diff --git a/Makefile b/Makefile
index 6ea3a401..b6d6de3d 100644
--- a/Makefile
+++ b/Makefile
@@ -88,7 +88,12 @@ GENERATED = \
 	schemas/xbrl/utr/volume-per-monetary-item-type.json \
 	schemas/iso/country/2020/alpha-2.json \
 	schemas/iso/country/2020/alpha-3.json \
-	schemas/iso/country/2020/numeric.json
+	schemas/iso/country/2020/numeric.json \
+	schemas/iso/language/2023/set-1.json \
+	schemas/iso/language/2023/set-2-bibliographic.json \
+	schemas/iso/language/2023/set-2-terminologic.json \
+	schemas/iso/language/2023/set-3.json \
+	schemas/iso/language/2023/set-5.json
 
 # TODO: Make `jsonschema fmt` automatically detect test files
 all: common test
@@ -152,7 +157,6 @@ schemas/iso/currency/2015/%.json: \
 	$(JSONSCHEMA) fmt $@
 
 build/xbrl/utr/%.json: scripts/xml2json.py vendor/data/xbrl/utr/%.xml
-	$(MKDIRP) $(dir $@)
 	$(PYTHON) $< $(word 2,$^) $@
 schemas/xbrl/utr/%.json: build/xbrl/utr/utr.json templates/xbrl/utr/%.jq
 	$(MKDIRP) $(dir $@)
@@ -166,6 +170,26 @@ schemas/iso/country/2020/%.json: \
 	$(JQ) --from-file $(word 2,$^) $< > $@
 	$(JSONSCHEMA) fmt $@
 
+build/iso/language/iso-639-2.json: \
+	vendor/data/iso/language/ISO-639-2_utf-8.txt \
+	scripts/csv2json.py
+	$(PYTHON) $(word 2,$^) --delimiter '|' --encoding utf-8-sig --no-header \
+		--field-names "part2b,part2t,part1,name,name_french" $< $@
+build/iso/language/iso-639-3.json: \
+	vendor/data/iso/language/iso-639-3_Code_Tables/iso-639-3_Code_Tables_20251015/iso-639-3.tab \
+	scripts/csv2json.py
+	$(PYTHON) $(word 2,$^) --tab $< $@
+build/iso/language/enriched.json: \
+	build/iso/language/iso-639-2.json \
+	build/iso/language/iso-639-3.json \
+	scripts/iso-language-enrich.jq
+	$(JQ) --slurpfile iso2 $< --slurpfile iso3 $(word 2,$^) -n -f $(word 3,$^) > $@
+schemas/iso/language/2023/%.json: \
+	build/iso/language/enriched.json \
+	templates/iso/language/2023/%.jq
+	$(MKDIRP) $(dir $@)
+	$(JQ) --from-file $(word 2,$^) $< > $@
+	$(JSONSCHEMA) fmt $@
 
 # TODO: Add a `jsonschema pkg` command instead
 .PHONY: dist
diff --git a/generate/iso/language/main.py b/generate/iso/language/main.py
deleted file mode 100644
index 926e9b85..00000000
--- a/generate/iso/language/main.py
+++ /dev/null
@@ -1,360 +0,0 @@
-import json
-import os
-import sys
-import csv
-
-
-def parse_iso_639_2(file_path, set_3_lookup_by_part1, set_3_lookup_by_part2b, set_3_lookup_by_part2t):
-    """Parse ISO-639-2 file which contains Set 1, Set 2, and Set 5."""
