z230
This commit is contained in:
@@ -1,40 +0,0 @@
|
||||
# sipiq_import_v1.2 — import SIPIQ odpovědí (folder workflow + provenance)
|
||||
|
||||
**Verze:** 1.2 · **Datum:** 2026-06-17 · **Studie:** 77242113UCO3002 (ICONIC / DAWN)
|
||||
|
||||
## Změny
|
||||
- **v1.2:** ke každé odpovědi `source_exported_at` = **datum/čas reportu podle filesystému**
|
||||
(mtime CSV souboru). Mimo content-hash → nezpůsobuje zbytečné UPDATE; backfilluje se i na
|
||||
"beze změny" cestě. v1.1 → `Feasibility\TRASH`.
|
||||
- **v1.1:** FOLDER workflow (`--folder`) — sebere *.csv, delta import, přesun do `Zpracováno`.
|
||||
|
||||
## Kolekce
|
||||
- `sipiq_questions` — slovník dotazníku (rekonstrukce SIPIQ jako v PDF).
|
||||
- `sipiq_responses` — 1 dok = 1 odpověď (`_id`=ResponseId), ploché `answers{}`,
|
||||
soft-link `investigator_oid`, `source_file` + `source_exported_at`, delta + `history[]`.
|
||||
|
||||
Zdroj = Qualtrics **CSV** (ř.1 Qcode, ř.2 text otázky, ř.3 ImportId=QID). Export labels,
|
||||
desetinná tečka, recode unanswered vypnuté.
|
||||
|
||||
## Delta (přepíše JEN změněná data)
|
||||
nová→INSERT; beze změn (shodný `content_sha256`)→jen `last_seen_at` + `source_file` + `source_exported_at`;
|
||||
změna→`$set` jen změněných polí + `$push` do `history[]`.
|
||||
|
||||
## Soft-link na investigators (nedestruktivní)
|
||||
pi_email → email/email2 (lower), pak recipient_email, fallback příjmení (bez diakritiky)+země.
|
||||
|
||||
## Použití
|
||||
```
|
||||
.venv\Scripts\python.exe Feasibility\sipiq_import_v1.2.py --dry-run # folder režim, default složka
|
||||
.venv\Scripts\python.exe Feasibility\sipiq_import_v1.2.py --apply
|
||||
.venv\Scripts\python.exe Feasibility\sipiq_import_v1.2.py --folder "<cesta>" --apply
|
||||
.venv\Scripts\python.exe Feasibility\sipiq_import_v1.2.py --csv "<cesta.csv>" --apply # jediný soubor, NEpřesouvá
|
||||
```
|
||||
Default složka `…\77242113UCO2001\ImportSIPIQcompled`; přesun do `Zpracováno` jen v `--apply` + folder režimu.
|
||||
`--scope czsk` (default) / `all`. Default = dry-run.
|
||||
|
||||
## Workflow
|
||||
Uživatel pokládá kompletní SIPIQ reporty (Qualtrics CSV, název
|
||||
`ICONIC+Phase+3b+UC+Study+(77242113UCO3002)_SipIQ_V1_13MAY2026_<datum>_<čas>.csv`) do
|
||||
`ImportSIPIQcompled\`. Po `--apply` se naimportují (delta) a přesunou do `Zpracováno\`.
|
||||
`source_exported_at` se bere z mtime souboru (datum/čas reportu dle filesystému).
|
||||
@@ -1,489 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
sipiq_import_v1.2.py
|
||||
====================
|
||||
Verze: 1.2
|
||||
Datum: 2026-06-17
|
||||
Autor: Claude Code (pro MUDr. Vladimíra Buzalku)
|
||||
|
||||
Změny proti v1.1
|
||||
----------------
|
||||
- PROVENANCE: ke každé odpovědi se ukládá `source_exported_at` = datum/čas reportu
|
||||
podle FILESYSTÉMU (mtime CSV souboru). Mimo content-hash → nezpůsobuje zbytečné
|
||||
UPDATE; backfilluje se i na "beze změny" cestě. Stará v1.1 ponechána v TRASH.
