From 92e2da4bb3e89f12a5f7cfc15e7c9aaa96ee039d Mon Sep 17 00:00:00 2001
From: Wajih-Ur-Raza Asif <152525473+wajih-rathore@users.noreply.github.com>
Date: Tue, 16 Jun 2026 22:51:03 +0500
Subject: [PATCH] fix(csv): skip leading blank lines so they don't wipe the
 whole table

A CSV whose first line is blank converted to an all-empty markdown table.
csv.reader yields [] for the blank line, so rows[0] had zero columns. That
empty row became the header, and every data row was then truncated with
row[:len(rows[0])] == row[:0], silently dropping all the data.

Skip leading empty rows before choosing the header. Adds a regression test
fixture with a leading blank first line.
---
 .../src/markitdown/converters/_csv_converter.py    |  7 +++++++
 packages/markitdown/tests/_test_vectors.py         | 14 ++++++++++++++
 .../tests/test_files/test_blank_first_line.csv     |  4 ++++
 3 files changed, 25 insertions(+)
 create mode 100644 packages/markitdown/tests/test_files/test_blank_first_line.csv

diff --git a/packages/markitdown/src/markitdown/converters/_csv_converter.py b/packages/markitdown/src/markitdown/converters/_csv_converter.py
index 7e9631e1b..3ff4d799a 100644
--- a/packages/markitdown/src/markitdown/converters/_csv_converter.py
+++ b/packages/markitdown/src/markitdown/converters/_csv_converter.py
@@ -51,6 +51,13 @@ def convert(
         reader = csv.reader(io.StringIO(content))
         rows = list(reader)
 
+        # A leading blank line (or any empty rows before the header) parses as an
+        # empty list. If that becomes the header its column count is 0, and every
+        # data row then gets truncated to nothing -- silent total data loss.
+        # Skip leading empty rows so the first real row becomes the header.
+        while rows and len(rows[0]) == 0:
+            rows.pop(0)
+
         if not rows:
             return DocumentConverterResult(markdown="")
 
diff --git a/packages/markitdown/tests/_test_vectors.py b/packages/markitdown/tests/_test_vectors.py
index 74fa9bd0a..0adeced77 100644
--- a/packages/markitdown/tests/_test_vectors.py
+++ b/packages/markitdown/tests/_test_vectors.py
@@ -152,6 +152,20 @@ class FileTestVector(object):
         ],
         must_not_include=[],
     ),
+    FileTestVector(
+        filename="test_blank_first_line.csv",
+        mimetype="text/csv",
+        charset="utf-8",
+        url=None,
+        must_include=[
+            "| name | age |",
+            "| bob | 3 |",
+            "| alice | 7 |",
+        ],
+        must_not_include=[
+            "|  |",
+        ],
+    ),
     FileTestVector(
         filename="test.json",
         mimetype="application/json",
diff --git a/packages/markitdown/tests/test_files/test_blank_first_line.csv b/packages/markitdown/tests/test_files/test_blank_first_line.csv
new file mode 100644
index 000000000..2bf2c831b
--- /dev/null
+++ b/packages/markitdown/tests/test_files/test_blank_first_line.csv
@@ -0,0 +1,4 @@
+
+name,age
+bob,3
+alice,7