Merge pull request #527 from ptth222/load-table-checks-improvement

Added better messaging
ISA-tools · Apr 12, 2024 · 8aba97f · 8aba97f
2 parents 874c7b5 + 682611d
commit 8aba97f
Showing 1 changed file with 9 additions and 35 deletions.
diff --git a/isatools/isatab/validate/rules/rules_40xx.py b/isatools/isatab/validate/rules/rules_40xx.py
@@ -472,7 +472,7 @@ def load_table_checks(df, filename):
  and not _RX_COMMENT.match(col):
  spl = ("(E) Expected only Characteristics, "
  "Factor Values or Comments following {} "
- "columns but found {} at offset {}".format(prop_name, col, x + 1, filename))
+ "columns but found {} at offset {} in file {}".format(prop_name, col, x + 1, filename))
  log.error(spl)
  error = {
  "message": "Unrecognised header",
@@ -489,7 +489,7 @@ def load_table_checks(df, filename):
  and not _RX_PARAMETER_VALUE.match(col) \
  and not _RX_COMMENT.match(col):
  spl = ("(E) Unexpected column heading following {} "
- "column. Found {} at offset {}".format(prop_name, col, x + 1, filename))
+ "column. Found {} at offset {} in file {}".format(prop_name, col, x + 1, filename))
  log.error(spl)
  error = {
  "message": "Unrecognised header",
@@ -504,26 +504,14 @@ def load_table_checks(df, filename):
  and not _RX_COMMENT.match(col):
  spl = ("(E) Expected only Characteristics, "
  "Comments following {} "
- "columns but found {} at offset {}".format(prop_name, col, x + 1, filename))
+ "columns but found {} at offset {} in file {}".format(prop_name, col, x + 1, filename))
  log.error(spl)
  error = {
  "message": "Unrecognised header",
  "supplemental": spl,
  "code": 4014
  }
  validator.add_error(**error)
- # if len(object_columns) > 1:
- #
- # spl = ("Unexpected column heading(s) following {} column. "
- # "Found {} at offset {}".format(
- # prop_name, object_columns[1:], 2), filename)
- # log.error(spl)
- # error = {
- # "message": "Unrecognised header",
- # "supplemental": spl,
- # "code": 4014
- # }
- # validator.add_error(**error)
  elif prop_name == 'Labeled Extract Name':
  if len(object_columns) > 1:
  if object_columns[1] == 'Label':
@@ -532,7 +520,7 @@ def load_table_checks(df, filename):
  'Term Accession Number']:
  spl = ("(E) Unexpected column heading "
  "following {} column. Found {} at "
- "offset {}".format(prop_name, col, x + 1, filename))
+ "offset {} in file {}".format(prop_name, col, x + 1, filename))
  log.error(spl)
  error = {
  "message": "Unrecognised header",
@@ -548,7 +536,7 @@ def load_table_checks(df, filename):
  and not _RX_COMMENT.match(col):
  spl = ("(E) Expected only Characteristics, "
  "Comments following {} "
- "columns but found {} at offset {}".format(prop_name, col, x + 1, filename))
+ "columns but found {} at offset {} in file {}".format(prop_name, col, x + 1, filename))
  log.error(spl)
  error = {
  "message": "Unrecognised header",
@@ -558,7 +546,7 @@ def load_table_checks(df, filename):
  validator.add_error(**error)
  else:
  spl = ("Expected Label column after Labeled Extract Name "
- "but none found")
+ "but none found in file {}".format(filename))
  log.error(spl)
  error = {
  "message": "Unrecognised header",
@@ -567,23 +555,10 @@ def load_table_checks(df, filename):
  }
  validator.add_error(**error)
  elif prop_name in DATA_FILE_LABELS:
- # [
- # 'Raw Data File',
- # 'Raw Spectral Data File',
- # 'Free Induction Decay Data File',
- # 'Image File',
- # 'Derived Data File',
- # 'Derived Spectral Data File',
- # 'Derived Array Data File',
- # 'Array Data File',
- # 'Protein Assignment File',
- # 'Peptide Assignment File',
- # 'Post Translational Modification Assignment File'
- # ]
  for x, col in enumerate(object_columns[1:]):
  if not _RX_COMMENT.match(col):
  spl = ("(E) Expected only Comments following {} "
- "columns but found {} at offset {}".format(prop_name, col, x + 1, filename))
+ "columns but found {} at offset {} in file {}".format(prop_name, col, x + 1, filename))
  log.error(spl)
  error = {
  "message": "Unrecognised header",
@@ -594,9 +569,8 @@ def load_table_checks(df, filename):
  elif _RX_FACTOR_VALUE.match(prop_name):
  for x, col in enumerate(object_columns[2:]):
  if col not in ['Term Source REF', 'Term Accession Number']:
- spl = (
- "(E) Unexpected column heading following {} column. "
- "Found {} at offset {}".format(prop_name, col, x + 1, filename))
+ spl = ("(E) Unexpected column heading following {} column. "
+ "Found {} at offset {} in file {}".format(prop_name, col, x + 1, filename))
  log.error(spl)
  error = {
  "message": "Unrecognised header",