Refactor the parsing logic to set up the reference between section and professors using compound keys

go.mod

@@ -4,7 +4,7 @@ go 1.24.0
 
 require (
 	github.com/PuerkitoBio/goquery v1.8.1
-	github.com/UTDNebula/nebula-api/api v0.0.0-20260226052950-dbe2edfa3cfe //points to the compound-key branch of the nebula-api.
+	github.com/UTDNebula/nebula-api/api v0.0.0-20260302171502-90e1baaaf4e1 //points to the compound-key branch of the nebula-api.
 	github.com/chromedp/cdproto v0.0.0-20250120090109-d38428e4d9c8
 	github.com/chromedp/chromedp v0.12.1
 	github.com/google/go-cmp v0.7.0

go.sum

@@ -30,8 +30,8 @@ github.com/GoogleCloudPlatform/opentelemetry-operations-go/internal/resourcemapp
 github.com/GoogleCloudPlatform/opentelemetry-operations-go/internal/resourcemapping v0.51.0/go.mod h1:otE2jQekW/PqXk1Awf5lmfokJx4uwuqcj1ab5SpGeW0=
 github.com/PuerkitoBio/goquery v1.8.1 h1:uQxhNlArOIdbrH1tr0UXwdVFgDcZDrZVdcpygAcwmWM=
 github.com/PuerkitoBio/goquery v1.8.1/go.mod h1:Q8ICL1kNUJ2sXGoAhPGUdYDJvgQgHzJsnnd3H7Ho5jQ=
-github.com/UTDNebula/nebula-api/api v0.0.0-20260226052950-dbe2edfa3cfe h1:QUcltcZLKB+kbP3xa7h+sbOwf7vxofRGPKXHo+B35Q4=
-github.com/UTDNebula/nebula-api/api v0.0.0-20260226052950-dbe2edfa3cfe/go.mod h1:vWwnuoXFE/Lo9yW6Z6DJguCtAHu0xMym+6r2IEru1v0=
+github.com/UTDNebula/nebula-api/api v0.0.0-20260302171502-90e1baaaf4e1 h1:xdceHH3Y2AiC0DV0bp47zN9FvM7JdzcpJrod7SIOR5w=
+github.com/UTDNebula/nebula-api/api v0.0.0-20260302171502-90e1baaaf4e1/go.mod h1:vWwnuoXFE/Lo9yW6Z6DJguCtAHu0xMym+6r2IEru1v0=
 github.com/andybalholm/cascadia v1.3.1 h1:nhxRkql1kdYCc8Snf7D5/D3spOX+dBgjA6u8x004T2c=
 github.com/andybalholm/cascadia v1.3.1/go.mod h1:R4bJ1UQfqADjvDa4P6HZHLh/3OxWWEqc0Sk8XGwHqvA=
 github.com/bytedance/gopkg v0.1.3 h1:TPBSwH8RsouGCBcMBktLt1AymVo2TVsBVCY4b6TnZ/M=

parser/courseParser.go

@@ -53,15 +53,8 @@ func getCourse(internalCourseNumber string, session schema.AcademicSession, rowI
 	CoursePrefix, CourseNumber := getPrefixAndNumber(classInfo)
 	catalogYear := getCatalogYear(session)
 
-	courseKey := schema.CourseKey{
-		Subject_prefix: CoursePrefix,
-		Course_number:  CourseNumber,
-		Catalog_year:   catalogYear,
-	}
-
 	course := schema.Course{
 		Id:                     primitive.NewObjectID(),
-		Key:                    courseKey,
 		Course_number:          CourseNumber,
 		Subject_prefix:         CoursePrefix,
 		Title:                  utils.TrimWhitespace(rowInfo["Course Title:"].Text()),
@@ -72,7 +65,7 @@ func getCourse(internalCourseNumber string, session schema.AcademicSession, rowI
 		Activity_type:          classInfo["Activity Type:"],
 		Grading:                classInfo["Grading:"],
 		Internal_course_number: internalCourseNumber,
-		Catalog_year:           getCatalogYear(session),
+		Catalog_year:           catalogYear,
 	}
 
 	// Try to get lecture/lab contact hours and offering frequency from course description

parser/courseParser_test.go

@@ -19,7 +19,7 @@ func TestGetCourse(t *testing.T) {
 			output := *getCourse(courseNum, testCase.Section.Academic_session, testCase.RowInfo, testCase.ClassInfo)
 			expected := testCase.Course
 