-    set_1 = {}
-    set_2_bibliographic = {}
-    set_2_terminologic = {}
-    set_5 = {}
-
-    with open(file_path, 'r', encoding='utf-8-sig') as file:
-        for line in file:
-            line = line.strip()
-            if not line:
-                continue
-
-            parts = line.split('|')
-            if len(parts) < 5:
-                continue
-
-            part2b = parts[0].strip()
-            part2t = parts[1].strip()
-            part1 = parts[2].strip()
-            english_name = parts[3].strip()
-            french_name = parts[4].strip()
-
-            # Determine if this is Set 5 (language families/groups)
-            is_language_family = 'languages' in english_name.lower() or 'language family' in english_name.lower()
-
-            # Set 5 entries
-            if is_language_family and part2b:
-                set_5[part2b] = {
-                    'name': english_name,
-                    'name_french': french_name
-                }
-            else:
-                # Set 1 entries
-                if part1:
-                    set_3_data = set_3_lookup_by_part1.get(part1, {})
-                    set_1[part1] = {
-                        'name': english_name,
-                        'name_french': french_name,
-                        'part2b': part2b if part2b else None,
-                        'part2t': part2t if part2t else None,
-                        'scope': set_3_data.get('scope'),
-                        'language_type': set_3_data.get('language_type')
-                    }
-
-                # Set 2 entries
-                if part2b:
-                    set_3_data = set_3_lookup_by_part2b.get(part2b, {})
-                    set_2_bibliographic[part2b] = {
-                        'name': english_name,
-                        'name_french': french_name,
-                        'part1': part1 if part1 else None,
-                        'scope': set_3_data.get('scope'),
-                        'language_type': set_3_data.get('language_type')
-                    }
-
-                if part2t:
-                    set_3_data = set_3_lookup_by_part2t.get(part2t, {})
-                    set_2_terminologic[part2t] = {
-                        'name': english_name,
-                        'name_french': french_name,
-                        'part1': part1 if part1 else None,
-                        'scope': set_3_data.get('scope'),
-                        'language_type': set_3_data.get('language_type')
-                    }
-
-    return set_1, set_2_bibliographic, set_2_terminologic, set_5
-
-
-def parse_iso_639_3(file_path):
-    """Parse ISO-639-3 file which contains Set 3."""
-    set_3 = {}
-
-    with open(file_path, 'r', encoding='utf-8') as file:
-        reader = csv.DictReader(file, delimiter='\t')
-        for row in reader:
-            code = row['Id'].strip()
-            if not code:
-                continue
-
-            metadata = {
-                'name': row['Ref_Name'].strip(),
-                'scope': row['Scope'].strip() if row['Scope'].strip() else None,
-                'language_type': row['Language_Type'].strip() if row['Language_Type'].strip() else None,
-                'part2b': row['Part2b'].strip() if row['Part2b'].strip() else None,
-                'part2t': row['Part2t'].strip() if row['Part2t'].strip() else None,
-                'part1': row['Part1'].strip() if row['Part1'].strip() else None,
-                'comment': row['Comment'].strip() if row['Comment'].strip() else None
-            }
-
-            set_3[code] = metadata
-
-    return set_3
-
-
-def build_set_3_lookups(set_3):
-    """Build lookup tables from Set 3 by Part1, Part2b, and Part2t codes."""
-    lookup_by_part1 = {}
-    lookup_by_part2b = {}
-    lookup_by_part2t = {}
-
-    for code, metadata in set_3.items():
-        if metadata.get('part1'):
-            lookup_by_part1[metadata['part1']] = {
-                'scope': metadata['scope'],
-                'language_type': metadata['language_type']
-            }
-        if metadata.get('part2b'):
-            lookup_by_part2b[metadata['part2b']] = {
-                'scope': metadata['scope'],
-                'language_type': metadata['language_type']
-            }
-        if metadata.get('part2t'):
-            lookup_by_part2t[metadata['part2t']] = {
-                'scope': metadata['scope'],
-                'language_type': metadata['language_type']
-            }
-
-    return lookup_by_part1, lookup_by_part2b, lookup_by_part2t
-
-
-def expand_scope(scope_code):
-    """Expand scope code to full word."""
-    if not scope_code:
-        return None
-
-    scope_map = {
-        'I': 'individual',
-        'M': 'macrolanguage',
-        'S': 'special'
-    }
-
-    if scope_code not in scope_map:
-        print(f"Error: Unknown scope code '{scope_code}'", file=sys.stderr)
-        sys.exit(1)
-
-    return scope_map[scope_code]
-
-
-def expand_language_type(type_code):
-    """Expand language type code to full word."""
