TSA/chapter-organizer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Enhance event occurrence parsing to correctly skip high school events

Browse Source 
This commit updates the EventOccurrenceParser to ensure that high school (HS) events are not incorrectly associated with middle school (MS) events during parsing. The logic now gracefully skips HS section headers, preventing any fuzzy matching from leading to incorrect associations. Additionally, a new unit test has been added to verify that HS occurrences are correctly excluded from MS event occurrences, ensuring the integrity of the parsing process.
This commit is contained in:
poprhythm
2026-01-09 08:32:41 -05:00
parent 19e5ef0675
commit 2eae3f205c
3 changed files with 96 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Core/Parsers/EventOccurrenceParser.cs
+25 -21
View File
@@ -73,20 +73,22 @@ public class EventOccurrenceParser
// Section headers break continuation mode
inContinuationMode = false;
// Use fuzzy matching to find the best matching event definition
// Check if this is an HS event - if so, skip gracefully regardless of whether it matches
// This prevents HS events from being incorrectly associated with MS events (e.g.,
// "Biotechnology Design – HS" matching "Biotechnology" MS event)
if (schoolLevel.Equals("HS", StringComparison.OrdinalIgnoreCase))
{
result.SkippedHSSectionHeaders.Add(normalizedLine);
currentEventDefinition = null; // Skip subsequent occurrences
inHSSection = true; // Mark that we're in an HS section
continue; // No issue created
}
// For MS events, use fuzzy matching to find the best matching event definition
var evt = EventOccurrenceParsers.SectionHeaderMatcher.MatchEventDefinition(eventNamePart, _events);
if (evt == null)
{
// Check if this is an HS event - if so, skip gracefully
if (schoolLevel.Equals("HS", StringComparison.OrdinalIgnoreCase))
{
result.SkippedHSSectionHeaders.Add(normalizedLine);
currentEventDefinition = null; // Skip subsequent occurrences
inHSSection = true; // Mark that we're in an HS section
continue; // No issue created
}
// For non-HS unmatched headers, create issue as before
// For unmatched MS headers, create issue
var bestRatio = EventOccurrenceParsers.SectionHeaderMatcher.GetBestMatchRatio(eventNamePart, _events);
issues.Add(new ParsingIssue
{
@@ -118,19 +120,21 @@ public class EventOccurrenceParser
// Section headers break continuation mode
inContinuationMode = false;
// Check if this is an HS event - if so, skip gracefully regardless of whether it matches
// This prevents HS events from being incorrectly associated with MS events
if (normalizedLine.Contains("HS", StringComparison.OrdinalIgnoreCase))
{
result.SkippedHSSectionHeaders.Add(normalizedLine);
currentEventDefinition = null; // Skip subsequent occurrences
inHSSection = true; // Mark that we're in an HS section
continue; // No issue created
}
// For MS events, use fuzzy matching to find the best matching event definition
var evt = EventOccurrenceParsers.SectionHeaderMatcher.MatchEventDefinition(normalizedLine, _events);
if (evt == null)
{
// Check if this is an HS event - if so, skip gracefully
if (normalizedLine.Contains("HS", StringComparison.OrdinalIgnoreCase))
{
result.SkippedHSSectionHeaders.Add(normalizedLine);
currentEventDefinition = null; // Skip subsequent occurrences
inHSSection = true; // Mark that we're in an HS section
continue; // No issue created
}
// For non-HS unmatched headers, create issue as before
// For unmatched MS headers, create issue
var bestRatio = EventOccurrenceParsers.SectionHeaderMatcher.GetBestMatchRatio(normalizedLine, _events);
issues.Add(new ParsingIssue
{