs +1 -3
- data/vendor/kreuzberg/tests/error_handling.rs +34 -43
- data/vendor/kreuzberg/tests/format_integration.rs +1 -7
- data/vendor/kreuzberg/tests/helpers/mod.rs +0 -60
- data/vendor/kreuzberg/tests/image_integration.rs +0 -2
- data/vendor/kreuzberg/tests/mime_detection.rs +16 -17
- data/vendor/kreuzberg/tests/ocr_configuration.rs +0 -4
- data/vendor/kreuzberg/tests/ocr_errors.rs +0 -22
- data/vendor/kreuzberg/tests/ocr_quality.rs +0 -2
- data/vendor/kreuzberg/tests/pandoc_integration.rs +503 -0
- data/vendor/kreuzberg/tests/pdf_integration.rs +0 -2
- data/vendor/kreuzberg/tests/pipeline_integration.rs +2 -36
- data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +0 -5
- data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +1 -17
- data/vendor/kreuzberg/tests/plugin_system.rs +0 -6
- data/vendor/kreuzberg/tests/registry_integration_tests.rs +22 -2
- data/vendor/kreuzberg/tests/security_validation.rs +1 -13
- data/vendor/kreuzberg/tests/test_fastembed.rs +23 -45
- metadata +25 -171
- data/.rubocop.yml +0 -543
- data/ext/kreuzberg_rb/native/.cargo/config.toml +0 -23
- data/ext/kreuzberg_rb/native/Cargo.lock +0 -7619
- data/lib/kreuzberg/error_context.rb +0 -136
- data/lib/kreuzberg/types.rb +0 -170
- data/lib/libpdfium.so +0 -0
- data/spec/binding/async_operations_spec.rb +0 -473
- data/spec/binding/batch_operations_spec.rb +0 -595
- data/spec/binding/batch_spec.rb +0 -359
- data/spec/binding/config_result_spec.rb +0 -377
- data/spec/binding/embeddings_spec.rb +0 -816
- data/spec/binding/error_recovery_spec.rb +0 -488
- data/spec/binding/font_config_spec.rb +0 -220
- data/spec/binding/images_spec.rb +0 -738
- data/spec/binding/keywords_extraction_spec.rb +0 -600
- data/spec/binding/metadata_types_spec.rb +0 -1228
- data/spec/binding/pages_extraction_spec.rb +0 -471
- data/spec/binding/tables_spec.rb +0 -641
- data/spec/unit/config/chunking_config_spec.rb +0 -213
- data/spec/unit/config/embedding_config_spec.rb +0 -343
- data/spec/unit/config/extraction_config_spec.rb +0 -438
- data/spec/unit/config/font_config_spec.rb +0 -285
- data/spec/unit/config/hierarchy_config_spec.rb +0 -314
- data/spec/unit/config/image_extraction_config_spec.rb +0 -209
- data/spec/unit/config/image_preprocessing_config_spec.rb +0 -249
- data/spec/unit/config/keyword_config_spec.rb +0 -229
- data/spec/unit/config/language_detection_config_spec.rb +0 -258
- data/spec/unit/config/ocr_config_spec.rb +0 -171
- data/spec/unit/config/page_config_spec.rb +0 -221
- data/spec/unit/config/pdf_config_spec.rb +0 -267
- data/spec/unit/config/postprocessor_config_spec.rb +0 -290
- data/spec/unit/config/tesseract_config_spec.rb +0 -181
- data/spec/unit/config/token_reduction_config_spec.rb +0 -251
- data/test/metadata_types_test.rb +0 -959
- data/vendor/Cargo.toml +0 -61
- data/vendor/kreuzberg/examples/bench_fixes.rs +0 -71
- data/vendor/kreuzberg/examples/test_pdfium_fork.rs +0 -62
- data/vendor/kreuzberg/src/chunking/processor.rs +0 -219
- data/vendor/kreuzberg/src/core/batch_optimizations.rs +0 -385