-    if not type_code:
-        return None
-
-    type_map = {
-        'L': 'living',
-        'E': 'extinct',
-        'H': 'historic',
-        'C': 'constructed',
-        'S': 'special',
-        'A': 'ancient'
-    }
-
-    if type_code not in type_map:
-        print(f"Error: Unknown language type code '{type_code}'", file=sys.stderr)
-        sys.exit(1)
-
-    return type_map[type_code]
-
-
-def build_base_schema():
-    """Build base schema with required fields."""
-    return {
-        "$schema": "https://json-schema.org/draft/2020-12/schema",
-        "x-license": "https://github.com/sourcemeta/std/blob/main/LICENSE",
-        "x-links": ["https://www.iso.org/standard/74575.html"]
-    }
-
-
-def generate_set_1_schema(set_1, output_dir):
-    """Generate schema for ISO 639-1 (2-letter codes)."""
-    schema = build_base_schema()
-    schema.update({
-        "$comment": "Set 1 contains the most common languages (2-letter codes). All Set 1 codes have corresponding codes in Set 2 and Set 3",
-        "title": "ISO 639-1:2023 Language Code",
-        "description": "A two-letter language code from ISO 639-1",
-        "examples": sorted(set_1.keys())[:4],
-        "anyOf": [
-            {
-                "const": code,
-                "title": metadata['name'],
-                **({'x-scope': expand_scope(metadata['scope'])} if metadata.get('scope') else {}),
-                **({'x-language-type': expand_language_type(metadata['language_type'])} if metadata.get('language_type') else {}),
-                **({'x-name-french': metadata['name_french']} if metadata.get('name_french') else {}),
-                **({'x-set-2-bibliographic': metadata['part2b']} if metadata.get('part2b') else {}),
-                **({'x-set-2-terminologic': metadata['part2t']} if metadata.get('part2t') else {})
-            }
-            for code, metadata in sorted(set_1.items())
-        ]
-    })
-
-    file_path = os.path.join(output_dir, "set-1.json")
-    with open(file_path, 'w') as file:
-        json.dump(schema, file, indent=2)
-        file.write('\n')
-    print(f"Generated {file_path} with {len(set_1)} codes")
-
-
-def generate_set_2_bibliographic_schema(set_2_bibliographic, output_dir):
-    """Generate schema for ISO 639-2 bibliographic codes."""
-    schema = build_base_schema()
-    schema.update({
-        "$comment": "Set 2 bibliographic is a superset of Set 1 and a subset of Set 3. Bibliographic codes are based on English language names",
-        "title": "ISO 639-2:2023 Bibliographic Language Code",
-        "description": "A three-letter bibliographic language code from ISO 639-2",
-        "examples": sorted(set_2_bibliographic.keys())[:4],
-        "anyOf": [
-            {
-                "const": code,
-                "title": metadata['name'],
-                **({'x-scope': expand_scope(metadata['scope'])} if metadata.get('scope') else {}),
-                **({'x-language-type': expand_language_type(metadata['language_type'])} if metadata.get('language_type') else {}),
-                **({'x-name-french': metadata['name_french']} if metadata.get('name_french') else {}),
-                **({'x-set-1': metadata['part1']} if metadata.get('part1') else {})
-            }
-            for code, metadata in sorted(set_2_bibliographic.items())
-        ]
-    })
-
-    file_path = os.path.join(output_dir, "set-2-bibliographic.json")
-    with open(file_path, 'w') as file:
-        json.dump(schema, file, indent=2)
-        file.write('\n')
-    print(f"Generated {file_path} with {len(set_2_bibliographic)} codes")
-
-
-def generate_set_2_terminologic_schema(set_2_terminologic, output_dir):
-    """Generate schema for ISO 639-2 terminologic codes."""
