747: update identifier validation message now that leading colons aren't allowed

pyxform/errors.py

@@ -41,6 +41,113 @@ def format(self, **kwargs):
 
 
 class ErrorCode(Enum):
+    HEADER_001: Detail = Detail(
+        name="Invalid missing header row.",
+        msg=(
+            "Invalid headers provided for sheet: '{sheet_name}'. For XLSForms, this may be due "
+            "a missing header row, in which case add a header row as per the reference template "
+            "https://xlsform.org/en/ref-table/. For internal API usage, may be due to a missing "
+            "mapping for '{header}', in which case ensure that the full set of headers appear "
+            "within the first 100 rows, or specify the header row in '{sheet_name}_header'."
+        ),
+    )
+    HEADER_002: Detail = Detail(
+        name="Invalid duplicate header.",
+        msg=(
+            "Invalid headers provided for sheet: '{sheet_name}'. Headers that are different "
+            "names for the same column were found: '{other}', '{header}'. Rename or remove one "
+            "of these columns."
+        ),
+    )
+    HEADER_003: Detail = Detail(
+        name="Invalid missing required header.",
+        msg=(
+            "Invalid headers provided for sheet: '{sheet_name}'. One or more required column "
+            "headers were not found: {missing}. "
+            "Learn more: https://xlsform.org/en/#setting-up-your-worksheets"
+        ),
+    )
+    HEADER_004: Detail = Detail(
+        name="Invalid choices header.",
+        msg=(
+            "[row : 1] On the 'choices' sheet, the '{column}' value is invalid. "
+            "Column headers must not be empty and must not contain spaces. "
+            "Learn more: https://xlsform.org/en/#setting-up-your-worksheets"
+        ),
+    )
+    INTERNAL_001: Detail = Detail(
+        name="Internal error: Incorrectly Processed Question Trigger Data",
+        msg=(
+            "Internal error: "
+            "PyXForm expected processed trigger data as a tuple, but received a "
+            "type '{type}' with value '{value}'."
+        ),
+    )
+    LABEL_001: Detail = Detail(
+        name="Invalid missing label in the choices sheet",
+        msg=(
+            "[row : {row}] On the 'choices' sheet, the 'label' value is invalid. "
+            "Choices should have a label. "
+            "Learn more: https://xlsform.org/en/#setting-up-your-worksheets"
+        ),
+    )
+    NAMES_001: Detail = Detail(
+        name="Invalid duplicate name in same context",
+        msg=(
+            "[row : {row}] On the 'survey' sheet, the 'name' value '{value}' is invalid. "
+            "Questions, groups, and repeats must be unique within their nearest parent group "
+            "or repeat, or the survey if not inside a group or repeat."
+        ),
+    )
+    NAMES_002: Detail = Detail(
+        name="Invalid duplicate name in context (case-insensitive)",
+        msg=(
+            "[row : {row}] On the 'survey' sheet, the 'name' value '{value}' is problematic. "
+            "The name is a case-insensitive match to another name. Questions, groups, and "
+            "repeats should be unique within the nearest parent group or repeat, or the survey "
+            "if not inside a group or repeat. Some data processing tools are not "
+            "case-sensitive, so the current names may make analysis difficult."
+        ),
+    )
+    NAMES_003: Detail = Detail(
+        name="Invalid repeat name same as survey",
+        msg=(
+            "[row : {row}] On the 'survey' sheet, the 'name' value '{value}' is invalid. "
+            "Repeat names must not be the same as the survey root (which defaults to 'data')."
+        ),
+    )
+    NAMES_004: Detail = Detail(
+        name="Invalid duplicate repeat name in the survey",
+        msg=(
+            "[row : {row}] On the 'survey' sheet, the 'name' value '{value}' is invalid. "
+            "Repeat names must unique anywhere in the survey, at all levels of group or "
+            "repeat nesting."
+        ),
+    )
+    NAMES_005: Detail = Detail(
+        name="Invalid duplicate meta name in the survey",
+        msg=(
+            "[row : {row}] On the 'survey' sheet, the 'name' value 'meta' is invalid. "
+            "The name 'meta' is reserved for form metadata."
+        ),
+    )
+    NAMES_006: Detail = Detail(
+        name="Invalid missing name in the choices sheet",
+        msg=(
+            "[row : {row}] On the 'choices' sheet, the 'name' value is invalid. "
+            "Choices must have a name. "
+            "Learn more: https://xlsform.org/en/#setting-up-your-worksheets"
+        ),
+    )
+    NAMES_007: Detail = Detail(
+        name="Invalid duplicate name in the choices sheet",
+        msg=(
+            "[row : {row}] On the 'choices' sheet, the 'name' value is invalid. "
+            "Choice names must be unique for each choice list. "
+            "If this is intentional, use the setting 'allow_choice_duplicates'. "
+            "Learn more: https://xlsform.org/#choice-names."
+        ),
+    )
     PYREF_001: Detail = Detail(
         name="PyXForm Reference Parsing Failed",
         msg=(
@@ -71,12 +178,18 @@ class ErrorCode(Enum):
             "'{q}' appears more than once."
         ),
     )
-    INTERNAL_001: Detail = Detail(
-        name="Internal error: Incorrectly Processed Question Trigger Data",
+    SURVEY_001 = Detail(
+        name="Survey Sheet Unmatched Group/Repeat/Loop End",
         msg=(
-            "Internal error: "
-            "PyXForm expected processed trigger data as a tuple, but received a "
-            "type '{type}' with value '{value}'."
+            "[row : {row}] Unmatched 'end_{type}'. "
+            "No matching 'begin_{type}' was found for the name '{name}'."
+        ),
+    )
+    SURVEY_002 = Detail(
+        name="Survey Sheet Unmatched Group/Repeat/Loop Begin",
+        msg=(
+            "[row : {row}] Unmatched 'begin_{type}'. "
+            "No matching 'end_{type}' was found for the name '{name}'."
         ),
     )
     SURVEY_003: Detail = Detail(

