feat: Add support for various CSV dialects and update documentation

Signed-off-by: Tobias Strebitzer <tobias.strebitzer@magloft.com>

docling/backend/csv_backend.py

@@ -4,13 +4,7 @@ from io import BytesIO, StringIO
 from pathlib import Path
 from typing import Set, Union
 
-from docling_core.types.doc import (
-    DoclingDocument,
-    DocumentOrigin,
-    GroupLabel,
-    TableCell,
-    TableData,
-)
+from docling_core.types.doc import DoclingDocument, DocumentOrigin, TableCell, TableData
 
 from docling.backend.abstract_backend import DeclarativeDocumentBackend
 from docling.datamodel.base_models import InputFormat
@@ -23,27 +17,21 @@ class CsvDocumentBackend(DeclarativeDocumentBackend):
     def __init__(self, in_doc: "InputDocument", path_or_stream: Union[BytesIO, Path]):
         super().__init__(in_doc, path_or_stream)
 
-        # Initialize parent for hierarchy
-        self.parent = None
-        self.valid = False
-
+        # Load content
         try:
             if isinstance(self.path_or_stream, BytesIO):
-                content = self.path_or_stream.getvalue().decode("utf-8")
-                self.csv_data = list(csv.reader(StringIO(content)))
+                self.content = self.path_or_stream.getvalue().decode("utf-8")
             elif isinstance(self.path_or_stream, Path):
-                with open(self.path_or_stream, 'r', newline='') as f:
-                    self.csv_data = list(csv.reader(f))
-            
+                with open(self.path_or_stream, "r", newline="") as f:
+                    self.content = f.read()
             self.valid = True
         except Exception as e:
-            self.valid = False
             raise RuntimeError(
                 f"CsvDocumentBackend could not load document with hash {self.document_hash}"
             ) from e
+        return
 
     def is_valid(self) -> bool:
-        _log.info(f"valid: {self.valid}")
         return self.valid
 
     @classmethod
@@ -60,6 +48,23 @@ class CsvDocumentBackend(DeclarativeDocumentBackend):
         return {InputFormat.CSV}
 
     def convert(self) -> DoclingDocument:
+        """
+        Parses the CSV data into a structured document model.
+        """
+
+        # Detect CSV dialect
+        dialect = csv.Sniffer().sniff(self.content)
+        _log.info(f'Parsing CSV with delimiter: "{dialect.delimiter}"')
+        if not dialect.delimiter in {",", ";", "\t", "|"}:
+            raise RuntimeError(
+                f"Cannot convert csv with unknown delimiter {dialect.delimiter}."
+            )
+
+        # Parce CSV
+        result = csv.reader(StringIO(self.content), dialect=dialect)
+        self.csv_data = list(result)
+        _log.info(f"Detected {len(self.csv_data)} lines")
+
         # Parse the CSV into a structured document model
         origin = DocumentOrigin(
             filename=self.file.name or "file.csv",
@@ -70,13 +75,6 @@ class CsvDocumentBackend(DeclarativeDocumentBackend):
         doc = DoclingDocument(name=self.file.stem or "file.csv", origin=origin)
 
         if self.is_valid():
-            # Create a section for the CSV content
-            self.parent = doc.add_group(
-                parent=None,
-                label=GroupLabel.SECTION,
-                name="csv content",
-            )
-
             # Convert CSV data to table
             if self.csv_data:
                 num_rows = len(self.csv_data)
@@ -104,7 +102,7 @@ class CsvDocumentBackend(DeclarativeDocumentBackend):
                         )
                         table_data.table_cells.append(cell)
 
-                doc.add_table(data=table_data, parent=self.parent)
+                doc.add_table(data=table_data)
         else:
             raise RuntimeError(
                 f"Cannot convert doc with {self.document_hash} because the backend failed to init."

docling/datamodel/document.py

@@ -1,6 +1,6 @@
+import csv
 import logging
 import re
-import csv
 from enum import Enum
 from io import BytesIO
 from pathlib import Path, PurePath
@@ -424,4 +424,4 @@ class _DocumentConversionInput(BaseModel):
         except csv.Error:
             return None
 