|
||||
|
||||
Změny proti v1.0
|
||||
----------------
|
||||
- FOLDER WORKFLOW (v1.1): režim --folder sebere *.csv ve složce, naimportuje (delta)
|
||||
a přesune do podsložky `Zpracováno`. Default složka =
|
||||
U:\\PythonProject\\Janssen\\Feasibility\\77242113UCO2001\\ImportSIPIQcompled.
|
||||
|
||||
Popis
|
||||
-----
|
||||
Import SIPIQ odpovědí (Qualtrics CSV export, studie 77242113UCO3002 / ICONIC DAWN)
|
||||
do MongoDB db `feasibility`. Dvě kolekce:
|
||||
* sipiq_questions – slovník dotazníku (1 dok = 1 logická otázka).
|
||||
* sipiq_responses – 1 dok = 1 odpověď (_id = Qualtrics ResponseId), ploché answers{},
|
||||
soft-link investigator_oid, delta bookkeeping + history[].
|
||||
|
||||
DELTA import (přepíše JEN změněná data): nová->insert; beze změn->jen last_seen_at;
|
||||
změna->$set jen změněných polí + push do history[].
|
||||
|
||||
Použití
|
||||
-------
|
||||
python sipiq_import_v1.2.py --dry-run # folder režim, default složka
|
||||
python sipiq_import_v1.2.py --apply
|
||||
python sipiq_import_v1.2.py --folder "<cesta>" --apply
|
||||
python sipiq_import_v1.2.py --csv "<cesta.csv>" --apply # jediný soubor (NEpřesouvá)
|
||||
|
||||
Závislosti: pymongo (.venv). Mongo 192.168.1.76:27017, bez auth.
|
||||
"""
|
||||
import argparse
|
||||
import csv
|
||||
import glob
|
||||
import hashlib
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import shutil
|
||||
import sys
|
||||
import unicodedata
|
||||
from datetime import datetime, timezone
|
||||
|
||||
try:
|
||||
from pymongo import MongoClient
|
||||
except ImportError:
|
||||
print("CHYBA: pymongo není nainstalován v aktuálním pythonu.", file=sys.stderr)
|
||||
raise
|
||||
|
||||
MONGO_URI = "mongodb://192.168.1.76:27017"
|
||||
DB_NAME = "feasibility"
|
||||
COL_Q = "sipiq_questions"
|
||||
COL_R = "sipiq_responses"
|
||||
DEFAULT_FOLDER = r"U:\PythonProject\Janssen\Feasibility\77242113UCO2001\ImportSIPIQcompled"
|
||||
PROCESSED_SUBDIR = "Zpracováno"
|
||||
|
||||
META_COLS = {
|
||||
"StartDate", "EndDate", "Status", "IPAddress", "Progress", "Duration (in seconds)",
|
||||
"Finished", "RecordedDate", "ResponseId", "RecipientLastName", "RecipientFirstName",
|
||||
"RecipientEmail", "ExternalReference", "LocationLatitude", "LocationLongitude",
|
||||
"DistributionChannel", "UserLanguage",
|
||||
}
|
||||
|
||||
PROMOTE = [
|
||||
"site_name", "site_address", "site_city", "site_state", "site_postcode", "site_country",
|
||||
"pi_first_name", "pi_last_name", "pi_phone", "pi_email",
|
||||
"sdl_site_id", "fire_site_id", "fire_investigator_id", "mailinglist_id",
|
||||
"survey_generated_by", "Date", "Time",
|
||||
]
|
||||
|
||||
SECTION_BY_QNUM = {}
|
||||
def _sec(rng, name):
|
||||
for n in rng:
|
||||
SECTION_BY_QNUM[n] = name
|
||||
_sec([2], "J&J Internal Assessment")
|
||||
_sec([6, 7, 8, 9, 10, 11, 12, 13], "Contact Information")
|
||||
_sec(range(14, 22), "Confidentiality Statement")
|
||||
_sec([25, 26, 27], "Interest")
|
||||
_sec([29, 30, 31, 32, 33, 34], "Protocol Requirements")
|
||||
_sec([36, 37, 38], "Enrollment")
|
||||
_sec([40, 41, 42, 43], "Patient Demographics Overview")
|
||||
_sec([45, 46, 47, 48, 49], "Site Overview")