-    schema = build_base_schema()
-    schema.update({
-        "$comment": "Set 2 terminologic is a superset of Set 1 and a subset of Set 3. Terminologic codes are based on native language names. Only about 20 languages have both bibliographic and terminologic codes",
-        "title": "ISO 639-2:2023 Terminologic Language Code",
-        "description": "A three-letter terminologic language code from ISO 639-2",
-        "examples": sorted(set_2_terminologic.keys())[:4],
-        "anyOf": [
-            {
-                "const": code,
-                "title": metadata['name'],
-                **({'x-scope': expand_scope(metadata['scope'])} if metadata.get('scope') else {}),
-                **({'x-language-type': expand_language_type(metadata['language_type'])} if metadata.get('language_type') else {}),
-                **({'x-name-french': metadata['name_french']} if metadata.get('name_french') else {}),
-                **({'x-set-1': metadata['part1']} if metadata.get('part1') else {})
-            }
-            for code, metadata in sorted(set_2_terminologic.items())
-        ]
-    })
-
-    file_path = os.path.join(output_dir, "set-2-terminologic.json")
-    with open(file_path, 'w') as file:
-        json.dump(schema, file, indent=2)
-        file.write('\n')
-    print(f"Generated {file_path} with {len(set_2_terminologic)} codes")
-
-
-def generate_set_3_schema(set_3, output_dir):
-    """Generate schema for ISO 639-3 (comprehensive language codes)."""
-    schema = build_base_schema()
-    schema.update({
-        "$comment": "Set 3 is a superset of Set 1 and Set 2. It provides comprehensive coverage of individual languages, macrolanguages, and special codes",
-        "title": "ISO 639-3:2023 Language Code",
-        "description": "A three-letter language code from ISO 639-3",
-        "examples": sorted(set_3.keys())[:4],
-        "anyOf": [
-            {
-                "const": code,
-                "title": metadata['name'],
-                **({'x-scope': expand_scope(metadata['scope'])} if metadata.get('scope') else {}),
-                **({'x-language-type': expand_language_type(metadata['language_type'])} if metadata.get('language_type') else {}),
-                **({'x-set-2-bibliographic': metadata['part2b']} if metadata.get('part2b') else {}),
-                **({'x-set-2-terminologic': metadata['part2t']} if metadata.get('part2t') else {}),
-                **({'x-set-1': metadata['part1']} if metadata.get('part1') else {}),
-                **({'$comment': metadata['comment']} if metadata.get('comment') else {})
-            }
-            for code, metadata in sorted(set_3.items())
-        ]
-    })
-
-    file_path = os.path.join(output_dir, "set-3.json")
-    with open(file_path, 'w') as file:
-        json.dump(schema, file, indent=2)
-        file.write('\n')
-    print(f"Generated {file_path} with {len(set_3)} codes")
-
-
-def generate_set_5_schema(set_5, output_dir):
-    """Generate schema for ISO 639-5 (language families and groups)."""
-    schema = build_base_schema()
-    schema.update({
-        "$comment": "Set 5 codes language families and groups, not individual languages. It is independent from Sets 1-3",
-        "title": "ISO 639-5:2023 Language Family Code",
-        "description": "A three-letter code for language families and groups from ISO 639-5",
-        "examples": sorted(set_5.keys())[:4],
-        "anyOf": [
-            {
-                "const": code,
-                "title": metadata['name'],
-                **({'x-name-french': metadata['name_french']} if metadata.get('name_french') else {})
-            }
-            for code, metadata in sorted(set_5.items())
-        ]
-    })
-
-    file_path = os.path.join(output_dir, "set-5.json")
-    with open(file_path, 'w') as file:
-        json.dump(schema, file, indent=2)
-        file.write('\n')
-    print(f"Generated {file_path} with {len(set_5)} codes")
-
-
-def main():
-    script_dir = os.path.dirname(os.path.abspath(__file__))
-    project_root = os.path.dirname(os.path.dirname(os.path.dirname(script_dir)))
-
-    iso_639_2_file = os.path.join(project_root, "vendor", "data", "iso", "language", "ISO-639-2_utf-8.txt")
-    iso_639_3_file = os.path.join(project_root, "vendor", "data", "iso", "language", "iso-639-3_Code_Tables", "iso-639-3_Code_Tables_20251015", "iso-639-3.tab")
-    output_dir = os.path.join(project_root, "schemas", "iso", "language", "2023")
-
-    if not os.path.exists(iso_639_2_file):
-        print(f"Error: Data file not found: {iso_639_2_file}", file=sys.stderr)
-        sys.exit(1)
-
-    if not os.path.exists(iso_639_3_file):
-        print(f"Error: Data file not found: {iso_639_3_file}", file=sys.stderr)
-        sys.exit(1)
-
-    # Parse Set 3 first to build lookup tables
-    print("Parsing ISO 639-3 data...")