-        return None
+        return None

docling/document_converter.py

@@ -10,11 +10,11 @@ from pydantic import BaseModel, ConfigDict, model_validator, validate_call
 
 from docling.backend.abstract_backend import AbstractDocumentBackend
 from docling.backend.asciidoc_backend import AsciiDocBackend
+from docling.backend.csv_backend import CsvDocumentBackend
 from docling.backend.docling_parse_v2_backend import DoclingParseV2DocumentBackend
 from docling.backend.html_backend import HTMLDocumentBackend
 from docling.backend.json.docling_json_backend import DoclingJSONBackend
 from docling.backend.md_backend import MarkdownDocumentBackend
-from docling.backend.csv_backend import CsvDocumentBackend
 from docling.backend.msexcel_backend import MsExcelDocumentBackend
 from docling.backend.mspowerpoint_backend import MsPowerpointDocumentBackend
 from docling.backend.msword_backend import MsWordDocumentBackend
@@ -66,6 +66,7 @@ class CsvFormatOption(FormatOption):
     pipeline_cls: Type = SimplePipeline
     backend: Type[AbstractDocumentBackend] = CsvDocumentBackend
 
+
 class ExcelFormatOption(FormatOption):
     pipeline_cls: Type = SimplePipeline
     backend: Type[AbstractDocumentBackend] = MsExcelDocumentBackend

docs/examples/backend_csv.ipynb

@@ -0,0 +1,80 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Conversion of CSV files\n",
+    "\n",
+    "This example shows how to convert CSV files to a structured Docling Document.\n",
+    "\n",
+    "* Multiple delimiters are supported: `,` `;` `|` `[tab]`\n",
+    "* Additional CSV dialect settings are detected automatically (e.g. quotes, line separator, escape character)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Example Code"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pathlib import Path\n",
+    "\n",
+    "from docling.document_converter import DocumentConverter\n",
+    "\n",
+    "# Convert CSV to Docling document\n",
+    "converter = DocumentConverter()\n",
+    "result = converter.convert(Path(\"../../tests/data/csv/csv-comma.csv\"))\n",
+    "output = result.document.export_to_markdown()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This code generates the following output:"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "|   Index | Customer Id     | First Name   | Last Name   | Company                         | City              | Country                    | Phone 1                | Phone 2               | Email                       | Subscription Date   | Website                     |\n",
+    "|---------|-----------------|--------------|-------------|---------------------------------|-------------------|----------------------------|------------------------|-----------------------|-----------------------------|---------------------|-----------------------------|\n",
+    "|       1 | DD37Cf93aecA6Dc | Sheryl       | Baxter      | Rasmussen Group                 | East Leonard      | Chile                      | 229.077.5154           | 397.884.0519x718      | zunigavanessa@smith.info    | 2020-08-24          | http://www.stephenson.com/  |\n",
+    "|       2 | 1Ef7b82A4CAAD10 | Preston      | Lozano, Dr  | Vega-Gentry                     | East Jimmychester | Djibouti                   | 5153435776             | 686-620-1820x944      | vmata@colon.com             | 2021-04-23          | http://www.hobbs.com/       |\n",
+    "|       3 | 6F94879bDAfE5a6 | Roy          | Berry       | Murillo-Perry                   | Isabelborough     | Antigua and Barbuda        | +1-539-402-0259        | (496)978-3969x58947   | beckycarr@hogan.com         | 2020-03-25          | http://www.lawrence.com/    |\n",
+    "|       4 | 5Cef8BFA16c5e3c | Linda        | Olsen       | Dominguez, Mcmillan and Donovan | Bensonview        | Dominican Republic         | 001-808-617-6467x12895 | +1-813-324-8756       | stanleyblackwell@benson.org | 2020-06-02          | http://www.good-lyons.com/  |\n",
+    "|       5 | 053d585Ab6b3159 | Joanna       | Bender      | Martin, Lang and Andrade        | West Priscilla    | Slovakia (Slovak Republic) | 001-234-203-0635x76146 | 001-199-446-3860x3486 | colinalvarado@miles.net     | 2021-04-17          | https://goodwin-ingram.com/ |"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "docling-TtEIaPrw-py3.12",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/examples/run_csv.py