- data/vendor/kreuzberg/src/core/config_validation.rs +0 -949
- data/vendor/kreuzberg/src/core/formats.rs +0 -235
- data/vendor/kreuzberg/src/core/server_config.rs +0 -1220
- data/vendor/kreuzberg/src/extraction/capacity.rs +0 -263
- data/vendor/kreuzberg/src/extraction/markdown.rs +0 -216
- data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +0 -284
- data/vendor/kreuzberg/src/extractors/bibtex.rs +0 -470
- data/vendor/kreuzberg/src/extractors/docbook.rs +0 -504
- data/vendor/kreuzberg/src/extractors/epub.rs +0 -696
- data/vendor/kreuzberg/src/extractors/fictionbook.rs +0 -492
- data/vendor/kreuzberg/src/extractors/jats.rs +0 -1054
- data/vendor/kreuzberg/src/extractors/jupyter.rs +0 -368
- data/vendor/kreuzberg/src/extractors/latex.rs +0 -653
- data/vendor/kreuzberg/src/extractors/markdown.rs +0 -701
- data/vendor/kreuzberg/src/extractors/odt.rs +0 -628
- data/vendor/kreuzberg/src/extractors/opml.rs +0 -635
- data/vendor/kreuzberg/src/extractors/orgmode.rs +0 -529
- data/vendor/kreuzberg/src/extractors/rst.rs +0 -577
- data/vendor/kreuzberg/src/extractors/rtf.rs +0 -809
- data/vendor/kreuzberg/src/extractors/security.rs +0 -484
- data/vendor/kreuzberg/src/extractors/security_tests.rs +0 -367
- data/vendor/kreuzberg/src/extractors/typst.rs +0 -651
- data/vendor/kreuzberg/src/language_detection/processor.rs +0 -218
- data/vendor/kreuzberg/src/ocr/language_registry.rs +0 -520
- data/vendor/kreuzberg/src/panic_context.rs +0 -154
- data/vendor/kreuzberg/src/pdf/bindings.rs +0 -306
- data/vendor/kreuzberg/src/pdf/bundled.rs +0 -408
- data/vendor/kreuzberg/src/pdf/fonts.rs +0 -358
- data/vendor/kreuzberg/src/pdf/hierarchy.rs +0 -903
- data/vendor/kreuzberg/src/text/quality_processor.rs +0 -231
- data/vendor/kreuzberg/src/text/utf8_validation.rs +0 -193
- data/vendor/kreuzberg/src/utils/pool.rs +0 -503
- data/vendor/kreuzberg/src/utils/pool_sizing.rs +0 -364
- data/vendor/kreuzberg/src/utils/string_pool.rs +0 -761
- data/vendor/kreuzberg/tests/api_embed.rs +0 -360
- data/vendor/kreuzberg/tests/api_extract_multipart.rs +0 -52
- data/vendor/kreuzberg/tests/api_large_pdf_extraction.rs +0 -471
- data/vendor/kreuzberg/tests/api_large_pdf_extraction_diagnostics.rs +0 -289
- data/vendor/kreuzberg/tests/batch_pooling_benchmark.rs +0 -154
- data/vendor/kreuzberg/tests/bibtex_parity_test.rs +0 -421
- data/vendor/kreuzberg/tests/config_integration_test.rs +0 -753
- data/vendor/kreuzberg/tests/data/hierarchy_ground_truth.json +0 -294
- data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +0 -500
- data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +0 -370
- data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +0 -275
- data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +0 -228
- data/vendor/kreuzberg/tests/html_table_test.rs +0 -551
- data/vendor/kreuzberg/tests/instrumentation_test.rs +0 -139
- data/vendor/kreuzberg/tests/jats_extractor_tests.rs +0 -639
- data/vendor/kreuzberg/tests/jupyter_extractor_tests.rs +0 -704
- data/vendor/kreuzberg/tests/latex_extractor_tests.rs +0 -496