|
||||
_sec([51], "Operational Considerations")
|
||||
_sec([53, 54], "Comments")
|
||||
_sec([57, 58, 59, 60, 61], "Patient Population")
|
||||
_sec([63, 64, 65, 66, 67], "Site Experience and Staffing")
|
||||
_sec([69], "Equipment and Facility Requirements")
|
||||
_sec([71, 72, 73, 74, 75], "Institutional Review Board, Ethics Committee, and Contracts")
|
||||
|
||||
STEM_OVERRIDE = {
|
||||
"Q31": "At your site, at what line(s) of treatment do you most commonly prescribe "
|
||||
"vedolizumab for patients with moderately to severely active ulcerative colitis?",
|
||||
"Q63": "Do you or your site staff have experience in performing the following types of "
|
||||
"study assessments/procedures?",
|
||||
"Q64": "The following personnel are required to run the study. "
|
||||
"Will your site have the following available?",
|
||||
"Q69": "The following equipment and facilities are required to run the studies. "
|
||||
"Are these available at your site?",
|
||||
}
|
||||
|
||||
|
||||
def now_iso():
|
||||
return datetime.now(timezone.utc).astimezone().isoformat(timespec="seconds")
|
||||
|
||||
|
||||
def file_mtime_iso(path):
|
||||
return datetime.fromtimestamp(os.path.getmtime(path)).astimezone().isoformat(timespec="seconds")
|
||||
|
||||
|
||||
def strip_accents(s):
|
||||
if not s:
|
||||
return ""
|
||||
return "".join(c for c in unicodedata.normalize("NFKD", s) if not unicodedata.combining(c))
|
||||
|
||||
|
||||
def norm_name(s):
|
||||
return re.sub(r"\s+", " ", strip_accents(s or "").lower()).strip()
|
||||
|
||||
|
||||
def sanitize_key(qcode):
|
||||
return qcode.replace("#", "_").replace(".", "_")
|
||||
|
||||
|
||||
def qnum(qcode):
|
||||
m = re.match(r"Q(\d+)", qcode)
|
||||
return int(m.group(1)) if m else None
|
||||
|
||||
|
||||
def qbase(qcode):
|
||||
m = re.match(r"(Q\d+)", qcode)
|
||||
return m.group(1) if m else qcode
|
||||
|
||||
|
||||
def import_id(h3_cell):
|
||||
try:
|
||||
return json.loads(h3_cell).get("ImportId", "")
|
||||
except Exception:
|
||||
return h3_cell
|
||||
|
||||
|
||||
def split_text(text):
|
||||
parts = [p.strip() for p in re.split(r"\s+-\s+", text)]
|
||||
stem = parts[0]
|
||||
if len(parts) == 1:
|
||||
return stem, None
|
||||
label_parts = [p for p in parts[1:] if p.lower() != "selected choice"]
|
||||
label_parts = [p for p in label_parts if not re.fullmatch(r"Q\d+#\d+", p)]
|
||||
return stem, (" - ".join(label_parts) if label_parts else None)
|
||||
|
||||
|
||||
def detect_type(qcode, observed):
|
||||
has_hash = "#" in qcode
|
||||
vals = [v for v in observed if v]
|
||||
yesno = vals and all(v in ("Yes", "No") for v in vals)
|
||||
numeric = vals and all(re.fullmatch(r"-?\d+(\.\d+)?", v) for v in vals)
|
||||
if has_hash and yesno:
|
||||
return "matrix_yesno"
|
||||
if has_hash and numeric:
|
||||
return "matrix_percent"
|
||||
if has_hash:
|
||||
return "matrix"
|
||||
if numeric:
|
||||
return "numeric"
|
||||
if yesno:
|
||||
return "yesno"
|
||||
return "single_or_text"
|
||||
|
||||
|
||||
def load_csv(path):
|
||||
with open(path, encoding="utf-8-sig", newline="") as fh:
|
||||
rows = list(csv.reader(fh))
|
||||
h1, h2, h3 = rows[0], rows[1], rows[2]