-    set_3 = parse_iso_639_3(iso_639_3_file)
-
-    print("Building Set 3 lookup tables...")
-    lookup_by_part1, lookup_by_part2b, lookup_by_part2t = build_set_3_lookups(set_3)
-
-    # Parse ISO 639-2 data with Set 3 lookups
-    print("Parsing ISO 639-2 data...")
-    set_1, set_2_bibliographic, set_2_terminologic, set_5 = parse_iso_639_2(
-        iso_639_2_file, lookup_by_part1, lookup_by_part2b, lookup_by_part2t
-    )
-
-    # Create output directory
-    os.makedirs(output_dir, exist_ok=True)
-
-    # Generate schemas
-    print("Generating schemas...")
-    generate_set_1_schema(set_1, output_dir)
-    generate_set_2_bibliographic_schema(set_2_bibliographic, output_dir)
-    generate_set_2_terminologic_schema(set_2_terminologic, output_dir)
-    generate_set_3_schema(set_3, output_dir)
-    generate_set_5_schema(set_5, output_dir)
-
-    print("Done!")
-
-
-if __name__ == "__main__":
-    main()
diff --git a/scripts/csv2json.py b/scripts/csv2json.py
new file mode 100644
index 00000000..91f2c657
--- /dev/null
+++ b/scripts/csv2json.py
@@ -0,0 +1,57 @@
+#!/usr/bin/env python3
+
+import csv
+import json
+import os
+import sys
+import argparse
+
+
+def csv_to_json(input_file, output_file, delimiter, has_header, encoding, field_names):
+    """Convert CSV/TSV file to JSON array."""
+    rows = []
+
+    with open(input_file, 'r', encoding=encoding) as file:
+        if has_header:
+            reader = csv.DictReader(file, delimiter=delimiter)
+            for row in reader:
+                rows.append(row)
+        elif field_names:
+            reader = csv.DictReader(file, delimiter=delimiter, fieldnames=field_names)
+            for row in reader:
+                rows.append(row)
+        else:
+            reader = csv.reader(file, delimiter=delimiter)
+            for row in reader:
+                rows.append(row)
+
+    output_directory = os.path.dirname(output_file)
+    if output_directory:
+        os.makedirs(output_directory, exist_ok=True)
+
+    with open(output_file, 'w', encoding='utf-8') as file:
+        json.dump(rows, file, indent=2, ensure_ascii=False)
+        file.write('\n')
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Convert CSV/TSV files to JSON')
+    parser.add_argument('input', help='Input CSV/TSV file')
+    parser.add_argument('output', help='Output JSON file')
+    parser.add_argument('-d', '--delimiter', default=',', help='Field delimiter (default: comma)')
+    parser.add_argument('--tab', action='store_true', help='Use tab as delimiter (shortcut for -d $\'\\t\')')
+    parser.add_argument('--no-header', action='store_true', help='First line is not a header (output as array of arrays)')
+    parser.add_argument('-e', '--encoding', default='utf-8', help='Input file encoding (default: utf-8)')
+    parser.add_argument('--field-names', help='Comma-separated field names (use with --no-header to create objects)')
+
+    args = parser.parse_args()
+
+    delimiter = '\t' if args.tab else args.delimiter
+    has_header = not args.no_header
+    field_names = args.field_names.split(',') if args.field_names else None
+
+    csv_to_json(args.input, args.output, delimiter, has_header, args.encoding, field_names)
+
+
+if __name__ == '__main__':
+    main()
diff --git a/scripts/iso-language-enrich.jq b/scripts/iso-language-enrich.jq
new file mode 100644
index 00000000..d4c41ab6
--- /dev/null
+++ b/scripts/iso-language-enrich.jq
@@ -0,0 +1,86 @@
+# Build lookup tables from Set 3 (ISO-639-3) for enrichment
+($iso3[0] | map(select(.Part1 != null and .Part1 != "")) | INDEX(.Part1)) as $lookup_by_part1 |
