Support experience.usc.edu STARS format: detect name via 'STARS Report for', ID via 'ID#:', + per-report link token; old format still works

redactors/pii.py

@@ -1,14 +1,17 @@
 """PII redaction pass.
 
 Detects the student-identifying fields by their template anchors (constant
-labels / formats), never by hard-coded student data:
-
-  - Student ID            (10-digit number in the page header)
-  - Roster name           ("Last, First, Middle" line under the ID header)
-  - Diploma name          (line after "Name as it will appear on your USC Diploma:")
-  - Mailing street        (after "Diploma will be mailed to:")
-  - Mailing city/state/zip (the line following the street)
+labels / formats), never by hard-coded student data. Handles both STARS
+layouts: the older "Microsoft Print To PDF" report and the newer
+experience.usc.edu ("Skia/PDF") report. Fields include:
+
+  - Student ID            ("ID#:" label, or a 10-digit number in the header)
+  - Header name           (after "STARS Report for ", experience.usc.edu)
+  - Roster name           ("Last, First, Middle" header line, Microsoft-print)
+  - Diploma name          (after "Name as it will appear on your USC Diploma:")
+  - Mailing street/zip    (the diploma "mailed to" block, Microsoft-print)
   - Sport / team          (between "Student Athlete:" and "Clock Date:")
+  - Report link           (per-report stars.usc.edu token in the print footer)
 """
 import re
 
@@ -20,8 +23,9 @@ ROSTER_RE = re.compile(r"^[A-Z][A-Za-z.'\-]+(?:,\s+[A-Za-z.'\-]+){1,3}$")
 
 TAG_MAP = {
     "Student ID": "ID", "Roster name": "NAME", "Diploma name": "NAME",
-    "Mailing street": "ADDRESS", "Mailing city/state/zip": "ADDRESS",
-    "Sport/team": "SPORT",
+    "Header name": "NAME", "Mailing street": "ADDRESS",
+    "Mailing city/state/zip": "ADDRESS", "Sport/team": "SPORT",
+    "Report link": "LINK",
 }
 
 
@@ -40,24 +44,48 @@ def _layout_lines(doc):
 
 
 def detect(doc):
-    """Return {label: value} of detected identifiers. Missing fields omitted."""
+    """Return {label: value} of detected identifiers. Missing fields omitted.
+
+    Supports two STARS layouts:
+      * "Microsoft Print To PDF"  — header has the ID then a "Last, First,
+        Middle" line; a diploma section with mailing address; sport line.
+      * experience.usc.edu ("Skia/PDF") — name follows "STARS Report for ",
+        ID follows "ID#:", plus a per-report link token in the footer; no
+        diploma/mailing-address section.
+    """
     lines = _layout_lines(doc)
+    text = "\n".join(lines)
     found = {}
 
-    id_line_idx = None
-    for i, ln in enumerate(lines[:8]):
-        m = ID_RE.search(ln)
-        if m:
-            found["Student ID"] = m.group(0)
-            id_line_idx = i
+    # --- Student ID -------------------------------------------------------
+    m = re.search(r"ID#:\s*(\d{9,10})", text)           # experience.usc.edu
+    if m:
+        found["Student ID"] = m.group(1)
+    else:
+        for ln in lines[:8]:                            # Microsoft-print header
+            mm = ID_RE.search(ln)
+            if mm:
+                found["Student ID"] = mm.group(0)
+                break
+
+    # --- Name (experience.usc.edu): "STARS Report for <First Middle Last>" -
+    m = re.search(r"STARS Report for\s+(.+)", text)
+    if m:
+        nm = re.split(r"\s{2,}|\|", m.group(1).strip())[0].strip()
+        if nm:
+            found["Header name"] = nm
+
+    # --- Roster name (Microsoft-print): "Last, First[, Middle]" in header --
+    for ln in lines[:8]:
+        cand = _first_chunk(ln)
+        if cand and ROSTER_RE.match(cand):
+            found["Roster name"] = cand
             break
 
-    if id_line_idx is not None:
-        for ln in lines[id_line_idx + 1: id_line_idx + 4]:
-            cand = _first_chunk(ln)
-            if cand and ROSTER_RE.match(cand):
-                found["Roster name"] = cand
-                break
+    # --- Per-report link token (experience.usc.edu print footer) ----------
+    m = re.search(r"https?://stars\.usc\.edu/\S+", text)
+    if m:
+        found["Report link"] = m.group(0)
 
     for i, ln in enumerate(lines):
         low = ln.lower()
@@ -134,7 +162,7 @@ def verify(doc, meta):
 
     soft = []
     tokens = set()
-    for label in ("Roster name", "Diploma name"):
+    for label in ("Roster name", "Diploma name", "Header name"):
         if label in values:
             for tok in re.split(r"[,\s]+", values[label]):
                 if len(tok) >= 4 and tok.isalpha():