From b36999500195bd9fdfc3c8c4005dc283667a704a Mon Sep 17 00:00:00 2001
From: rajeswari1301 <rpeda001@ucr.edu>
Date: Tue, 2 Jun 2026 11:09:33 -0500
Subject: [PATCH] add duplicate block id detection

Co-authored-by: Copilot <copilot@github.com>
---
 src/dayamlchecker/messages.py       |  8 ++++
 src/dayamlchecker/yaml_structure.py | 18 +++++++
 tests/test_yaml_structure.py        | 74 +++++++++++++++++++++++++++++
 3 files changed, 100 insertions(+)

diff --git a/src/dayamlchecker/messages.py b/src/dayamlchecker/messages.py
index 2fedc18..cc85e13 100644
--- a/src/dayamlchecker/messages.py
+++ b/src/dayamlchecker/messages.py
@@ -19,6 +19,7 @@ class FindingClass(StrEnum):
 
 class MessageId(StrEnum):
     YAML_DUPLICATE_KEY = "yaml_duplicate_key"
+    YAML_DUPLICATE_BLOCK_ID = "yaml_duplicate_block_id"
     YAML_PARSE_ERROR = "yaml_parse_error"
     YAML_STRING_REQUIRED = "yaml_string_required"
 
@@ -190,6 +191,13 @@ class MessageDefinition:
         summary="YAML parsing error",
         template="{error}",
     ),
+    MessageId.YAML_DUPLICATE_BLOCK_ID: MessageDefinition(
+        code="EG104",
+        severity=Severity.ERROR,
+        finding_class=FindingClass.GENERAL,
+        summary="Duplicate block id",
+        template='Duplicate block id "{block_id}" - first used at line {first_line}. Docassemble will silently use the later block, which is almost certainly a mistake',
+    ),
     MessageId.YAML_STRING_REQUIRED: MessageDefinition(
         code="EG103",
         severity=Severity.ERROR,
diff --git a/src/dayamlchecker/yaml_structure.py b/src/dayamlchecker/yaml_structure.py
index 9251729..6b15c74 100644
--- a/src/dayamlchecker/yaml_structure.py
+++ b/src/dayamlchecker/yaml_structure.py
@@ -1580,6 +1580,7 @@ def find_errors_from_string(
     ]
     yaml_parser = _make_yaml_parser()
     prior_conditional_fields: list[dict[str, Any]] = []
+    seen_ids: dict[str, int] = {}
     parsed_docs: list[ParsedInterviewDocument] = []
     has_yaml_parse_errors = False
     line_number = 1
@@ -1704,6 +1705,23 @@ def find_errors_from_string(
                         )
                     )
 
+        block_id = _get_case_insensitive(doc, "id")
+        if isinstance(block_id, str) and block_id.strip():
+            block_id_clean = block_id.strip()
+            block_start = line_number + 1 if line_number > 1 else line_number
+            if block_id_clean in seen_ids:
+                all_errors.append(
+                    make_finding(
+                        MessageId.YAML_DUPLICATE_BLOCK_ID,
+                        file_name=input_file,
+                        line_number=block_start,
+                        block_id=block_id_clean,
+                        first_line=seen_ids[block_id_clean],
+                    )
+                )
+            else:
+                seen_ids[block_id_clean] = block_start
+
         unmatched_refs = _find_unmatched_interview_order_references(
             doc, prior_conditional_fields
         )
diff --git a/tests/test_yaml_structure.py b/tests/test_yaml_structure.py
index 241bd08..b54f1ff 100644
--- a/tests/test_yaml_structure.py
+++ b/tests/test_yaml_structure.py
@@ -2035,6 +2035,80 @@ def test_accessibility_html_rules_are_reported(self):
             f"Expected HTML accessibility parity findings, got: {errs}",
         )
 
+    def test_duplicate_block_id_errors(self):
+        """Error: two blocks with the same id should be flagged"""
+        invalid = """
+id: intro
+question: |
+  What is your name?
+field: user_name
+---
+id: intro
+mandatory: True
+question: |
+  Hello
+"""
+        errs = find_errors_from_string(invalid, input_file="<string_invalid>")
+        self.assertTrue(
+            any(e.message_id == "yaml_duplicate_block_id" for e in errs),
+            f"Expected duplicate id error, got: {errs}",
+        )
+
+    def test_unique_block_ids_valid(self):
+        """Valid: blocks with different ids should pass"""
+        valid = """
+id: intro
+question: |
+  What is your name?
+field: user_name
+---
+id: summary
+mandatory: True
+question: |
+  Hello
+"""
+        errs = find_errors_from_string(valid, input_file="<string_valid>")
+        self.assertFalse(
+            any(e.message_id == "yaml_duplicate_block_id" for e in errs),
+            f"Did not expect duplicate id error, got: {errs}",
+        )
+
+    def test_duplicate_id_case_sensitive(self):
+        """Valid: id matching is case sensitive"""
+        valid = """
+id: intro
+question: |
+  What is your name?
+field: user_name
+---
+id: Intro
+mandatory: True
+question: |
+  Hello
+"""
+        errs = find_errors_from_string(valid, input_file="<string_valid>")
+        self.assertFalse(
+            any(e.message_id == "yaml_duplicate_block_id" for e in errs),
+            f"Did not expect duplicate id error for different cases, got: {errs}",
+        )
+
+    def test_no_ids_valid(self):
+        """Valid: blocks with no ids should pass clean"""
+        valid = """
+question: |
+  What is your name?
+field: user_name
+---
+mandatory: True
+question: |
+  Hello
+"""
+        errs = find_errors_from_string(valid, input_file="<string_valid>")
+        self.assertFalse(
+            any(e.message_id == "yaml_duplicate_block_id" for e in errs),
+            f"Did not expect duplicate id error with no ids, got: {errs}",
+        )
+
 
 if __name__ == "__main__":
     unittest.main()