+($iso3[0] | map(select(.Part2b != null and .Part2b != "")) | INDEX(.Part2b)) as $lookup_by_part2b |
+($iso3[0] | map(select(.Part2t != null and .Part2t != "")) | INDEX(.Part2t)) as $lookup_by_part2t |
+
+# Process ISO-639-2 data to extract Sets 1, 2, and 5
+($iso2[0] | map(
+  . as $entry |
+  ($entry.name | ascii_downcase | (contains("languages") or contains("language family"))) as $is_language_family |
+  {
+    is_family: $is_language_family,
+    part1: ($entry.part1 // "" | if . == "" then null else . end),
+    part2b: ($entry.part2b // "" | if . == "" then null else . end),
+    part2t: ($entry.part2t // "" | if . == "" then null else . end),
+    name: $entry.name,
+    name_french: ($entry.name_french // "" | if . == "" then null else . end)
+  }
+)) as $processed_iso2 |
+
+# Set 5: Language families (identified by name patterns)
+($processed_iso2 | map(select(.is_family and .part2b != null) | {
+  code: .part2b,
+  name: .name,
+  name_french: .name_french
+})) as $set_5 |
+
+# Set 1: 2-letter codes (part1)
+($processed_iso2 | map(select(.is_family | not) | select(.part1 != null) |
+  ($lookup_by_part1[.part1] // {}) as $set_3_data |
+  {
+    code: .part1,
+    name: .name,
+    name_french: .name_french,
+    part2b: .part2b,
+    part2t: .part2t,
+    scope: ($set_3_data.Scope // "" | if . == "" then null else . end),
+    language_type: ($set_3_data.Language_Type // "" | if . == "" then null else . end)
+  }
+)) as $set_1 |
+
+# Set 2 bibliographic: 3-letter bibliographic codes (part2b)
+($processed_iso2 | map(select(.is_family | not) | select(.part2b != null) |
+  ($lookup_by_part2b[.part2b] // {}) as $set_3_data |
+  {
+    code: .part2b,
+    name: .name,
+    name_french: .name_french,
+    part1: .part1,
+    scope: ($set_3_data.Scope // "" | if . == "" then null else . end),
+    language_type: ($set_3_data.Language_Type // "" | if . == "" then null else . end)
+  }
+)) as $set_2_bibliographic |
+
+# Set 2 terminologic: 3-letter terminologic codes (part2t)
+($processed_iso2 | map(select(.is_family | not) | select(.part2t != null) |
+  ($lookup_by_part2t[.part2t] // {}) as $set_3_data |
+  {
+    code: .part2t,
+    name: .name,
+    name_french: .name_french,
+    part1: .part1,
+    scope: ($set_3_data.Scope // "" | if . == "" then null else . end),
+    language_type: ($set_3_data.Language_Type // "" | if . == "" then null else . end)
+  }
+)) as $set_2_terminologic |
+
+# Set 3: All ISO-639-3 codes
+($iso3[0] | map(select(.Id != null and .Id != "") | {
+  code: .Id,
+  name: .Ref_Name,
+  scope: (.Scope // "" | if . == "" then null else . end),
+  language_type: (.Language_Type // "" | if . == "" then null else . end),
+  part2b: (.Part2b // "" | if . == "" then null else . end),
+  part2t: (.Part2t // "" | if . == "" then null else . end),
+  part1: (.Part1 // "" | if . == "" then null else . end),
+  comment: (.Comment // "" | if . == "" then null else . end)
+})) as $set_3 |
+
+# Output combined structure
+{
+  set_1: $set_1,
+  set_2_bibliographic: $set_2_bibliographic,
+  set_2_terminologic: $set_2_terminologic,
+  set_3: $set_3,
+  set_5: $set_5
+}
diff --git a/templates/iso/language/2023/set-1.jq b/templates/iso/language/2023/set-1.jq
new file mode 100644
index 00000000..fc912195
--- /dev/null
+++ b/templates/iso/language/2023/set-1.jq
@@ -0,0 +1,41 @@
+# Scope expansion map
+def expand_scope:
+  if . == "I" then "individual"
+  elif . == "M" then "macrolanguage"
+  elif . == "S" then "special"
+  else . end;
+
+# Language type expansion map
+def expand_language_type:
+  if . == "L" then "living"
+  elif . == "E" then "extinct"
+  elif . == "H" then "historic"