- data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +0 -490
- data/vendor/kreuzberg/tests/ocr_language_registry.rs +0 -191
- data/vendor/kreuzberg/tests/odt_extractor_tests.rs +0 -674
- data/vendor/kreuzberg/tests/opml_extractor_tests.rs +0 -616
- data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +0 -822
- data/vendor/kreuzberg/tests/page_markers.rs +0 -297
- data/vendor/kreuzberg/tests/pdf_hierarchy_detection.rs +0 -301
- data/vendor/kreuzberg/tests/pdf_hierarchy_quality.rs +0 -589
- data/vendor/kreuzberg/tests/pdf_ocr_triggering.rs +0 -301
- data/vendor/kreuzberg/tests/pdf_text_merging.rs +0 -475
- data/vendor/kreuzberg/tests/pdfium_linking.rs +0 -340
- data/vendor/kreuzberg/tests/rst_extractor_tests.rs +0 -694
- data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +0 -775
- data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +0 -1260
- data/vendor/kreuzberg/tests/typst_extractor_tests.rs +0 -648
- data/vendor/kreuzberg-ffi/Cargo.toml +0 -67
- data/vendor/kreuzberg-ffi/README.md +0 -851
- data/vendor/kreuzberg-ffi/benches/result_view_benchmark.rs +0 -227
- data/vendor/kreuzberg-ffi/build.rs +0 -168
- data/vendor/kreuzberg-ffi/cbindgen.toml +0 -37
- data/vendor/kreuzberg-ffi/kreuzberg-ffi.pc.in +0 -12
- data/vendor/kreuzberg-ffi/kreuzberg.h +0 -3012
- data/vendor/kreuzberg-ffi/src/batch_streaming.rs +0 -588
- data/vendor/kreuzberg-ffi/src/config.rs +0 -1341
- data/vendor/kreuzberg-ffi/src/error.rs +0 -901
- data/vendor/kreuzberg-ffi/src/extraction.rs +0 -555
- data/vendor/kreuzberg-ffi/src/helpers.rs +0 -879
- data/vendor/kreuzberg-ffi/src/lib.rs +0 -977
- data/vendor/kreuzberg-ffi/src/memory.rs +0 -493
- data/vendor/kreuzberg-ffi/src/mime.rs +0 -329
- data/vendor/kreuzberg-ffi/src/panic_shield.rs +0 -265
- data/vendor/kreuzberg-ffi/src/plugins/document_extractor.rs +0 -442
- data/vendor/kreuzberg-ffi/src/plugins/mod.rs +0 -14
- data/vendor/kreuzberg-ffi/src/plugins/ocr_backend.rs +0 -628
- data/vendor/kreuzberg-ffi/src/plugins/post_processor.rs +0 -438
- data/vendor/kreuzberg-ffi/src/plugins/validator.rs +0 -329
- data/vendor/kreuzberg-ffi/src/result.rs +0 -510
- data/vendor/kreuzberg-ffi/src/result_pool.rs +0 -639
- data/vendor/kreuzberg-ffi/src/result_view.rs +0 -773
- data/vendor/kreuzberg-ffi/src/string_intern.rs +0 -568
- data/vendor/kreuzberg-ffi/src/types.rs +0 -363
- data/vendor/kreuzberg-ffi/src/util.rs +0 -210
- data/vendor/kreuzberg-ffi/src/validation.rs +0 -848
- data/vendor/kreuzberg-ffi/tests.disabled/README.md +0 -48
- data/vendor/kreuzberg-ffi/tests.disabled/config_loading_tests.rs +0 -299
- data/vendor/kreuzberg-ffi/tests.disabled/config_tests.rs +0 -346
- data/vendor/kreuzberg-ffi/tests.disabled/extractor_tests.rs +0 -232
- data/vendor/kreuzberg-ffi/tests.disabled/plugin_registration_tests.rs +0 -470
- data/vendor/kreuzberg-tesseract/.commitlintrc.json +0 -13
- data/vendor/kreuzberg-tesseract/.crate-ignore +0 -2
- data/vendor/kreuzberg-tesseract/Cargo.lock +0 -2933
- data/vendor/kreuzberg-tesseract/Cargo.toml +0 -57
- data/vendor/kreuzberg-tesseract/LICENSE +0 -22
