docvortex 0.4.8__tar.gz → 0.4.9__tar.gz

{docvortex-0.4.8/src/docvortex.egg-info → docvortex-0.4.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: docvortex
-Version: 0.4.8
+Version: 0.4.9
 Summary: A fast, multi-format document parsing and conversion engine
 License-Expression: MIT
 Project-URL: Repository, https://github.com/myhloli/DocVortex
@@ -77,7 +77,7 @@ DocVortex is a standalone Python engine for parsing and converting documents.
 It reads native text and document structure into a unified representation,
 then exports the result in the formats your workflow needs.
 
-- **Multi-format input** — read text PDFs, Office files, OpenDocument files, EPUB, HTML, OFD and CSV.
+- **Multi-format input** — read text PDFs, Office files, OpenDocument files, EPUB, HTML, OFD, CSV and TSV.
 - **Parse once, export many times** — reuse the same result for Markdown, HTML, LaTeX, DOCX, EPUB, PDF and structured JSON.
 - **Portable results** — save document structure and image assets in a Bundle, then export again without the source file.
 - **Composable APIs** — use the complete pipeline or integrate analysis, postprocessing and rendering separately.
@@ -135,7 +135,7 @@ use `overwrite=True` in Python or `--overwrite` in the CLI to replace them.
 | PDF with native text | PDF |
 | Word & rich text | DOC, DOCX, RTF |
 | Presentations | PPT, PPTX |
-| Spreadsheets | XLS, XLSX, CSV |
+| Spreadsheets | XLS, XLSX, CSV, TSV |
 | OpenDocument | ODT, ODS, ODP |
 | E-books & web documents | EPUB, HTML |
 | Open Fixed-layout Document | OFD |

{docvortex-0.4.8 → docvortex-0.4.9}/README.md

@@ -23,7 +23,7 @@ DocVortex is a standalone Python engine for parsing and converting documents.
 It reads native text and document structure into a unified representation,
 then exports the result in the formats your workflow needs.
 
-- **Multi-format input** — read text PDFs, Office files, OpenDocument files, EPUB, HTML, OFD and CSV.
+- **Multi-format input** — read text PDFs, Office files, OpenDocument files, EPUB, HTML, OFD, CSV and TSV.
 - **Parse once, export many times** — reuse the same result for Markdown, HTML, LaTeX, DOCX, EPUB, PDF and structured JSON.
 - **Portable results** — save document structure and image assets in a Bundle, then export again without the source file.
 - **Composable APIs** — use the complete pipeline or integrate analysis, postprocessing and rendering separately.
@@ -81,7 +81,7 @@ use `overwrite=True` in Python or `--overwrite` in the CLI to replace them.
 | PDF with native text | PDF |
 | Word & rich text | DOC, DOCX, RTF |
 | Presentations | PPT, PPTX |
-| Spreadsheets | XLS, XLSX, CSV |
+| Spreadsheets | XLS, XLSX, CSV, TSV |
 | OpenDocument | ODT, ODS, ODP |
 | E-books & web documents | EPUB, HTML |
 | Open Fixed-layout Document | OFD |

{docvortex-0.4.8 → docvortex-0.4.9}/docs/METADATA.md

@@ -43,7 +43,7 @@ FILETIME values are UTC. Missing or invalid dates are not replaced with filesyst
 | EPUB | OPF Dublin Core and recognized meta properties | `spine` |
 | OFD | DocInfo; first nonempty scalar across DocBody entries | `physical`, summed across documents |
 | HTML | title, standard meta, Dublin Core, Open Graph, document language | `logical`, 1 |
-| CSV | no embedded descriptive property convention | `logical`, 1 |
+| CSV / TSV | no embedded descriptive property convention | `logical`, 1 |
 
 A declared count may be stale and is not a measured layout. Counts are never inferred from the
 number of pages selected for parsing. Source author strings are not authors inferred from body text.

