ltc-code 0.2.11__tar.gz → 0.2.12__tar.gz

{ltc_code-0.2.11 → ltc_code-0.2.12}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: ltc-code
-Version: 0.2.11
+Version: 0.2.12
 Summary: Add your description here
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown

{ltc_code-0.2.11 → ltc_code-0.2.12}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ltc-code"
-version = "0.2.11"
+version = "0.2.12"
 description = "Add your description here"
 readme = "README.md"
 requires-python = ">=3.9"

ltc_code-0.2.12/src/ltc_code/nsc/naics.csv

@@ -0,0 +1,25 @@
+naics_code,sector
+11,"Agriculture, Forestry, Fishing and Hunting"
+21,"Mining, Quarrying, and Oil and Gas Extraction"
+22,Utilities
+23,Construction
+31,Manufacturing
+32,Manufacturing
+33,Manufacturing
+42,Wholesale Trade
+44,Retail Trade
+45,Retail Trade
+48,Transportation and Warehousing
+49,Transportation and Warehousing
+51,Information
+52,Finance and Insurance
+53,Real Estate and Rental and Leasing
+54,"Professional, Scientific, and Technical Services"
+55,Management of Companies and Enterprises
+56,Administrative and Support and Waste Management and Remediation Services
+61,Educational Services
+62,Health Care and Social Assistance
+71,"Arts, Entertainment, and Recreation"
+72,Accommodation and Food Services
+81,Other Services (except Public Administration)
+92,Public Administration

ltc_code-0.2.12/src/ltc_code/nsc/naics.py

@@ -0,0 +1,126 @@
+from __future__ import annotations
+
+import csv
+import re
+import zipfile
+from pathlib import Path
+from xml.etree import ElementTree as ET
+
+
+BASE_DIR = Path(__file__).resolve().parent
+RAW_DIR = BASE_DIR
+CLEAN_DIR = BASE_DIR
+OUTPUT_PATH = BASE_DIR / "naics.csv"
+
+NS = {"x": "http://schemas.openxmlformats.org/spreadsheetml/2006/main"}
+SECTOR_CODE_RE = re.compile(r"^\s*(\d{2})(?:\s*-\s*(\d{2}))?\s*$")
+LETTER_RE = re.compile(r"[A-Za-z]")
+
+
+def _shared_strings(workbook: zipfile.ZipFile) -> list[str]:
+    try:
+        root = ET.fromstring(workbook.read("xl/sharedStrings.xml"))
+    except KeyError:
+        return []
+
+    strings: list[str] = []
+    for item in root.findall("x:si", NS):
+        strings.append("".join(text.text or "" for text in item.findall(".//x:t", NS)))
+    return strings
+
+
+def _cell_value(cell: ET.Element, shared_strings: list[str]) -> str:
+    cell_type = cell.attrib.get("t")
+
+    if cell_type == "inlineStr":
+        return "".join(text.text or "" for text in cell.findall(".//x:t", NS)).strip()
+
+    value = cell.find("x:v", NS)
+    if value is None or value.text is None:
+        return ""
+
+    text = value.text.strip()
+    if cell_type == "s":
+        return shared_strings[int(text)].strip()
+    return text
+
+
+def read_first_sheet_rows(path: Path) -> list[list[str]]:
+    with zipfile.ZipFile(path) as workbook:
+        shared_strings = _shared_strings(workbook)
+        sheet = ET.fromstring(workbook.read("xl/worksheets/sheet1.xml"))
+
+    rows: list[list[str]] = []
+    for row in sheet.findall(".//x:sheetData/x:row", NS):
+        values = [
+            _cell_value(cell, shared_strings)
+            for cell in row.findall("x:c", NS)
+        ]
+        rows.append(values)
+    return rows
+
+
+def expand_sector_code(code: str) -> list[str]:
+    match = SECTOR_CODE_RE.fullmatch(code)
+    if match is None:
+        return []
+
+    start = int(match.group(1))
+    end = int(match.group(2) or match.group(1))
+    return [f"{sector:02d}" for sector in range(start, end + 1)]
+
+
+def clean_naics_rows(rows: list[list[str]]) -> list[dict[str, str]]:
+    cleaned: list[dict[str, str]] = []
+    seen: set[tuple[str, str]] = set()
+
+    for row in rows:
+        values = [value.strip() for value in row if value.strip()]
+        if len(values) < 2:
+            continue
+
+        for index, value in enumerate(values[:-1]):
+            sector_codes = expand_sector_code(value)
+            if not sector_codes:
+                continue
+
+            sector_name = values[index + 1].strip()
+            if (
+                not sector_name
+                or not LETTER_RE.search(sector_name)
+                or sector_name.lower() in {"sector", "title", "description"}
+            ):
+                continue
+
+            for sector_code in sector_codes:
+                record = (sector_code, sector_name)
+                if record in seen:
+                    continue
+                cleaned.append({"naics_code": sector_code, "sector": sector_name})
+                seen.add(record)
+            break
+
+    return cleaned
+
+
+def main() -> None:
+    source_files = sorted(RAW_DIR.glob("*.xlsx"))
+    if not source_files:
+        raise FileNotFoundError(f"No .xlsx files found in {RAW_DIR}")
+
+    rows = read_first_sheet_rows(source_files[0])
+    cleaned = clean_naics_rows(rows)
+    if not cleaned:
+        raise ValueError(f"No sector-level NAICS rows found in {source_files[0]}")
+
+    CLEAN_DIR.mkdir(parents=True, exist_ok=True)
+    with OUTPUT_PATH.open("w", newline="", encoding="utf-8") as output_file:
+        writer = csv.DictWriter(output_file, fieldnames=["naics_code", "sector"])
+        writer.writeheader()
+        writer.writerows(cleaned)
+
+    print(f"Wrote {len(cleaned)} rows to {OUTPUT_PATH}")
+
+
+if __name__ == "__main__":
+    main()