|
||||
data = rows[3:]
|
||||
cols = [{"i": i, "code": c, "text": t, "qid": import_id(j)}
|
||||
for i, (c, t, j) in enumerate(zip(h1, h2, h3))]
|
||||
return cols, data
|
||||
|
||||
|
||||
def col_getter(cols, data):
|
||||
idx = {c["code"]: c["i"] for c in cols}
|
||||
def get(row, code):
|
||||
i = idx.get(code)
|
||||
return (row[i].strip() if i is not None and i < len(row) else "")
|
||||
return get, idx
|
||||
|
||||
|
||||
def is_question_col(code):
|
||||
return bool(re.match(r"Q\d", code))
|
||||
|
||||
|
||||
def build_questions(cols, data):
|
||||
qcols = [c for c in cols if is_question_col(c["code"])]
|
||||
observed = {c["code"]: set() for c in qcols}
|
||||
for row in data:
|
||||
for c in qcols:
|
||||
v = (row[c["i"]].strip() if c["i"] < len(row) else "")
|
||||
if v:
|
||||
observed[c["code"]].add(v)
|
||||
groups, order_seen = {}, []
|
||||
for c in qcols:
|
||||
base = qbase(c["code"])
|
||||
if base not in groups:
|
||||
groups[base] = {"_id": base, "order": c["i"], "qnum": qnum(c["code"]),
|
||||
"section": SECTION_BY_QNUM.get(qnum(c["code"]), "Other"),
|
||||
"qids": [], "text": split_text(c["text"])[0],
|
||||
"items": [], "_obs": set(), "_types": []}
|
||||
order_seen.append(base)
|
||||
g = groups[base]
|
||||
bq = re.match(r"(QID\d+)", c["qid"] or "")
|
||||
if bq and bq.group(1) not in g["qids"]:
|
||||
g["qids"].append(bq.group(1))
|
||||
_, label = split_text(c["text"])
|
||||
item = {"key": sanitize_key(c["code"]), "qcode": c["code"], "qid": c["qid"]}
|
||||
if label:
|
||||
item["label"] = label
|
||||
g["items"].append(item)
|
||||
g["_obs"] |= observed[c["code"]]
|
||||
g["_types"].append(detect_type(c["code"], observed[c["code"]]))
|
||||
out = []
|
||||
for n, base in enumerate(order_seen):
|
||||
g = groups[base]
|
||||
obs = sorted(g.pop("_obs"))
|
||||
types = g.pop("_types")
|
||||
gtype = max(set(types), key=types.count) if types else "single_or_text"
|
||||
g["type"] = gtype
|
||||
if gtype in ("yesno", "matrix_yesno"):
|
||||
g["options"] = ["Yes", "No"]
|
||||
elif gtype == "single_or_text" and obs and len(obs) <= 12:
|
||||
g["options"] = obs
|
||||
else:
|
||||
g["options"] = []
|
||||
if base in STEM_OVERRIDE:
|
||||
g["text"] = STEM_OVERRIDE[base]
|
||||
g["order"] = n
|
||||
if len(g["items"]) == 1 and "label" not in g["items"][0]:
|
||||
g["items"] = []
|
||||
out.append(g)
|
||||
return out
|
||||
|
||||
|
||||
def build_response(cols, get, row, source_file):
|
||||
rid = get(row, "ResponseId")
|
||||
answers = {}
|
||||
for c in cols:
|
||||
if is_question_col(c["code"]):
|
||||
v = (row[c["i"]].strip() if c["i"] < len(row) else "")
|
||||
if v:
|
||||
answers[sanitize_key(c["code"])] = v
|
||||
meta = {
|
||||
"start_date": get(row, "StartDate") or None,
|
||||
"end_date": get(row, "EndDate") or None,
|
||||
"recorded_date": get(row, "RecordedDate") or None,
|
||||
"status": get(row, "Status") or None,
|
||||
"progress": int(get(row, "Progress")) if get(row, "Progress").isdigit() else (get(row, "Progress") or None),
|
||||
"finished": get(row, "Finished") in ("True", "1", "TRUE"),
|
||||
"duration_sec": int(get(row, "Duration (in seconds)")) if get(row, "Duration (in seconds)").isdigit() else None,