@@ -1,32 +0,0 @@
-import json
-import logging
-from pathlib import Path
-
-import yaml
-
-from docling.datamodel.base_models import InputFormat
-from docling.document_converter import DocumentConverter
-
-logging.basicConfig(level=logging.DEBUG)
-
-def main():
-    # Convert CSV to Docling document:
-    source = "https://drive.google.com/uc?id=1zO8ekHWx9U7mrbx_0Hoxxu6od7uxJqWw&export=download"
-    converter = DocumentConverter()
-    result = converter.convert(source)
-
-    # Export Docling document:
-    out_path = Path("scratch")
-    print(f"Document converted." f"\nSaving output to: {str(out_path)}")
-    with (out_path / f"customers-100.md").open("w") as fp:
-        fp.write(result.document.export_to_markdown())
-
-    with (out_path / f"customers-100.json").open("w") as fp:
-        fp.write(json.dumps(result.document.export_to_dict()))
-
-    with (out_path / f"customers-100.yaml").open("w") as fp:
-        fp.write(yaml.safe_dump(result.document.export_to_dict()))
-
-
-if __name__ == "__main__":
-    main()

mkdocs.yml

@@ -80,6 +80,7 @@ nav:
       - "RapidOCR with custom OCR models": examples/rapidocr_with_custom_models.py
       - "Accelerator options": examples/run_with_accelerator.py
       - "Simple translation": examples/translate.py
+      - examples/backend_csv.ipynb
       - examples/backend_xml_rag.ipynb
     - ✂️ Chunking:
       - examples/hybrid_chunking.ipynb

tests/data/csv/csv-comma.csv

@@ -1,6 +1,6 @@
 Index,Customer Id,First Name,Last Name,Company,City,Country,Phone 1,Phone 2,Email,Subscription Date,Website
 1,DD37Cf93aecA6Dc,Sheryl,Baxter,Rasmussen Group,East Leonard,Chile,229.077.5154,397.884.0519x718,zunigavanessa@smith.info,2020-08-24,http://www.stephenson.com/
-2,1Ef7b82A4CAAD10,Preston,Lozano,Vega-Gentry,East Jimmychester,Djibouti,5153435776,686-620-1820x944,vmata@colon.com,2021-04-23,http://www.hobbs.com/
+2,1Ef7b82A4CAAD10,Preston,"Lozano, Dr",Vega-Gentry,East Jimmychester,Djibouti,5153435776,686-620-1820x944,vmata@colon.com,2021-04-23,http://www.hobbs.com/
 3,6F94879bDAfE5a6,Roy,Berry,Murillo-Perry,Isabelborough,Antigua and Barbuda,+1-539-402-0259,(496)978-3969x58947,beckycarr@hogan.com,2020-03-25,http://www.lawrence.com/
 4,5Cef8BFA16c5e3c,Linda,Olsen,"Dominguez, Mcmillan and Donovan",Bensonview,Dominican Republic,001-808-617-6467x12895,+1-813-324-8756,stanleyblackwell@benson.org,2020-06-02,http://www.good-lyons.com/
 5,053d585Ab6b3159,Joanna,Bender,"Martin, Lang and Andrade",West Priscilla,Slovakia (Slovak Republic),001-234-203-0635x76146,001-199-446-3860x3486,colinalvarado@miles.net,2021-04-17,https://goodwin-ingram.com/