- data/vendor/kreuzberg-tesseract/README.md +0 -399
- data/vendor/kreuzberg-tesseract/build.rs +0 -1127
- data/vendor/kreuzberg-tesseract/patches/README.md +0 -71
- data/vendor/kreuzberg-tesseract/patches/tesseract.diff +0 -199
- data/vendor/kreuzberg-tesseract/src/api.rs +0 -1371
- data/vendor/kreuzberg-tesseract/src/choice_iterator.rs +0 -77
- data/vendor/kreuzberg-tesseract/src/enums.rs +0 -297
- data/vendor/kreuzberg-tesseract/src/error.rs +0 -81
- data/vendor/kreuzberg-tesseract/src/lib.rs +0 -145
- data/vendor/kreuzberg-tesseract/src/monitor.rs +0 -57
- data/vendor/kreuzberg-tesseract/src/mutable_iterator.rs +0 -197
- data/vendor/kreuzberg-tesseract/src/page_iterator.rs +0 -253
- data/vendor/kreuzberg-tesseract/src/result_iterator.rs +0 -286
- data/vendor/kreuzberg-tesseract/src/result_renderer.rs +0 -183
- data/vendor/kreuzberg-tesseract/tests/integration_test.rs +0 -211
|
@@ -34,7 +34,6 @@ use std::io::Cursor;
|
|
|
34
34
|
use std::path::Path;
|
|
35
35
|
|
|
36
36
|
use crate::error::{KreuzbergError, Result};
|
|
37
|
-
use crate::extraction::capacity;
|
|
38
37
|
use crate::types::{ExcelSheet, ExcelWorkbook};
|
|
39
38
|
|
|
40
39
|
#[cfg(feature = "office")]
|
|
@@ -145,153 +144,110 @@ fn process_sheet(name: &str, range: &Range<Data>) -> ExcelSheet {
|
|
|
145
144
|
|
|
146
145
|
let estimated_capacity = 50 + (cols * 20) + (rows * cols * 12);
|
|
147
146
|
|
|
148
|
-
if rows == 0 || cols == 0 {
|
|
149
|
-
|
|
150
|
-
ExcelSheet {
|
|
151
|
-
name: name.to_owned(),
|
|
152
|
-
markdown,
|
|
153
|
-
row_count: rows,
|
|
154
|
-
col_count: cols,
|
|
155
|
-
cell_count,
|
|
156
|
-
table_cells: None,
|
|
157
|
-
}
|
|
147
|
+
let markdown = if rows == 0 || cols == 0 {
|
|
148
|
+
format!("## {}\n\n*Empty sheet*", name)
|
|
158
149
|
} else {
|
|
159
|
-
|
|
160
|
-
|
|
161
|
-
|
|
162
|
-
|
|
163
|
-
|
|
164
|
-
|
|
165
|
-
|
|
166
|
-
|
|
167
|
-
|
|
150
|
+
generate_markdown_from_range_optimized(name, range, estimated_capacity)
|
|
151
|
+
};
|
|
152
|
+
|
|
153
|
+
ExcelSheet {
|
|
154
|
+
name: name.to_owned(),
|
|
155
|
+
markdown,
|
|
156
|
+
row_count: rows,
|
|
157
|
+
col_count: cols,
|
|
158
|
+
cell_count,
|
|
168
159
|
}
|
|
169
160
|
}
|
|
170
161
|
|
|
171
|
-
|
|
172
|
-
|
|
173
|
-
|
|
174
|
-
|
|
175
|
-
|
|
176
|
-
///
|
|
177
|
-
/// Returns (markdown, table_cells) where table_cells is a 2D vector of strings.
|
|
178
|
-
fn generate_markdown_and_cells(sheet_name: &str, range: &Range<Data>, capacity: usize) -> (String, Vec<Vec<String>>) {
|
|
162
|
+
fn generate_markdown_from_range_optimized(sheet_name: &str, range: &Range<Data>, capacity: usize) -> String {
|
|
163
|
+
let mut result = String::with_capacity(capacity);
|
|
164
|
+
|
|
165
|
+
write!(result, "## {}\n\n", sheet_name).unwrap();
|
|
166
|
+
|
|
179
167
|
let rows: Vec<_> = range.rows().collect();
|
|
180
168
|
if rows.is_empty() {
|
|
181
|
-
|
|
182
|
-
|
|
183
|
-
write!(result, "## {}\n\n*No data*", sheet_name).unwrap();
|
|
184
|
-
return (result, Vec::new());
|
|
169
|
+
result.push_str("*No data*");