pyxform/parsing/sheet_headers.py

@@ -4,29 +4,12 @@
 from typing import Any
 
 from pyxform import constants
-from pyxform.errors import PyXFormError
+from pyxform.errors import ErrorCode, PyXFormError
 from pyxform.parsing.expression import maybe_strip
 from pyxform.xls2json_backends import RE_WHITESPACE
 
 SMART_QUOTES = {"\u2018": "'", "\u2019": "'", "\u201c": '"', "\u201d": '"'}
 RE_SMART_QUOTES = re.compile(r"|".join(re.escape(old) for old in SMART_QUOTES))
-INVALID_HEADER = (
-    "Invalid headers provided for sheet: '{sheet_name}'. For XLSForms, this may be due "
-    "a missing header row, in which case add a header row as per the reference template "
-    "https://xlsform.org/en/ref-table/. For internal API usage, may be due to a missing "
-    "mapping for '{header}', in which case ensure that the full set of headers appear "
-    "within the first 100 rows, or specify the header row in '{sheet_name}_header'."
-)
-INVALID_DUPLICATE = (
-    "Invalid headers provided for sheet: '{sheet_name}'. Headers that are different "
-    "names for the same column were found: '{other}', '{header}'. Rename or remove one "
-    "of these columns."
-)
-INVALID_MISSING_REQUIRED = (
-    "Invalid headers provided for sheet: '{sheet_name}'. One or more required column "
-    "headers were not found: {missing}. "
-    "Learn more: https://xlsform.org/en/#setting-up-your-worksheets"
-)
 
 
 def clean_text_values(
@@ -196,7 +179,7 @@ def process_row(
         tokens = header_key.get(header, None)
         if not tokens:
             raise PyXFormError(
-                INVALID_HEADER.format(sheet_name=sheet_name, header=header)
+                ErrorCode.HEADER_001.value.format(sheet_name=sheet_name, header=header)
             )
         elif len(tokens) == 1:
             out_row[tokens[0]] = val
@@ -268,7 +251,7 @@ def dealias_and_group_headers(
                 other_header = tokens_key.get(tokens)
                 if other_header and new_header != header:
                     raise PyXFormError(
-                        INVALID_DUPLICATE.format(
+                        ErrorCode.HEADER_002.value.format(
                             sheet_name=sheet_name,
                             other=other_header,
                             header=header,
@@ -293,7 +276,7 @@ def dealias_and_group_headers(
         missing = {h for h in headers_required if h not in {h[0] for h in tokens_key}}
         if missing:
             raise PyXFormError(
-                INVALID_MISSING_REQUIRED.format(
+                ErrorCode.HEADER_003.value.format(
                     sheet_name=sheet_name, missing=", ".join(f"'{h}'" for h in missing)
                 )
             )