tests/data/csv/csv-pipe.csv

@@ -0,0 +1,6 @@
+Index|Customer Id|First Name|Last Name|Company|City|Country|Phone 1|Phone 2|Email|Subscription Date|Website
+1|DD37Cf93aecA6Dc|Sheryl|Baxter|Rasmussen Group|East Leonard|Chile|229.077.5154|397.884.0519x718|zunigavanessa@smith.info|2020-08-24|http://www.stephenson.com/
+2|1Ef7b82A4CAAD10|Preston|Lozano|Vega-Gentry|East Jimmychester|Djibouti|5153435776|686-620-1820x944|vmata@colon.com|2021-04-23|http://www.hobbs.com/
+3|6F94879bDAfE5a6|Roy|Berry|Murillo-Perry|Isabelborough|Antigua and Barbuda|+1-539-402-0259|(496)978-3969x58947|beckycarr@hogan.com|2020-03-25|http://www.lawrence.com/
+4|5Cef8BFA16c5e3c|Linda|Olsen|"Dominguez|Mcmillan and Donovan"|Bensonview|Dominican Republic|001-808-617-6467x12895|+1-813-324-8756|stanleyblackwell@benson.org|2020-06-02|http://www.good-lyons.com/
+5|053d585Ab6b3159|Joanna|Bender|"Martin|Lang and Andrade"|West Priscilla|Slovakia (Slovak Republic)|001-234-203-0635x76146|001-199-446-3860x3486|colinalvarado@miles.net|2021-04-17|https://goodwin-ingram.com/

tests/data/csv/csv-semicolon.csv

@@ -0,0 +1,6 @@
+Index;Customer Id;First Name;Last Name;Company;City;Country;Phone 1;Phone 2;Email;Subscription Date;Website
+1;DD37Cf93aecA6Dc;Sheryl;Baxter;Rasmussen Group;East Leonard;Chile;229.077.5154;397.884.0519x718;zunigavanessa@smith.info;2020-08-24;http://www.stephenson.com/
+2;1Ef7b82A4CAAD10;Preston;Lozano;Vega-Gentry;East Jimmychester;Djibouti;5153435776;686-620-1820x944;vmata@colon.com;2021-04-23;http://www.hobbs.com/
+3;6F94879bDAfE5a6;Roy;Berry;Murillo-Perry;Isabelborough;Antigua and Barbuda;+1-539-402-0259;(496)978-3969x58947;beckycarr@hogan.com;2020-03-25;http://www.lawrence.com/
+4;5Cef8BFA16c5e3c;Linda;Olsen;"Dominguez;Mcmillan and Donovan";Bensonview;Dominican Republic;001-808-617-6467x12895;+1-813-324-8756;stanleyblackwell@benson.org;2020-06-02;http://www.good-lyons.com/
+5;053d585Ab6b3159;Joanna;Bender;"Martin;Lang and Andrade";West Priscilla;Slovakia (Slovak Republic);001-234-203-0635x76146;001-199-446-3860x3486;colinalvarado@miles.net;2021-04-17;https://goodwin-ingram.com/

tests/data/csv/csv-tab.csv

@@ -0,0 +1,6 @@
+Index	Customer Id	First Name	Last Name	Company	City	Country	Phone 1	Phone 2	Email	Subscription Date	Website
+1	DD37Cf93aecA6Dc	Sheryl	Baxter	Rasmussen Group	East Leonard	Chile	229.077.5154	397.884.0519x718	zunigavanessa@smith.info	2020-08-24	http://www.stephenson.com/
+2	1Ef7b82A4CAAD10	Preston	Lozano	Vega-Gentry	East Jimmychester	Djibouti	5153435776	686-620-1820x944	vmata@colon.com	2021-04-23	http://www.hobbs.com/
+3	6F94879bDAfE5a6	Roy	Berry	Murillo-Perry	Isabelborough	Antigua and Barbuda	+1-539-402-0259	(496)978-3969x58947	beckycarr@hogan.com	2020-03-25	http://www.lawrence.com/
+4	5Cef8BFA16c5e3c	Linda	Olsen	"Dominguez	Mcmillan and Donovan"	Bensonview	Dominican Republic	001-808-617-6467x12895	+1-813-324-8756	stanleyblackwell@benson.org	2020-06-02	http://www.good-lyons.com/
+5	053d585Ab6b3159	Joanna	Bender	"Martin	Lang and Andrade"	West Priscilla	Slovakia (Slovak Republic)	001-234-203-0635x76146	001-199-446-3860x3486	colinalvarado@miles.net	2021-04-17	https://goodwin-ingram.com/