|
|
170
|
+
return result;
|
|
185
171
|
}
|
|
186
172
|
|
|
187
173
|
let header = &rows[0];
|
|
188
174
|
let header_len = header.len();
|
|
189
|
-
let row_count = rows.len();
|
|
190
|
-
|
|
191
|
-
let table_capacity = capacity::estimate_table_markdown_capacity(row_count, header_len);
|
|
192
|
-
|
|
193
|
-
let mut exact_size = 16 + sheet_name.len();
|
|
194
|
-
|
|
195
|
-
exact_size += 2 + (header_len * 2);
|
|
196
|
-
exact_size += header_len * 10;
|
|
197
|
-
|
|
198
|
-
exact_size += 5 + (header_len * 5);
|
|
199
|
-
|
|
200
|
-
exact_size += (row_count - 1) * (5 + header_len * 15);
|
|
201
|
-
|
|
202
|
-
let mut markdown = String::with_capacity(exact_size.max(table_capacity).max(capacity));
|
|
203
|
-
let mut cells: Vec<Vec<String>> = Vec::with_capacity(row_count);
|
|
204
|
-
|
|
205
|
-
write!(markdown, "## {}\n\n", sheet_name).unwrap();
|
|
206
175
|
|
|
207
|
-
|
|
208
|
-
markdown.push_str("| ");
|
|
176
|
+
result.push_str("| ");
|
|
209
177
|
for (i, cell) in header.iter().enumerate() {
|
|
210
178
|
if i > 0 {
|
|
211
|
-
|
|
212
|
-
}
|
|
213
|
-
let cell_str = format_cell_to_string(cell);
|
|
214
|
-
header_cells.push(cell_str.clone());
|
|
215
|
-
|
|
216
|
-
if cell_str.contains('|') || cell_str.contains('\\') {
|
|
217
|
-
escape_markdown_into(&mut markdown, &cell_str);
|
|
218
|
-
} else {
|
|
219
|
-
markdown.push_str(&cell_str);
|
|
179
|
+
result.push_str(" | ");
|
|
220
180
|
}
|
|
181
|
+
format_cell_value_into(&mut result, cell);
|
|
221
182
|
}
|
|
222
|
-
|
|
223
|
-
cells.push(header_cells);
|
|
183
|
+
result.push_str(" |\n");
|
|
224
184
|
|
|
225
|
-
|
|
185
|
+
result.push_str("| ");
|
|
226
186
|
for i in 0..header_len {
|
|
227
187
|
if i > 0 {
|
|
228
|
-
|
|
188
|
+
result.push_str(" | ");
|
|
229
189
|
}
|
|
230
|
-
|
|
190
|
+
result.push_str("---");
|
|
231
191
|
}
|
|
232
|
-
|
|
192
|
+
result.push_str(" |\n");
|
|
233
193
|
|
|
234
194
|
for row in rows.iter().skip(1) {
|
|
235
|
-
|
|
236
|
-
markdown.push_str("| ");
|
|
195
|
+
result.push_str("| ");
|
|
237
196
|
for i in 0..header_len {
|
|
238
197
|
if i > 0 {
|
|
239
|
-
|
|
198
|
+
result.push_str(" | ");
|
|
240
199
|
}
|
|
241
200
|
if let Some(cell) = row.get(i) {
|
|
242
|
-
|
|
243
|
-
row_cells.push(cell_str.clone());
|
|
244
|
-
|
|
245
|
-
if cell_str.contains('|') || cell_str.contains('\\') {
|
|
246
|
-
escape_markdown_into(&mut markdown, &cell_str);
|
|
247
|
-
} else {
|
|
248
|
-
markdown.push_str(&cell_str);
|
|
249
|
-
}
|
|
250
|
-
} else {
|
|
251
|
-
row_cells.push(String::new());
|
|
201
|
+
format_cell_value_into(&mut result, cell);
|
|
252
202
|
}
|
|
253
203
|
}
|
|
254
|
-
|
|
255
|
-
cells.push(row_cells);
|
|
204
|
+
result.push_str(" |\n");
|
|
256
205
|
}
|
|
257
206
|
|
|
258
|
-
|
|
207
|
+
result
|
|
259
208
|
}
|
|
260
209
|
|
|
261
|
-
/// Convert a Data cell to its string representation.
|
|
262
|
-
///
|
|
263
|
-
/// This helper function is shared between markdown generation and cell extraction
|
|
264
|
-
/// to ensure byte-identical output.