+  elif . == "C" then "constructed"
+  elif . == "S" then "special"
+  elif . == "A" then "ancient"
+  else . end;
+
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "title": "ISO 639-1:2023 Language Code",
+  "description": "A two-letter language code from ISO 639-1",
+  "$comment": "Set 1 contains the most common languages (2-letter codes). All Set 1 codes have corresponding codes in Set 2 and Set 3",
+  "examples": (.set_1 | sort_by(.code) | .[0:4] | map(.code)),
+  "x-license": "https://github.com/sourcemeta/std/blob/main/LICENSE",
+  "x-links": ["https://www.iso.org/standard/74575.html"],
+  "anyOf": (
+    .set_1
+    | sort_by(.code)
+    | map({
+        "title": .name
+      } +
+      (if .scope then {"x-scope": (.scope | expand_scope)} else {} end) +
+      (if .language_type then {"x-language-type": (.language_type | expand_language_type)} else {} end) +
+      (if .name_french then {"x-name-french": .name_french} else {} end) +
+      (if .part2b then {"x-set-2-bibliographic": .part2b} else {} end) +
+      (if .part2t then {"x-set-2-terminologic": .part2t} else {} end) +
+      {
+        "const": .code
+      })
+  )
+}
diff --git a/templates/iso/language/2023/set-2-bibliographic.jq b/templates/iso/language/2023/set-2-bibliographic.jq
new file mode 100644
index 00000000..9e957f4a
--- /dev/null
+++ b/templates/iso/language/2023/set-2-bibliographic.jq
@@ -0,0 +1,40 @@
+# Scope expansion map
+def expand_scope:
+  if . == "I" then "individual"
+  elif . == "M" then "macrolanguage"
+  elif . == "S" then "special"
+  else . end;
+
+# Language type expansion map
+def expand_language_type:
+  if . == "L" then "living"
+  elif . == "E" then "extinct"
+  elif . == "H" then "historic"
+  elif . == "C" then "constructed"
+  elif . == "S" then "special"
+  elif . == "A" then "ancient"
+  else . end;
+
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "title": "ISO 639-2:2023 Bibliographic Language Code",
+  "description": "A three-letter bibliographic language code from ISO 639-2",
+  "$comment": "Set 2 bibliographic is a superset of Set 1 and a subset of Set 3. Bibliographic codes are based on English language names",
+  "examples": (.set_2_bibliographic | sort_by(.code) | .[0:4] | map(.code)),
+  "x-license": "https://github.com/sourcemeta/std/blob/main/LICENSE",
+  "x-links": ["https://www.iso.org/standard/74575.html"],
+  "anyOf": (
+    .set_2_bibliographic
+    | sort_by(.code)
+    | map({
+        "title": .name
+      } +
+      (if .scope then {"x-scope": (.scope | expand_scope)} else {} end) +
+      (if .language_type then {"x-language-type": (.language_type | expand_language_type)} else {} end) +
+      (if .name_french then {"x-name-french": .name_french} else {} end) +
+      (if .part1 then {"x-set-1": .part1} else {} end) +
+      {
+        "const": .code
+      })
+  )
+}
diff --git a/templates/iso/language/2023/set-2-terminologic.jq b/templates/iso/language/2023/set-2-terminologic.jq
new file mode 100644
index 00000000..ca715ace
--- /dev/null
+++ b/templates/iso/language/2023/set-2-terminologic.jq
@@ -0,0 +1,40 @@
+# Scope expansion map
+def expand_scope:
+  if . == "I" then "individual"
+  elif . == "M" then "macrolanguage"
+  elif . == "S" then "special"
+  else . end;
+
+# Language type expansion map
+def expand_language_type:
+  if . == "L" then "living"
+  elif . == "E" then "extinct"
+  elif . == "H" then "historic"
+  elif . == "C" then "constructed"
+  elif . == "S" then "special"
+  elif . == "A" then "ancient"
+  else . end;
+
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "title": "ISO 639-2:2023 Terminologic Language Code",