pyxform/validators/pyxform/choices.py

@@ -1,27 +1,5 @@
 from pyxform import constants
-from pyxform.errors import PyXFormError
-
-INVALID_NAME = (
-    "[row : {row}] On the 'choices' sheet, the 'name' value is invalid. "
-    "Choices must have a name. "
-    "Learn more: https://xlsform.org/en/#setting-up-your-worksheets"
-)
-INVALID_LABEL = (
-    "[row : {row}] On the 'choices' sheet, the 'label' value is invalid. "
-    "Choices should have a label. "
-    "Learn more: https://xlsform.org/en/#setting-up-your-worksheets"
-)
-INVALID_HEADER = (
-    "[row : 1] On the 'choices' sheet, the '{column}' value is invalid. "
-    "Column headers must not be empty and must not contain spaces. "
-    "Learn more: https://xlsform.org/en/#setting-up-your-worksheets"
-)
-INVALID_DUPLICATE = (
-    "[row : {row}] On the 'choices' sheet, the 'name' value is invalid. "
-    "Choice names must be unique for each choice list. "
-    "If this is intentional, use the setting 'allow_choice_duplicates'. "
-    "Learn more: https://xlsform.org/#choice-names."
-)
+from pyxform.errors import ErrorCode, PyXFormError
 
 
 def validate_headers(
@@ -31,7 +9,7 @@ def check():
         for header in headers:
             header = header[0]
             if header != constants.LIST_NAME_S and (" " in header or header == ""):
-                warnings.append(INVALID_HEADER.format(column=header))
+                warnings.append(ErrorCode.HEADER_004.value.format(column=header))
                 yield header
 
     return tuple(check())
@@ -44,14 +22,16 @@ def validate_choice_list(
     duplicate_errors = []
     for option in options:
         if constants.NAME not in option:
-            raise PyXFormError(INVALID_NAME.format(row=option["__row"]))
+            raise PyXFormError(ErrorCode.NAMES_006.value.format(row=option["__row"]))
         elif constants.LABEL not in option:
-            warnings.append(INVALID_LABEL.format(row=option["__row"]))
+            warnings.append(ErrorCode.LABEL_001.value.format(row=option["__row"]))
 
         if not allow_duplicates:
             name = option[constants.NAME]
             if name in seen_options:
-                duplicate_errors.append(INVALID_DUPLICATE.format(row=option["__row"]))
+                duplicate_errors.append(
+                    ErrorCode.NAMES_007.value.format(row=option["__row"])
+                )
             else:
                 seen_options.add(name)
 

pyxform/validators/pyxform/unique_names.py

@@ -1,46 +1,5 @@
 from pyxform import constants as const
-from pyxform.errors import Detail, PyXFormError
-
-NAMES001 = Detail(
-    name="Invalid duplicate name in same context",
-    msg=(
-        "[row : {row}] On the 'survey' sheet, the 'name' value '{value}' is invalid. "
-        "Questions, groups, and repeats must be unique within their nearest parent group "
-        "or repeat, or the survey if not inside a group or repeat."
-    ),
-)
-NAMES002 = Detail(
-    name="Invalid duplicate name in context (case-insensitive)",
-    msg=(
-        "[row : {row}] On the 'survey' sheet, the 'name' value '{value}' is problematic. "
-        "The name is a case-insensitive match to another name. Questions, groups, and "
-        "repeats should be unique within the nearest parent group or repeat, or the survey "
-        "if not inside a group or repeat. Some data processing tools are not "
-        "case-sensitive, so the current names may make analysis difficult."
-    ),
-)
-NAMES003 = Detail(
-    name="Invalid repeat name same as survey",
-    msg=(
-        "[row : {row}] On the 'survey' sheet, the 'name' value '{value}' is invalid. "
-        "Repeat names must not be the same as the survey root (which defaults to 'data')."
-    ),
-)
-NAMES004 = Detail(
-    name="Invalid duplicate repeat name in the survey",
-    msg=(
-        "[row : {row}] On the 'survey' sheet, the 'name' value '{value}' is invalid. "
-        "Repeat names must unique anywhere in the survey, at all levels of group or "
-        "repeat nesting."
-    ),
-)
-NAMES005 = Detail(
-    name="Invalid duplicate meta name in the survey",
-    msg=(
-        "[row : {row}] On the 'survey' sheet, the 'name' value 'meta' is invalid. "
-        "The name 'meta' is reserved for form metadata."
-    ),
-)
+from pyxform.errors import ErrorCode, PyXFormError
 