|
||||
"user_language": get(row, "UserLanguage") or None,
|
||||
"distribution_channel": get(row, "DistributionChannel") or None,
|
||||
"ip_address": get(row, "IPAddress") or None,
|
||||
"location_lat": get(row, "LocationLatitude") or None,
|
||||
"location_lng": get(row, "LocationLongitude") or None,
|
||||
"survey_date": get(row, "Date") or None,
|
||||
"survey_time": get(row, "Time") or None,
|
||||
}
|
||||
doc = {
|
||||
"_id": rid, "study": "77242113UCO3002",
|
||||
"site_country": get(row, "site_country") or None,
|
||||
"site_name": get(row, "site_name") or None,
|
||||
"site_city": get(row, "site_city") or None,
|
||||
"site_state": get(row, "site_state") or None,
|
||||
"site_postcode": get(row, "site_postcode") or None,
|
||||
"site_address": get(row, "site_address") or None,
|
||||
"pi_first_name": get(row, "pi_first_name") or None,
|
||||
"pi_last_name": get(row, "pi_last_name") or None,
|
||||
"pi_email": (get(row, "pi_email") or "").lower() or None,
|
||||
"pi_phone": get(row, "pi_phone") or None,
|
||||
"sdl_site_id": get(row, "sdl_site_id") or None,
|
||||
"fire_site_id": get(row, "fire_site_id") or None,
|
||||
"fire_investigator_id": get(row, "fire_investigator_id") or None,
|
||||
"mailinglist_id": get(row, "mailinglist_id") or None,
|
||||
"survey_generated_by": get(row, "survey_generated_by") or None,
|
||||
"recipient_email": (get(row, "RecipientEmail") or "").lower() or None,
|
||||
"recipient_last_name": get(row, "RecipientLastName") or None,
|
||||
"recipient_first_name": get(row, "RecipientFirstName") or None,
|
||||
"meta": meta,
|
||||
"is_full_sipiq": any(k.startswith(("Q57", "Q58", "Q59", "Q63", "Q66", "Q71")) for k in answers),
|
||||
"interested": answers.get("Q25"),
|
||||
"answers": answers,
|
||||
"investigator_oid": None, "investigator_match": None,
|
||||
"source_file": source_file,
|
||||
}
|
||||
return doc
|
||||
|
||||
|
||||
def content_hash(doc):
|
||||
payload = {k: doc[k] for k in doc if k not in
|
||||
("content_sha256", "first_imported_at", "last_seen_at", "last_updated_at",
|
||||
"history", "investigator_oid", "investigator_match", "source_file",
|
||||
"source_exported_at")}
|
||||
return hashlib.sha256(json.dumps(payload, sort_keys=True, ensure_ascii=False,
|
||||
default=str).encode("utf-8")).hexdigest()
|
||||
|
||||
|
||||
def load_investigators(db):
|
||||
inv = list(db.investigators.find(
|
||||
{"zeme": {"$in": ["Czech Republic", "Slovakia"]}},
|
||||
{"prijmeni": 1, "jmeno": 1, "email": 1, "email2": 1, "zeme": 1, "KROK": 1}))
|
||||
by_email, by_name = {}, {}
|
||||
for d in inv:
|
||||
for ef in ("email", "email2"):
|
||||
e = (d.get(ef) or "").lower().strip()
|
||||
if e:
|
||||
by_email.setdefault(e, d)
|
||||
nm = norm_name(d.get("prijmeni"))
|
||||
if nm:
|
||||
by_name.setdefault((nm, d.get("zeme")), []).append(d)
|
||||
return inv, by_email, by_name
|
||||
|
||||
|
||||
def soft_link(doc, by_email, by_name):
|
||||
e = (doc.get("pi_email") or "").lower().strip()
|
||||
if e and e in by_email:
|
||||
d = by_email[e]; return d["_id"], f"email:{e}", d
|
||||
e2 = (doc.get("recipient_email") or "").lower().strip()
