From ce243a57b24d6adecb169487e706290d91b22d19 Mon Sep 17 00:00:00 2001
From: Frederick Muriuki Muriithi
Date: Tue, 20 Feb 2024 10:57:56 +0300
Subject: Track filename in the errors

R/qtl2 bundles can contain more than one file, of the same type. When
errors are encountered in any of the files, we need to be able to
inform the user which file it is, in addition to the line and column
number.
---
 quality_control/headers.py | 24 ++++++++++++++----------
 1 file changed, 14 insertions(+), 10 deletions(-)

(limited to 'quality_control/headers.py')

diff --git a/quality_control/headers.py b/quality_control/headers.py
index f4f4dad..436ea5a 100644
--- a/quality_control/headers.py
+++ b/quality_control/headers.py
@@ -5,30 +5,34 @@ from typing import Union, Tuple, Sequence
 
 from quality_control.errors import InvalidValue, DuplicateHeading
 
-def invalid_header(
-        line_number: int, headers: Sequence[str]) -> Union[InvalidValue, None]:
+def invalid_header(filename: str,
+                   line_number: int,
+                   headers: Sequence[str]) -> Union[InvalidValue, None]:
     """Return an `InvalidValue` object if the header row has less than 2
     items."""
     if len(headers) < 2:
         return InvalidValue(
-            line_number, 0, "<TAB>".join(headers),
+            filename, line_number, 0, "<TAB>".join(headers),
             "The header MUST contain at least 2 columns")
     return None
 
 def invalid_headings(
-        line_number: int, strains: Sequence[str],
+        filename: str, line_number: int, strains: Sequence[str],
         headings: Sequence[str]) -> Union[Tuple[InvalidValue, ...], None]:
     """Return tuple of `InvalidValue` objects for each error found for every
     column heading."""
     return tuple(
-        InvalidValue(
-            line_number, col, header, f"'{header}' not a valid strain.")
+        InvalidValue(filename,
+                     line_number,
+                     col,
+                     header,
+                     f"'{header}' not a valid strain.")
         for col, header in
         enumerate(headings, start=2) if header not in strains)
 
-def duplicate_headings(
-        line_number: int,
-        headers: Sequence[str]) -> Tuple[DuplicateHeading, ...]:
+def duplicate_headings(filename: str,
+                       line_number: int,
+                       headers: Sequence[str]) -> Tuple[DuplicateHeading, ...]:
     """Return a tuple of `DuplicateHeading` objects for each column heading that
     is a duplicate of another column heading."""
     def __update_columns__(acc, item):
@@ -42,7 +46,7 @@ def duplicate_headings(
     }
     return tuple(
         DuplicateHeading(
-            line_number, columns, heading, (
+            filename, line_number, columns, heading, (
                 f"Heading '{heading}', is repeated in columns "
                 f"{','.join(str(i) for i in columns)}"))
         for heading, columns in repeated.items())
-- 
cgit v1.2.3