+  "description": "A three-letter terminologic language code from ISO 639-2",
+  "$comment": "Set 2 terminologic is a superset of Set 1 and a subset of Set 3. Terminologic codes are based on native language names. Only about 20 languages have both bibliographic and terminologic codes",
+  "examples": (.set_2_terminologic | sort_by(.code) | .[0:4] | map(.code)),
+  "x-license": "https://github.com/sourcemeta/std/blob/main/LICENSE",
+  "x-links": ["https://www.iso.org/standard/74575.html"],
+  "anyOf": (
+    .set_2_terminologic
+    | sort_by(.code)
+    | map({
+        "title": .name
+      } +
+      (if .scope then {"x-scope": (.scope | expand_scope)} else {} end) +
+      (if .language_type then {"x-language-type": (.language_type | expand_language_type)} else {} end) +
+      (if .name_french then {"x-name-french": .name_french} else {} end) +
+      (if .part1 then {"x-set-1": .part1} else {} end) +
+      {
+        "const": .code
+      })
+  )
+}
diff --git a/templates/iso/language/2023/set-3.jq b/templates/iso/language/2023/set-3.jq
new file mode 100644
index 00000000..1b2cd151
--- /dev/null
+++ b/templates/iso/language/2023/set-3.jq
@@ -0,0 +1,42 @@
+# Scope expansion map
+def expand_scope:
+  if . == "I" then "individual"
+  elif . == "M" then "macrolanguage"
+  elif . == "S" then "special"
+  else . end;
+
+# Language type expansion map
+def expand_language_type:
+  if . == "L" then "living"
+  elif . == "E" then "extinct"
+  elif . == "H" then "historic"
+  elif . == "C" then "constructed"
+  elif . == "S" then "special"
+  elif . == "A" then "ancient"
+  else . end;
+
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "title": "ISO 639-3:2023 Language Code",
+  "description": "A three-letter language code from ISO 639-3",
+  "$comment": "Set 3 is a superset of Set 1 and Set 2. It provides comprehensive coverage of individual languages, macrolanguages, and special codes",
+  "examples": (.set_3 | sort_by(.code) | .[0:4] | map(.code)),
+  "x-license": "https://github.com/sourcemeta/std/blob/main/LICENSE",
+  "x-links": ["https://www.iso.org/standard/74575.html"],
+  "anyOf": (
+    .set_3
+    | sort_by(.code)
+    | map({
+        "title": .name
+      } +
+      (if .scope then {"x-scope": (.scope | expand_scope)} else {} end) +
+      (if .language_type then {"x-language-type": (.language_type | expand_language_type)} else {} end) +
+      (if .part2b then {"x-set-2-bibliographic": .part2b} else {} end) +
+      (if .part2t then {"x-set-2-terminologic": .part2t} else {} end) +
+      (if .part1 then {"x-set-1": .part1} else {} end) +
+      (if .comment then {"$comment": .comment} else {} end) +
+      {
+        "const": .code
+      })
+  )
+}
diff --git a/templates/iso/language/2023/set-5.jq b/templates/iso/language/2023/set-5.jq
new file mode 100644
index 00000000..97ead6a9
--- /dev/null
+++ b/templates/iso/language/2023/set-5.jq
@@ -0,0 +1,20 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "title": "ISO 639-5:2023 Language Family Code",
+  "description": "A three-letter code for language families and groups from ISO 639-5",
+  "$comment": "Set 5 codes language families and groups, not individual languages. It is independent from Sets 1-3",
+  "examples": (.set_5 | sort_by(.code) | .[0:4] | map(.code)),
+  "x-license": "https://github.com/sourcemeta/std/blob/main/LICENSE",
+  "x-links": ["https://www.iso.org/standard/74575.html"],
+  "anyOf": (
+    .set_5
+    | sort_by(.code)
+    | map({
+        "title": .name
+      } +
+      (if .name_french then {"x-name-french": .name_french} else {} end) +
+      {
+        "const": .code
+      })
+  )
+}