|
|
265
210
|
#[inline]
|
|
266
|
-
fn
|
|
211
|
+
fn format_cell_value_into(buffer: &mut String, data: &Data) {
|
|
267
212
|
match data {
|
|
268
|
-
Data::Empty =>
|
|
269
|
-
Data::String(s) =>
|
|
213
|
+
Data::Empty => {}
|
|
214
|
+
Data::String(s) => {
|
|
215
|
+
if s.contains('|') || s.contains('\\') {
|
|
216
|
+
escape_markdown_into(buffer, s);
|
|
217
|
+
} else {
|
|
218
|
+
buffer.push_str(s);
|
|
219
|
+
}
|
|
220
|
+
}
|
|
270
221
|
Data::Float(f) => {
|
|
271
222
|
if f.fract() == 0.0 {
|
|
272
|
-
|
|
223
|
+
write!(buffer, "{:.1}", f).unwrap();
|
|
273
224
|
} else {
|
|
274
|
-
|
|
225
|
+
write!(buffer, "{}", f).unwrap();
|
|
275
226
|
}
|
|
276
227
|
}
|
|
277
|
-
Data::Int(i) =>
|
|
228
|
+
Data::Int(i) => {
|
|
229
|
+
write!(buffer, "{}", i).unwrap();
|
|
230
|
+
}
|
|
278
231
|
Data::Bool(b) => {
|
|
279
|
-
if *b {
|
|
280
|
-
"true".to_string()
|
|
281
|
-
} else {
|
|
282
|
-
"false".to_string()
|
|
283
|
-
}
|
|
232
|
+
buffer.push_str(if *b { "true" } else { "false" });
|
|
284
233
|
}
|
|
285
234
|
Data::DateTime(dt) => {
|
|
286
235
|
if let Some(datetime) = dt.as_datetime() {
|
|
287
|
-
|
|
236
|
+
write!(buffer, "{}", datetime.format("%Y-%m-%d %H:%M:%S")).unwrap();
|
|
288
237
|
} else {
|
|
289
|
-
|
|
238
|
+
write!(buffer, "{:?}", dt).unwrap();
|
|
290
239
|
}
|
|
291
240
|
}
|
|
292
|
-
Data::Error(e) =>
|
|
293
|
-
|
|
294
|
-
|
|
241
|
+
Data::Error(e) => {
|
|
242
|
+
write!(buffer, "#ERR: {:?}", e).unwrap();
|
|
243
|
+
}
|
|
244
|
+
Data::DateTimeIso(s) => {
|
|
245
|
+
buffer.push_str(s);
|
|
246
|
+
}
|
|
247
|
+
Data::DurationIso(s) => {
|
|
248
|
+
buffer.push_str("DURATION: ");
|
|
249
|
+
buffer.push_str(s);
|
|
250
|
+
}
|
|
295
251
|
}
|
|
296
252
|
}
|
|
297
253
|
|
|
@@ -469,12 +425,31 @@ mod tests {
|
|
|
469
425
|
use super::*;
|
|
470
426
|
|
|
471
427
|
#[test]
|
|
472
|
-
fn
|
|
473
|
-
|
|
474
|
-
|
|
475
|
-
|
|
476
|
-
assert_eq!(
|
|
477
|
-
|
|
428
|
+
fn test_format_cell_value_into() {
|
|
429
|
+
let mut buffer = String::with_capacity(100);
|
|
430
|
+
|
|
431
|
+
format_cell_value_into(&mut buffer, &Data::Empty);
|
|
432
|
+
assert_eq!(buffer, "");
|
|
433
|
+
|
|
434
|
+
buffer.clear();
|
|
435
|
+
format_cell_value_into(&mut buffer, &Data::String("test".to_owned()));
|
|
436
|
+
assert_eq!(buffer, "test");
|
|
437
|
+
|
|
438
|
+
buffer.clear();
|
|
439
|
+
format_cell_value_into(&mut buffer, &Data::Float(42.0));
|
|
440
|
+
assert_eq!(buffer, "42.0");
|
|
441
|
+
|
|
442
|
+
buffer.clear();
|
|
443
|
+
format_cell_value_into(&mut buffer, &Data::Float(std::f64::consts::PI));
|
|
444
|
+
assert_eq!(buffer, "3.141592653589793");
|
|
445
|
+
|
|
446
|
+
buffer.clear();
|
|
447
|
+
format_cell_value_into(&mut buffer, &Data::Int(100));
|
|
448
|
+
assert_eq!(buffer, "100");
|
|
449
|
+
|
|
450
|
+
buffer.clear();
|
|
451
|
+
format_cell_value_into(&mut buffer, &Data::Bool(true));
|
|
452
|
+
assert_eq!(buffer, "true");
|
|
478
453
|
}
|
|
479
454
|
|
|
480
455
|
#[test]
|
|
@@ -495,35 +470,43 @@ mod tests {
|
|
|
495
470
|
|
|
496
471
|
#[test]
|
|
497
472
|
fn test_capacity_optimization() {
|
|
498
|
-
let buffer = String::with_capacity(100);
|
|
473
|
+
let mut buffer = String::with_capacity(100);
|
|
474
|
+
format_cell_value_into(&mut buffer, &Data::String("test".to_owned()));
|
|
475
|
+
|
|
499
476
|
assert!(buffer.capacity() >= 100);
|
|
500
477
|
}
|
|
501
478
|
|
|
502
479
|
#[test]
|
|
503
480
|
fn test_format_cell_value_datetime() {
|
|
504
481
|
use calamine::{ExcelDateTime, ExcelDateTimeType};
|
|
482
|
+
let mut buffer = String::new();
|
|
483
|
+
|
|
505
484
|
let dt = Data::DateTime(ExcelDateTime::new(49353.5, ExcelDateTimeType::DateTime, false));
|
|
506
|
-
|
|
507
|
-
assert!(!
