"""Minimal stdlib-only .xlsx reader (shared strings, inline strings, numbers). Only reads cell values; formulas are not evaluated (cached values are used). The workbook is treated as untrusted data: it is parsed with xml.etree only. """ import re import zipfile import xml.etree.ElementTree as ET NS = {"m": "http://schemas.openxmlformats.org/spreadsheetml/2006/main"} REL_NS = "http://schemas.openxmlformats.org/officeDocument/2006/relationships" PKG_REL_NS = "http://schemas.openxmlformats.org/package/2006/relationships" def _col_index(ref: str) -> int: m = re.match(r"([A-Z]+)", ref) n = 0 for ch in m.group(1): n = n * 26 + (ord(ch) - 64) return n - 1 def _text(el) -> str: # concatenates all descendants (handles rich text runs) return "".join(t.text or "" for t in el.iter("{%s}t" % NS["m"])) class Workbook: def __init__(self, path: str): self.zf = zipfile.ZipFile(path) self.shared = [] if "xl/sharedStrings.xml" in self.zf.namelist(): root = ET.fromstring(self.zf.read("xl/sharedStrings.xml")) for si in root.findall("m:si", NS): self.shared.append(_text(si)) wb = ET.fromstring(self.zf.read("xl/workbook.xml")) rels = ET.fromstring(self.zf.read("xl/_rels/workbook.xml.rels")) rid_to_target = {r.get("Id"): r.get("Target") for r in rels.findall("{%s}Relationship" % PKG_REL_NS)} self.sheets = {} for s in wb.find("m:sheets", NS).findall("m:sheet", NS): rid = s.get("{%s}id" % REL_NS) target = rid_to_target[rid] if target.startswith("/"): target = target[1:] elif not target.startswith("xl/"): target = "xl/" + target self.sheets[s.get("name")] = target def rows(self, sheet_name: str): """Yields lists of cell values (str, float, or None) for each row, dense by column.""" data = self.zf.read(self.sheets[sheet_name]) root = ET.fromstring(data) sd = root.find("m:sheetData", NS) for row in sd.findall("m:row", NS): cells = {} for c in row.findall("m:c", NS): ref = c.get("r") t = c.get("t") v = c.find("m:v", NS) val = None if t == "s" and v is not None: val = self.shared[int(v.text)] elif t == "inlineStr": is_ = c.find("m:is", NS) val = _text(is_) if is_ is not None else None elif t == "str": val = v.text if v is not None else None elif t == "b": val = (v.text == "1") if v is not None else None elif v is not None and v.text is not None: try: val = float(v.text) except ValueError: val = v.text cells[_col_index(ref)] = val if not cells: yield [] continue width = max(cells) + 1 yield [cells.get(i) for i in range(width)]