 
 def validate_question_group_repeat_name(
@@ -73,15 +32,17 @@ def validate_question_group_repeat_name(
 
     if name in seen_names:
         if name == const.META:
-            raise PyXFormError(NAMES005.format(row=row_number))
+            raise PyXFormError(ErrorCode.NAMES_005.value.format(row=row_number))
         else:
-            raise PyXFormError(NAMES001.format(row=row_number, value=name))
+            raise PyXFormError(
+                ErrorCode.NAMES_001.value.format(row=row_number, value=name)
+            )
     seen_names.add(name)
 
     question_name_lower = name.lower()
     if question_name_lower in seen_names_lower:
         # No case-insensitive warning for 'meta' since it's not an exported data table.
-        warnings.append(NAMES002.format(row=row_number, value=name))
+        warnings.append(ErrorCode.NAMES_002.value.format(row=row_number, value=name))
     seen_names_lower.add(question_name_lower)
 
 
@@ -107,7 +68,11 @@ def validate_repeat_name(
     """
     if control_type == const.REPEAT:
         if name == instance_element_name:
-            raise PyXFormError(NAMES003.format(row=row_number, value=name))
+            raise PyXFormError(
+                ErrorCode.NAMES_003.value.format(row=row_number, value=name)
+            )
         elif name in seen_names:
-            raise PyXFormError(NAMES004.format(row=row_number, value=name))
+            raise PyXFormError(
+                ErrorCode.NAMES_004.value.format(row=row_number, value=name)
+            )
         seen_names.add(name)

pyxform/xls2json.py

@@ -21,7 +21,7 @@
     validate_entity_repeat_target,
     validate_entity_saveto,
 )
-from pyxform.errors import Detail, PyXFormError
+from pyxform.errors import ErrorCode, PyXFormError
 from pyxform.parsing.expression import is_xml_tag
 from pyxform.parsing.sheet_headers import dealias_and_group_headers
 from pyxform.question_type_dictionary import get_meta_group
@@ -60,20 +60,6 @@
 RE_OSM = re.compile(
     r"(?P<osm_command>(" + "|".join(aliases.osm) + r")) (?P<list_name>\S+)"
 )
-SURVEY_001 = Detail(
-    name="Survey Sheet Unmatched Group/Repeat/Loop End",
-    msg=(
-        "[row : {row}] Unmatched 'end_{type}'. "
-        "No matching 'begin_{type}' was found for the name '{name}'."
-    ),
-)
-SURVEY_002 = Detail(
-    name="Survey Sheet Unmatched Group/Repeat/Loop Begin",
-    msg=(
-        "[row : {row}] Unmatched 'begin_{type}'. "
-        "No matching 'end_{type}' was found for the name '{name}'."
-    ),
-)
 
 
 def dealias_types(dict_array):
@@ -769,7 +755,7 @@ def workbook_to_json(
                 control_type = aliases.control[parse_dict["type"]]
                 if prev_control_type != control_type or len(stack) == 1:
                     raise PyXFormError(
-                        SURVEY_001.format(
+                        ErrorCode.SURVEY_001.value.format(
                             row=row_number,
                             type=control_type,
                             name=row.get(constants.NAME),
@@ -1410,7 +1396,7 @@ def workbook_to_json(
 
     if len(stack) > 1:
         raise PyXFormError(
-            SURVEY_002.format(
+            ErrorCode.SURVEY_002.value.format(
                 row=stack[-1]["row_number"],
                 type=stack[-1]["control_type"],
                 name=stack[-1]["control_name"],