|
|
485
|
+
format_cell_value_into(&mut buffer, &dt);
|
|
486
|
+
assert!(!buffer.is_empty());
|
|
508
487
|
}
|
|
509
488
|
|
|
510
489
|
#[test]
|
|
511
490
|
fn test_format_cell_value_error() {
|
|
512
491
|
use calamine::CellErrorType;
|
|
513
|
-
let
|
|
514
|
-
|
|
492
|
+
let mut buffer = String::new();
|
|
493
|
+
|
|
494
|
+
format_cell_value_into(&mut buffer, &Data::Error(CellErrorType::Div0));
|
|
495
|
+
assert!(buffer.contains("#ERR"));
|
|
515
496
|
}
|
|
516
497
|
|
|
517
498
|
#[test]
|
|
518
499
|
fn test_format_cell_value_datetime_iso() {
|
|
519
|
-
let
|
|
520
|
-
|
|
500
|
+
let mut buffer = String::new();
|
|
501
|
+
format_cell_value_into(&mut buffer, &Data::DateTimeIso("2024-01-01T10:30:00".to_owned()));
|
|
502
|
+
assert_eq!(buffer, "2024-01-01T10:30:00");
|
|
521
503
|
}
|
|
522
504
|
|
|
523
505
|
#[test]
|
|
524
506
|
fn test_format_cell_value_duration_iso() {
|
|
525
|
-
let
|
|
526
|
-
|
|
507
|
+
let mut buffer = String::new();
|
|
508
|
+
format_cell_value_into(&mut buffer, &Data::DurationIso("PT1H30M".to_owned()));
|
|
509
|
+
assert_eq!(buffer, "DURATION: PT1H30M");
|
|
527
510
|
}
|
|
528
511
|
|
|
529
512
|
#[test]
|
|
@@ -588,16 +571,16 @@ mod tests {
|
|
|
588
571
|
}
|
|
589
572
|
|
|
590
573
|
#[test]
|
|
591
|
-
fn
|
|
592
|
-
let range: Range<Data> = Range::
|
|
593
|
-
let
|
|
574
|
+
fn test_generate_markdown_empty_range() {
|
|
575
|
+
let range: Range<Data> = Range::new((0, 0), (0, 0));
|
|
576
|
+
let markdown = generate_markdown_from_range_optimized("Test", &range, 100);
|
|
594
577
|
|
|
595
578
|
assert!(markdown.contains("## Test"));
|
|
596
|
-
assert!(
|
|
579
|
+
assert!(markdown.contains("|"));
|
|
597
580
|
}
|
|
598
581
|
|
|
599
582
|
#[test]
|
|
600
|
-
fn
|
|
583
|
+
fn test_generate_markdown_with_headers() {
|
|
601
584
|
let mut range: Range<Data> = Range::new((0, 0), (1, 2));
|
|
602
585
|
range.set_value((0, 0), Data::String("Col1".to_owned()));
|
|
603
586
|
range.set_value((0, 1), Data::String("Col2".to_owned()));
|
|
@@ -606,16 +589,20 @@ mod tests {
|
|
|
606
589
|
range.set_value((1, 1), Data::String("B".to_owned()));
|
|
607
590
|
range.set_value((1, 2), Data::String("C".to_owned()));
|
|
608
591
|
|
|
609
|
-
let
|
|
592
|
+
let markdown = generate_markdown_from_range_optimized("Sheet1", &range, 200);
|
|
610
593
|
|
|
611
594
|
assert!(markdown.contains("## Sheet1"));
|
|
612
595
|
assert!(markdown.contains("Col1"));
|
|
596
|
+
assert!(markdown.contains("Col2"));
|
|
597
|
+
assert!(markdown.contains("Col3"));
|
|
613
598
|
assert!(markdown.contains("---"));
|
|
614
|
-
|
|
599
|
+
assert!(markdown.contains("A"));
|
|
600
|
+
assert!(markdown.contains("B"));
|
|
601
|
+
assert!(markdown.contains("C"));
|
|
615
602
|
}
|
|
616
603
|
|
|
617
604
|
#[test]
|
|
618
|
-
fn
|
|
605
|
+