{docvortex-0.4.8 → docvortex-0.4.9}/schemas/middle-2.0.json

@@ -762,6 +762,7 @@
             "xlsx",
             "rtf",
             "csv",
+            "tsv",
             "epub",
             "html",
             "ofd",

{docvortex-0.4.8 → docvortex-0.4.9}/schemas/model-2.0.json

@@ -15,6 +15,7 @@
             "xlsx",
             "rtf",
             "csv",
+            "tsv",
             "epub",
             "html",
             "ofd",

{docvortex-0.4.8 → docvortex-0.4.9}/src/docvortex/api.py

@@ -84,6 +84,7 @@ def analyze(
         else:
             model_types: dict[FileSuffix, type[NativeBinaryAnalyzer]] = {
                 "csv": models.CsvModel,
+                "tsv": models.CsvModel,
                 "epub": models.EpubModel,
                 "doc": models.DocModel,
                 "docx": models.DocxModel,

{docvortex-0.4.8 → docvortex-0.4.9}/src/docvortex/document/detection.py

@@ -279,13 +279,13 @@ def _has_rtf_signature_by_path(file_path: Path) -> bool:
 
 
 def _resolve_signatureless_csv_suffix(detected_suffix: str, file_path: str | Path | None) -> str:
-    """以 .csv/.tsv 扩展名兜底无签名分隔文本，并保留强内容类型的优先级。"""
+    """以 .csv/.tsv 扩展名兜底无签名分隔文本：按扩展名返回独立后缀，并保留强内容类型的优先级。"""
     extension = Path(file_path).suffix.lower().lstrip(".") if file_path else ""
     if extension in CSV_EXTENSIONS:
         if detected_suffix in _STRONG_CONTENT_SUFFIXES:
             return detected_suffix
-        return "csv"
-    if detected_suffix == "csv":
+        return extension
+    if detected_suffix in ("csv", "tsv"):
         if extension in ODF_MIMETYPE_SUFFIXES.values():
             return "txt"
         return extension or "txt"

{docvortex-0.4.8 → docvortex-0.4.9}/src/docvortex/document/filetypes.py

@@ -65,7 +65,8 @@ FILE_TYPE_BY_EXTENSION: dict[str, str] = {
     **dict.fromkeys(IMAGE_EXTENSIONS, "image"),
     **{ext: ext for ext in OFFICE_EXTENSIONS},
     **dict.fromkeys(HTML_EXTENSIONS, "html"),
-    **dict.fromkeys(CSV_EXTENSIONS, "csv"),
+    "csv": "csv",
+    "tsv": "tsv",
     **dict.fromkeys(EPUB_EXTENSIONS, "epub"),
     **dict.fromkeys(OFD_EXTENSIONS, "ofd"),
     "txt": "text",

{docvortex-0.4.8 → docvortex-0.4.9}/src/docvortex/schema.py

@@ -56,6 +56,7 @@ FileSuffix: TypeAlias = Literal[
     "xlsx",
     "rtf",
     "csv",
+    "tsv",
     "epub",
     "html",
     "ofd",

{docvortex-0.4.8 → docvortex-0.4.9}/src/docvortex/version.py

@@ -1,3 +1,3 @@
-__version__ = "0.4.8"
+__version__ = "0.4.9"
 
 __all__ = ["__version__"]

{docvortex-0.4.8 → docvortex-0.4.9/src/docvortex.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: docvortex
-Version: 0.4.8
+Version: 0.4.9
 Summary: A fast, multi-format document parsing and conversion engine
 License-Expression: MIT
 Project-URL: Repository, https://github.com/myhloli/DocVortex
@@ -77,7 +77,7 @@ DocVortex is a standalone Python engine for parsing and converting documents.
 It reads native text and document structure into a unified representation,
 then exports the result in the formats your workflow needs.
 
-- **Multi-format input** — read text PDFs, Office files, OpenDocument files, EPUB, HTML, OFD and CSV.
+- **Multi-format input** — read text PDFs, Office files, OpenDocument files, EPUB, HTML, OFD, CSV and TSV.
 - **Parse once, export many times** — reuse the same result for Markdown, HTML, LaTeX, DOCX, EPUB, PDF and structured JSON.
 - **Portable results** — save document structure and image assets in a Bundle, then export again without the source file.
 - **Composable APIs** — use the complete pipeline or integrate analysis, postprocessing and rendering separately.
@@ -135,7 +135,7 @@ use `overwrite=True` in Python or `--overwrite` in the CLI to replace them.
 | PDF with native text | PDF |
 | Word & rich text | DOC, DOCX, RTF |
 | Presentations | PPT, PPTX |
-| Spreadsheets | XLS, XLSX, CSV |
+| Spreadsheets | XLS, XLSX, CSV, TSV |
 | OpenDocument | ODT, ODS, ODP |
 | E-books & web documents | EPUB, HTML |
 | Open Fixed-layout Document | OFD |