tests/data/groundtruth/docling_v2/csv-comma.csv.itxt

@@ -0,0 +1,2 @@
+item-0 at level 0: unspecified: group _root_
+  item-1 at level 1: table with [6x12]

tests/data/groundtruth/docling_v2/csv-comma.csv.json

@@ -1,11 +1,11 @@
 {
   "schema_name": "DoclingDocument",
   "version": "1.1.0",
-  "name": "test-01",
+  "name": "csv-comma",
   "origin": {
     "mimetype": "text/csv",
-    "binary_hash": 7076108075619672109,
-    "filename": "test-01.csv"
+    "binary_hash": 297933764223584292,
+    "filename": "csv-comma.csv"
   },
   "furniture": {
     "self_ref": "#/furniture",
@@ -18,36 +18,21 @@
     "self_ref": "#/body",
     "children": [
       {
-        "$ref": "#/groups/0"
+        "$ref": "#/tables/0"
       }
     ],
     "content_layer": "body",
     "name": "_root_",
     "label": "unspecified"
   },
-  "groups": [
-    {
-      "self_ref": "#/groups/0",
-      "parent": {
-        "$ref": "#/body"
-      },
-      "children": [
-        {
-          "$ref": "#/tables/0"
-        }
-      ],
-      "content_layer": "body",
-      "name": "csv content",
-      "label": "section"
-    }
-  ],
+  "groups": [],
   "texts": [],
   "pictures": [],
   "tables": [
     {
       "self_ref": "#/tables/0",
       "parent": {
-        "$ref": "#/groups/0"
+        "$ref": "#/body"
       },
       "children": [],
       "content_layer": "body",
@@ -389,7 +374,7 @@
             "end_row_offset_idx": 3,
             "start_col_offset_idx": 3,
             "end_col_offset_idx": 4,
-            "text": "Lozano",
+            "text": "Lozano, Dr",
             "column_header": false,
             "row_header": false,
             "row_section": false
@@ -1262,7 +1247,7 @@
               "end_row_offset_idx": 3,
               "start_col_offset_idx": 3,
               "end_col_offset_idx": 4,
-              "text": "Lozano",
+              "text": "Lozano, Dr",
               "column_header": false,
               "row_header": false,
               "row_section": false

tests/data/groundtruth/docling_v2/csv-comma.csv.md

@@ -1,7 +1,7 @@
 |   Index | Customer Id     | First Name   | Last Name   | Company                         | City              | Country                    | Phone 1                | Phone 2               | Email                       | Subscription Date   | Website                     |
 |---------|-----------------|--------------|-------------|---------------------------------|-------------------|----------------------------|------------------------|-----------------------|-----------------------------|---------------------|-----------------------------|
 |       1 | DD37Cf93aecA6Dc | Sheryl       | Baxter      | Rasmussen Group                 | East Leonard      | Chile                      | 229.077.5154           | 397.884.0519x718      | zunigavanessa@smith.info    | 2020-08-24          | http://www.stephenson.com/  |
-|       2 | 1Ef7b82A4CAAD10 | Preston      | Lozano      | Vega-Gentry                     | East Jimmychester | Djibouti                   | 5153435776             | 686-620-1820x944      | vmata@colon.com             | 2021-04-23          | http://www.hobbs.com/       |
+|       2 | 1Ef7b82A4CAAD10 | Preston      | Lozano, Dr  | Vega-Gentry                     | East Jimmychester | Djibouti                   | 5153435776             | 686-620-1820x944      | vmata@colon.com             | 2021-04-23          | http://www.hobbs.com/       |
 |       3 | 6F94879bDAfE5a6 | Roy          | Berry       | Murillo-Perry                   | Isabelborough     | Antigua and Barbuda        | +1-539-402-0259        | (496)978-3969x58947   | beckycarr@hogan.com         | 2020-03-25          | http://www.lawrence.com/    |
 |       4 | 5Cef8BFA16c5e3c | Linda        | Olsen       | Dominguez, Mcmillan and Donovan | Bensonview        | Dominican Republic         | 001-808-617-6467x12895 | +1-813-324-8756       | stanleyblackwell@benson.org | 2020-06-02          | http://www.good-lyons.com/  |
 |       5 | 053d585Ab6b3159 | Joanna       | Bender      | Martin, Lang and Andrade        | West Priscilla    | Slovakia (Slovak Republic) | 001-234-203-0635x76146 | 001-199-446-3860x3486 | colinalvarado@miles.net     | 2021-04-17          | https://goodwin-ingram.com/ |