fn test_generate_markdown_sparse_data() {
|
|
619
606
|
let mut range: Range<Data> = Range::new((0, 0), (2, 2));
|
|
620
607
|
range.set_value((0, 0), Data::String("A".to_owned()));
|
|
621
608
|
range.set_value((0, 1), Data::String("B".to_owned()));
|
|
@@ -623,42 +610,46 @@ mod tests {
|
|
|
623
610
|
range.set_value((1, 0), Data::String("X".to_owned()));
|
|
624
611
|
range.set_value((1, 2), Data::String("Z".to_owned()));
|
|
625
612
|
|
|
626
|
-
let
|
|
613
|
+
let markdown = generate_markdown_from_range_optimized("Sparse", &range, 200);
|
|
627
614
|
|
|
628
615
|
assert!(markdown.contains("X"));
|
|
629
616
|
assert!(markdown.contains("Z"));
|
|
630
|
-
|
|
617
|
+
let lines: Vec<&str> = markdown.lines().collect();
|
|
618
|
+
assert!(lines.iter().any(|line| line.contains("| |") || line.contains("| |")));
|
|
631
619
|
}
|
|
632
620
|
|
|
633
621
|
#[test]
|
|
634
622
|
fn test_format_cell_value_float_integer() {
|
|
635
|
-
let
|
|
636
|
-
|
|
623
|
+
let mut buffer = String::new();
|
|
624
|
+
format_cell_value_into(&mut buffer, &Data::Float(100.0));
|
|
625
|
+
assert_eq!(buffer, "100.0");
|
|
637
626
|
}
|
|
638
627
|
|
|
639
628
|
#[test]
|
|
640
629
|
fn test_format_cell_value_float_decimal() {
|
|
641
|
-
let
|
|
642
|
-
|
|
630
|
+
let mut buffer = String::new();
|
|
631
|
+
format_cell_value_into(&mut buffer, &Data::Float(12.3456));
|
|
632
|
+
assert_eq!(buffer, "12.3456");
|
|
643
633
|
}
|
|
644
634
|
|
|
645
635
|
#[test]
|
|
646
636
|
fn test_format_cell_value_bool_false() {
|
|
647
|
-
let
|
|
648
|
-
|
|
637
|
+
let mut buffer = String::new();
|
|
638
|
+
format_cell_value_into(&mut buffer, &Data::Bool(false));
|
|
639
|
+
assert_eq!(buffer, "false");
|
|
649
640
|
}
|
|
650
641
|
|
|
651
642
|
#[test]
|
|
652
|
-
fn
|
|
643
|
+
fn test_format_cell_value_string_with_pipe() {
|
|
653
644
|
let mut buffer = String::new();
|
|
654
|
-
|
|
645
|
+
format_cell_value_into(&mut buffer, &Data::String("value|with|pipes".to_owned()));
|
|
655
646
|
assert_eq!(buffer, "value\\|with\\|pipes");
|
|
656
647
|
}
|
|
657
648
|
|
|
658
649
|
#[test]
|
|
659
|
-
fn
|
|
650
|
+
fn test_format_cell_value_string_with_backslash() {
|
|
660
651
|
let mut buffer = String::new();
|
|
661
|
-
|
|
652
|
+
format_cell_value_into(&mut buffer, &Data::String("path\\to\\file".to_owned()));
|
|
662
653
|
assert_eq!(buffer, "path\\\\to\\\\file");
|
|
663
654
|
}
|
|
664
655
|
|
|
@@ -670,7 +661,7 @@ mod tests {
|
|
|
670
661
|
range.set_value((1, 0), Data::String("A".to_owned()));
|
|
671
662
|
range.set_value((1, 1), Data::String("B".to_owned()));
|
|
672
663
|
|
|
673
|
-
let
|
|
664
|
+
let markdown = generate_markdown_from_range_optimized("Test", &range, 100);
|
|
674
665
|
|
|
675
666
|
let lines: Vec<&str> = markdown.lines().collect();
|
|
676
667
|
assert!(lines[0].contains("## Test"));
|