-			diff := cmp.Diff(expected, output, cmpopts.IgnoreFields(schema.Course{}, "Id", "Enrollment_reqs", "Prerequisites", "Key", "Section_keys"))
+			diff := cmp.Diff(expected, output, cmpopts.IgnoreFields(schema.Course{}, "Id", "Sections", "Enrollment_reqs", "Prerequisites"))
 
 			if diff != "" {
 				t.Errorf("Failed (-expected +got)\n %s", diff)

parser/parser_test.go

@@ -316,7 +316,7 @@ func TestParse(t *testing.T) {
 		t.Run(key, func(t *testing.T) {
 			if outputCourse, ok := CoursesByKey[key]; ok {
 				diff := cmp.Diff(expectedCourse, outputCourse,
-					cmpopts.IgnoreFields(schema.Course{}, "Id", "Key", "Section_keys"),
+					cmpopts.IgnoreFields(schema.Course{}, "Id"),
 				)
 
 				if diff != "" {
@@ -361,7 +361,7 @@ func TestParse(t *testing.T) {
 			if outputProfessor, ok := ProfessorsByKey[key]; ok {
 
 				diff := cmp.Diff(expectedProfessor, outputProfessor,
-					cmpopts.IgnoreFields(schema.Professor{}, "Id", "Key", "Section_keys"),
+					cmpopts.IgnoreFields(schema.Professor{}, "Id"),
 					cmp.Transformer("Sections", func(sections []primitive.ObjectID) []string {
 						result := make([]string, 0, len(sections))
 						for _, id := range sections {
@@ -411,7 +411,7 @@ func TestParse(t *testing.T) {
 		t.Run(key, func(t *testing.T) {
 			if outputSection, ok := SectionsByClass[key]; ok {
 				diff := cmp.Diff(expectedSection, outputSection,
-					cmpopts.IgnoreFields(schema.Section{}, "Id", "Key", "Course_key", "Professor_keys"),
+					cmpopts.IgnoreFields(schema.Section{}, "Id"),
 					cmp.Transformer("Professors", func(profIds []primitive.ObjectID) []string {
 						result := make([]string, 0, len(profIds))
 						for _, id := range profIds {

parser/professorParser.go

@@ -10,7 +10,7 @@ import (
 	"go.mongodb.org/mongo-driver/bson/primitive"
 )
 
-func parseProfessors(sectionId schema.SectionKey, rowInfo map[string]*goquery.Selection) []schema.ProfessorKey {
+func parseProfessors(sectionKey schema.ProfSectionKey, rowInfo map[string]*goquery.Selection) []schema.ProfessorKey {
 	professorText := utils.TrimWhitespace(rowInfo["Instructor(s):"].Text())
 	professorMatches := personRegexp.FindAllStringSubmatch(professorText, -1)
 	var profRefs []schema.ProfessorKey = make([]schema.ProfessorKey, 0, len(professorMatches))
@@ -36,7 +36,7 @@ func parseProfessors(sectionId schema.SectionKey, rowInfo map[string]*goquery.Se
 
 		prof, profExists := Professors[profKey]
 		if profExists {
-			prof.Section_keys = append(prof.Section_keys, sectionId)
+			prof.Sections = append(prof.Sections, sectionKey)
 			profRefs = append(profRefs, professorKey)
 			continue
 		}
@@ -45,10 +45,9 @@ func parseProfessors(sectionId schema.SectionKey, rowInfo map[string]*goquery.Se
 		prof.Id = primitive.NewObjectID()
 		prof.First_name = firstName
 		prof.Last_name = lastName
-		prof.Key = professorKey
 		prof.Titles = []string{utils.TrimWhitespace(match[2])}
 		prof.Email = utils.TrimWhitespace(match[3])
-		prof.Section_keys = []schema.SectionKey{sectionId}
+		prof.Sections = []schema.ProfSectionKey{sectionKey}
 		profRefs = append(profRefs, professorKey)
 		Professors[profKey] = prof
 		ProfessorIDMap[prof.Id] = profKey

parser/profileLoader.go

@@ -37,13 +37,6 @@ func loadProfiles(inDir string) {
 		}
 
 		profKey := prof.First_name + prof.Last_name
-
-		professorKey := schema.ProfessorKey {
-			First_name: prof.First_name,
-			Last_name: prof.Last_name,
-		}
-
-		prof.Key = professorKey
 		Professors[profKey] = &prof
 		ProfessorIDMap[prof.Id] = profKey
 	}

parser/sectionParser.go

@@ -42,36 +42,35 @@ func parseSection(rowInfo map[string]*goquery.Selection, classInfo map[string]st
 	classNum, courseNum := getInternalClassAndCourseNum(classInfo)
 	session := getAcademicSession(rowInfo)
 	courseRef := parseCourse(courseNum, session, rowInfo, classInfo)
-
 	sectionNumber := getSectionNumber(classInfo)
 
 	id := primitive.NewObjectID()
 