tests/data/groundtruth/docling_v2/csv-pipe.csv.itxt

@@ -0,0 +1,2 @@
+item-0 at level 0: unspecified: group _root_
+  item-1 at level 1: table with [6x12]

tests/data/groundtruth/docling_v2/csv-pipe.csv.md

@@ -0,0 +1,7 @@
+|   Index | Customer Id     | First Name   | Last Name   | Company                        | City              | Country                    | Phone 1                | Phone 2               | Email                       | Subscription Date   | Website                     |
+|---------|-----------------|--------------|-------------|--------------------------------|-------------------|----------------------------|------------------------|-----------------------|-----------------------------|---------------------|-----------------------------|
+|       1 | DD37Cf93aecA6Dc | Sheryl       | Baxter      | Rasmussen Group                | East Leonard      | Chile                      | 229.077.5154           | 397.884.0519x718      | zunigavanessa@smith.info    | 2020-08-24          | http://www.stephenson.com/  |
+|       2 | 1Ef7b82A4CAAD10 | Preston      | Lozano      | Vega-Gentry                    | East Jimmychester | Djibouti                   | 5153435776             | 686-620-1820x944      | vmata@colon.com             | 2021-04-23          | http://www.hobbs.com/       |
+|       3 | 6F94879bDAfE5a6 | Roy          | Berry       | Murillo-Perry                  | Isabelborough     | Antigua and Barbuda        | +1-539-402-0259        | (496)978-3969x58947   | beckycarr@hogan.com         | 2020-03-25          | http://www.lawrence.com/    |
+|       4 | 5Cef8BFA16c5e3c | Linda        | Olsen       | Dominguez|Mcmillan and Donovan | Bensonview        | Dominican Republic         | 001-808-617-6467x12895 | +1-813-324-8756       | stanleyblackwell@benson.org | 2020-06-02          | http://www.good-lyons.com/  |
+|       5 | 053d585Ab6b3159 | Joanna       | Bender      | Martin|Lang and Andrade        | West Priscilla    | Slovakia (Slovak Republic) | 001-234-203-0635x76146 | 001-199-446-3860x3486 | colinalvarado@miles.net     | 2021-04-17          | https://goodwin-ingram.com/ |

tests/data/groundtruth/docling_v2/csv-semicolon.csv.itxt

@@ -0,0 +1,2 @@
+item-0 at level 0: unspecified: group _root_
+  item-1 at level 1: table with [6x12]