{docvortex-0.4.8 → docvortex-0.4.9}/tests/test_format_matrix.py

@@ -1,4 +1,4 @@
-"""覆盖全部十五种原生文档输入与七种输出的独立端到端矩阵。"""
+"""覆盖全部十六种原生文档输入与七种输出的独立端到端矩阵。"""
 
 from __future__ import annotations
 
@@ -27,6 +27,8 @@ def source_payload(suffix: str) -> bytes:
         return builders[suffix]()
     if suffix == "csv":
         return b"name,value\nalpha,1\nbeta,2\n"
+    if suffix == "tsv":
+        return b"name\tvalue\nalpha\t1\nbeta\t2\n"
     if suffix == "html":
         return b"<html><h1>Title</h1><p>Native conversion</p></html>"
     if suffix == "pdf":
@@ -35,7 +37,7 @@ def source_payload(suffix: str) -> bytes:
 
 
 @pytest.mark.parametrize(
-    "suffix", ["pdf", "doc", "docx", "ppt", "pptx", "xls", "xlsx", "rtf", "csv", "html", "epub", "ofd", "odt", "ods", "odp"]
+    "suffix", ["pdf", "doc", "docx", "ppt", "pptx", "xls", "xlsx", "rtf", "csv", "tsv", "html", "epub", "ofd", "odt", "ods", "odp"]
 )
 def test_all_native_formats_render_all_targets(suffix: str, monkeypatch: pytest.MonkeyPatch) -> None:
     """每种原生格式完成分析、后处理和七种目标编码，不导入宿主。"""

{docvortex-0.4.8 → docvortex-0.4.9}/tests/unittest/test_flash_csv.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import codecs
 from io import BytesIO
+from pathlib import Path
 
 import pytest
 from _native_test_utils import analyze_native_test_document
@@ -9,6 +10,7 @@ from bs4 import BeautifulSoup
 
 from docvortex.analyzers.native import CsvModel
 from docvortex.analyzers.native import csv as csv_module
+from docvortex.document.detection import guess_suffix_by_bytes, guess_suffix_by_path
 from docvortex.render.html import render_html
 from docvortex.render.markdown import render_markdown
 from docvortex.schema import BlockType
@@ -169,3 +171,45 @@ def test_csv_default_grid_budget_rejects_wide_dom_before_rendering() -> None:
 
     with pytest.raises(ValueError, match="max_grid_slots"):
         CsvModel().predict(BytesIO(payload))
+
+
+def test_delimited_extension_resolves_to_independent_suffix() -> None:
+    """以 .csv/.tsv 路径兜底时按扩展名返回独立后缀，不再把 tsv 折叠为 csv。"""
+    payload = b"name,city\nAlice,London\n"
+
+    assert guess_suffix_by_bytes(payload, "demo.csv") == "csv"
+    assert guess_suffix_by_bytes(payload, "demo.tsv") == "tsv"
+
+
+def test_tsv_signatureless_bytes_without_path_require_explicit_suffix() -> None:
+    """无路径字节流不自动进入 tsv 解析，必须显式 file_suffix（与 csv 对称）。"""
+    payload = b"name\tcity\nAlice\tLondon\nBob\tParis\n" * 5
+
+    assert guess_suffix_by_bytes(payload) == "txt"
+
+
+def test_strong_content_signature_overrides_tsv_extension_fallback() -> None:
+    """RTF 强内容签名必须覆盖 .tsv 的无签名扩展名兜底。"""
+    payload = b"\xef\xbb\xbf \r\n{\\RTF1\\ANSI body}"
+
+    assert guess_suffix_by_bytes(payload, "disguised.tsv") == "rtf"
+
+
+def test_tsv_path_detection_returns_independent_suffix(tmp_path: Path) -> None:
+    """真实 .tsv 路径按独立后缀识别。"""
+    tsv_path = tmp_path / "demo.tsv"
+    tsv_path.write_bytes("姓名\t年龄\n张三\t30\n李四\t40\n".encode())
+
+    assert guess_suffix_by_path(tsv_path) == "tsv"
+
+
+def test_tsv_uses_shared_csv_engine_and_records_independent_file_suffix() -> None:
+    """tsv 复用 CSV 引擎与自动分隔符嗅探，并如实记录独立 file_suffix。"""
+    payload = "姓名\t年龄\n张三\t30\n李四\t40\n".encode()
+    middle, _ = analyze_native_test_document(payload, file_suffix="tsv")
+
+    assert middle.metadata.file_suffix == "tsv"
+    assert len(middle.pages) == 1
+    markdown = render_markdown(middle)
+    assert "张三" in markdown
+    assert "30" in markdown