 	// Build compound keys
-	courseKey := courseRef.Key
+	courseKey := schema.CourseKey{
+		Subject_prefix: courseRef.Subject_prefix,
+		Course_number:  courseRef.Course_number,
+		Catalog_year:   courseRef.Catalog_year,
+	}
 
-	if (courseKey == schema.CourseKey{}) {
-		courseKey = schema.CourseKey{
-			Subject_prefix: courseRef.Subject_prefix,
-			Course_number:  courseRef.Course_number,
-			Catalog_year:   courseRef.Catalog_year,
-		}
+	courseSectionKey := schema.CourseSectionKey{
+		Section_number: sectionNumber,
+		Term: session.Name,
 	}
-	sectionKey := schema.SectionKey{
+
+	profSectionKey := schema.ProfSectionKey{
 		Subject_prefix: courseRef.Subject_prefix,
 		Course_number:  courseRef.Course_number,
-		Catalog_year:   courseRef.Catalog_year,
-		Term:           session.Name,
 		Section_number: sectionNumber,
+		Term:           session.Name,
 	}
 
 	section := schema.Section{
 		Id:                    id,
-		Key:                   sectionKey,
 		Section_number:        sectionNumber,
-		Course_key:            courseKey,
+		Course:                courseKey,
 		Academic_session:      session,
-		Professor_keys:        parseProfessors(sectionKey, rowInfo),
+		Professors:            parseProfessors(profSectionKey, rowInfo),
 		Teaching_assistants:   getTeachingAssistants(rowInfo),
 		Internal_class_number: classNum,
 		Instruction_mode:      getInstructionMode(classInfo),
@@ -85,7 +84,7 @@ func parseSection(rowInfo map[string]*goquery.Selection, classInfo map[string]st
 	Sections[section.Id] = &section
 
 	// Append new section to course's section listing
-	courseRef.Section_keys = append(courseRef.Section_keys, sectionKey)
+	courseRef.Sections = append(courseRef.Sections, courseSectionKey)
 }
 
 // getInternalClassAndCourseNum returns a sections internal course and class number,

parser/testdata/case_000/course.json

@@ -15,7 +15,10 @@
 	"corequisites": null,
 	"co_or_pre_requisites": null,
 	"sections": [
-		"67d07ee0c972c18731e23bd8"
+		{
+			"section_number": "003",
+			"term": "25S"
+		}
 	],
 	"lecture_contact_hours": "3",
 	"laboratory_contact_hours": "0",

parser/testdata/case_000/professors.json

@@ -17,7 +17,12 @@
 		"image_uri": "",
 		"office_hours": null,
 		"sections": [
-			"67d07ee0c972c18731e23bd8"
+			{
+				"subject_prefix": "ACCT",
+				"course_number": "2301",
+				"section_number": "003",
+				"term": "25S"
+			}
 		]
 	},
 	{
@@ -38,7 +43,12 @@
 		"image_uri": "",
 		"office_hours": null,
 		"sections": [
-			"67d07ee0c972c18731e23bd8"
+			{
+				"subject_prefix": "ACCT",
+				"course_number": "2301",
+				"section_number": "003",
+				"term": "25S"
+			}
 		]
 	}
 ]

parser/testdata/case_000/section.json

@@ -1,16 +1,26 @@
 {
 	"_id": "67d07ee0c972c18731e23bd8",
 	"section_number": "003",
-	"course_reference": "67d07ee0c972c18731e23bd7",
+	"course_key": {
+		"subject_prefix": "ACCT",
+		"course_number": "2301",
+		"catalog_year": "24"
+	},
 	"section_corequisites": null,
 	"academic_session": {
 		"name": "25S",
 		"start_date": "2025-01-21T00:00:00-06:00",
 		"end_date": "2025-05-16T00:00:00-05:00"
 	},
 	"professors": [
-		"67d07ee0c972c18731e23bd9",
-		"67d07ee0c972c18731e23bda"
+		{
+			"first_name": "Naim Bugra",
+			"last_name": "Ozel"
+		},
+		{
+			"first_name": "Jieying",
+			"last_name": "Zhang"
+		}
 	],
 	"teaching_assistants": [
 		{