tests/data/groundtruth/docling_v2/csv-semicolon.csv.md

@@ -0,0 +1,7 @@
+|   Index | Customer Id     | First Name   | Last Name   | Company                        | City              | Country                    | Phone 1                | Phone 2               | Email                       | Subscription Date   | Website                     |
+|---------|-----------------|--------------|-------------|--------------------------------|-------------------|----------------------------|------------------------|-----------------------|-----------------------------|---------------------|-----------------------------|
+|       1 | DD37Cf93aecA6Dc | Sheryl       | Baxter      | Rasmussen Group                | East Leonard      | Chile                      | 229.077.5154           | 397.884.0519x718      | zunigavanessa@smith.info    | 2020-08-24          | http://www.stephenson.com/  |
+|       2 | 1Ef7b82A4CAAD10 | Preston      | Lozano      | Vega-Gentry                    | East Jimmychester | Djibouti                   | 5153435776             | 686-620-1820x944      | vmata@colon.com             | 2021-04-23          | http://www.hobbs.com/       |
+|       3 | 6F94879bDAfE5a6 | Roy          | Berry       | Murillo-Perry                  | Isabelborough     | Antigua and Barbuda        | +1-539-402-0259        | (496)978-3969x58947   | beckycarr@hogan.com         | 2020-03-25          | http://www.lawrence.com/    |
+|       4 | 5Cef8BFA16c5e3c | Linda        | Olsen       | Dominguez;Mcmillan and Donovan | Bensonview        | Dominican Republic         | 001-808-617-6467x12895 | +1-813-324-8756       | stanleyblackwell@benson.org | 2020-06-02          | http://www.good-lyons.com/  |
+|       5 | 053d585Ab6b3159 | Joanna       | Bender      | Martin;Lang and Andrade        | West Priscilla    | Slovakia (Slovak Republic) | 001-234-203-0635x76146 | 001-199-446-3860x3486 | colinalvarado@miles.net     | 2021-04-17          | https://goodwin-ingram.com/ |

tests/data/groundtruth/docling_v2/csv-tab.csv.itxt

@@ -0,0 +1,2 @@
+item-0 at level 0: unspecified: group _root_
+  item-1 at level 1: table with [6x12]

tests/data/groundtruth/docling_v2/csv-tab.csv.md

@@ -0,0 +1,7 @@
+|   Index | Customer Id     | First Name   | Last Name   | Company         | City              | Country                    | Phone 1                | Phone 2               | Email                       | Subscription Date   | Website                     |
+|---------|-----------------|--------------|-------------|-----------------|-------------------|----------------------------|------------------------|-----------------------|-----------------------------|---------------------|-----------------------------|
+|       1 | DD37Cf93aecA6Dc | Sheryl       | Baxter      | Rasmussen Group | East Leonard      | Chile                      | 229.077.5154           | 397.884.0519x718      | zunigavanessa@smith.info    | 2020-08-24          | http://www.stephenson.com/  |
+|       2 | 1Ef7b82A4CAAD10 | Preston      | Lozano      | Vega-Gentry     | East Jimmychester | Djibouti                   | 5153435776             | 686-620-1820x944      | vmata@colon.com             | 2021-04-23          | http://www.hobbs.com/       |
+|       3 | 6F94879bDAfE5a6 | Roy          | Berry       | Murillo-Perry   | Isabelborough     | Antigua and Barbuda        | +1-539-402-0259        | (496)978-3969x58947   | beckycarr@hogan.com         | 2020-03-25          | http://www.lawrence.com/    |
+|       4 | 5Cef8BFA16c5e3c | Linda        | Olsen       | Dominguez	Mcmillan and Donovan                 | Bensonview        | Dominican Republic         | 001-808-617-6467x12895 | +1-813-324-8756       | stanleyblackwell@benson.org | 2020-06-02          | http://www.good-lyons.com/  |
+|       5 | 053d585Ab6b3159 | Joanna       | Bender      | Martin	Lang and Andrade                 | West Priscilla    | Slovakia (Slovak Republic) | 001-234-203-0635x76146 | 001-199-446-3860x3486 | colinalvarado@miles.net     | 2021-04-17          | https://goodwin-ingram.com/ |

tests/data/groundtruth/docling_v2/test-01.csv.itxt

@@ -1,3 +0,0 @@
-item-0 at level 0: unspecified: group _root_
-  item-1 at level 1: section: group csv content
-    item-2 at level 2: table with [6x12]

tests/test_backend_csv.py

@@ -50,9 +50,7 @@ def test_e2e_csv_conversions():
     for csv_path in csv_paths:
         print(f"converting {csv_path}")
 
-        gt_path = (
-            csv_path.parent.parent / "groundtruth" / "docling_v2" / csv_path.name
-        )
+        gt_path = csv_path.parent.parent / "groundtruth" / "docling_v2" / csv_path.name
 
         conv_result: ConversionResult = converter.convert(csv_path)