parser/testdata/case_001/course.json

@@ -15,7 +15,10 @@
 	"corequisites": null,
 	"co_or_pre_requisites": null,
 	"sections": [
-		"67d07ee0c972c18731e23bdc"
+		{
+			"section_number": "001",
+			"term": "25S"
+		}
 	],
 	"lecture_contact_hours": "3",
 	"laboratory_contact_hours": "0",

parser/testdata/case_001/professors.json

@@ -17,7 +17,12 @@
 		"image_uri": "",
 		"office_hours": null,
 		"sections": [
-			"67d07ee0c972c18731e23bdc"
+			{
+				"subject_prefix": "ACCT",
+				"course_number": "2301",
+				"section_number": "001",
+				"term": "25S"
+			}
 		]
 	},
 	{
@@ -38,7 +43,12 @@
 		"image_uri": "",
 		"office_hours": null,
 		"sections": [
-			"67d07ee0c972c18731e23bdc"
+			{
+				"subject_prefix": "ACCT",
+				"course_number": "2301",
+				"section_number": "001",
+				"term": "25S"
+			}
 		]
 	}
 ]

parser/testdata/case_001/section.json

@@ -1,16 +1,26 @@
 {
 	"_id": "67d07ee0c972c18731e23bdc",
 	"section_number": "001",
-	"course_reference": "67d07ee0c972c18731e23bdb",
+	"course_key": {
+		"subject_prefix": "ACCT",
+		"course_number": "2301",
+		"catalog_year": "24"
+	},
 	"section_corequisites": null,
 	"academic_session": {
 		"name": "25S",
 		"start_date": "2025-01-21T00:00:00-06:00",
 		"end_date": "2025-05-16T00:00:00-05:00"
 	},
 	"professors": [
-		"67d07ee0c972c18731e23bdd",
-		"67d07ee0c972c18731e23bde"
+		{
+			"first_name": "Jieying",
+			"last_name": "Zhang"
+		},
+		{
+			"first_name": "Naim Bugra",
+			"last_name": "Ozel"
+		}
 	],
 	"teaching_assistants": [
 		{

parser/testdata/case_002/course.json

@@ -15,7 +15,10 @@
 	"corequisites": null,
 	"co_or_pre_requisites": null,
 	"sections": [
-		"67d07ee0c972c18731e23be0"
+		{
+			"section_number": "501",
+			"term": "25S"
+		}
 	],
 	"lecture_contact_hours": "3",
 	"laboratory_contact_hours": "0",

parser/testdata/case_002/professors.json

@@ -17,7 +17,12 @@
 		"image_uri": "",
 		"office_hours": null,
 		"sections": [
-			"67d07ee0c972c18731e23be0"
+			{
+				"subject_prefix": "BA",
+				"course_number": "1320",
+				"section_number": "501",
+				"term": "25S"
+			}
 		]
 	}
 ]

parser/testdata/case_002/section.json

@@ -1,15 +1,22 @@
 {
 	"_id": "67d07ee0c972c18731e23be0",
 	"section_number": "501",
-	"course_reference": "67d07ee0c972c18731e23bdf",
+	"course_key": {
+		"subject_prefix": "BA",
+		"course_number": "1320",
+		"catalog_year": "24"
+	},
 	"section_corequisites": null,
 	"academic_session": {
 		"name": "25S",
 		"start_date": "2025-01-21T00:00:00-06:00",
 		"end_date": "2025-05-16T00:00:00-05:00"
 	},
 	"professors": [
-		"67d07ee0c972c18731e23be1"
+		{
+			"first_name": "Peter",
+			"last_name": "Lewin"
+		}
 	],
 	"teaching_assistants": [
 		{

parser/testdata/case_003/course.json

@@ -15,7 +15,10 @@
 	"corequisites": null,
 	"co_or_pre_requisites": null,
 	"sections": [
-		"67d07ee0c972c18731e23be3"
+		{
+			"section_number": "016",
+			"term": "25S"
+		}
 	],
 	"lecture_contact_hours": "1",
 	"laboratory_contact_hours": "0",