|
||||
if e2 and e2 in by_email:
|
||||
d = by_email[e2]; return d["_id"], f"recipient_email:{e2}", d
|
||||
nm = norm_name(doc.get("pi_last_name"))
|
||||
cand = by_name.get((nm, doc.get("site_country")), [])
|
||||
if len(cand) == 1:
|
||||
return cand[0]["_id"], f"prijmeni:{nm}", cand[0]
|
||||
if len(cand) > 1:
|
||||
return None, f"prijmeni_ambiguous:{nm}({len(cand)})", None
|
||||
return None, "NENALEZENO", None
|
||||
|
||||
|
||||
def diff_docs(old, new):
|
||||
changes = []
|
||||
def walk(prefix, o, n):
|
||||
for k in sorted(set((o or {}).keys()) | set((n or {}).keys())):
|
||||
ov, nv = (o or {}).get(k), (n or {}).get(k)
|
||||
if isinstance(ov, dict) or isinstance(nv, dict):
|
||||
walk(f"{prefix}{k}.", ov or {}, nv or {})
|
||||
elif ov != nv:
|
||||
changes.append({"key": f"{prefix}{k}", "old": ov, "new": nv})
|
||||
for field in ("answers", "meta"):
|
||||
walk(f"{field}.", old.get(field, {}), new.get(field, {}))
|
||||
for k in ("site_name", "pi_email", "pi_last_name", "interested", "is_full_sipiq"):
|
||||
if old.get(k) != new.get(k):
|
||||
changes.append({"key": k, "old": old.get(k), "new": new.get(k)})
|
||||
return changes
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
def process_file(db, csv_path, scope, dry, by_email, by_name):
|
||||
source_file = os.path.basename(csv_path)
|
||||
exported_at = file_mtime_iso(csv_path) # datum/čas reportu dle filesystému (mtime)
|
||||
cols, data = load_csv(csv_path)
|
||||
get, _ = col_getter(cols, data)
|
||||
if scope == "czsk":
|
||||
data = [r for r in data if get(r, "site_country") in ("Czech Republic", "Slovakia")]
|
||||
print(f"\n########## {source_file} (rozsah={scope}, odpovědí={len(data)}, export={exported_at}) ##########")
|
||||
|
||||
cols_all, data_all = load_csv(csv_path)
|
||||
questions = build_questions(cols_all, data_all)
|
||||
|
||||
docs, link_rows = [], []
|
||||
for r in data:
|
||||
doc = build_response(cols, get, r, source_file)
|
||||
oid, how, matched = soft_link(doc, by_email, by_name)
|
||||
doc["investigator_oid"] = oid
|
||||
doc["investigator_match"] = how
|
||||
doc["source_exported_at"] = exported_at
|
||||
doc["content_sha256"] = content_hash(doc)
|
||||
docs.append(doc)
|
||||
link_rows.append((doc, how, matched))
|
||||
|
||||
existing = {d["_id"]: d for d in db[COL_R].find({}, {"content_sha256": 1})}
|
||||
to_insert = [d for d in docs if d["_id"] not in existing]
|
||||
to_update = [d for d in docs if d["_id"] in existing and existing[d["_id"]].get("content_sha256") != d["content_sha256"]]
|
||||
unchanged = [d for d in docs if d["_id"] in existing and existing[d["_id"]].get("content_sha256") == d["content_sha256"]]
|
||||
|
||||
mk7 = mko = un = 0
|
||||
for doc, how, m in link_rows:
|
||||
krok = (m or {}).get("KROK", "")
|
||||
if m and str(krok).startswith("7"): mk7 += 1
|
||||
elif m: mko += 1
|
||||
else: un += 1
|
||||
print(f" slovník: {len(questions)} otázek | soft-link: KROK7={mk7}, jiný={mko}, nenapárováno={un}")
|
||||
print(f" delta: INSERT={len(to_insert)}, UPDATE={len(to_update)}, beze změny={len(unchanged)}")
|
||||
if un:
|
||||
for doc, how, m in link_rows:
|
||||
if not m:
|
||||
print(f" ✗ NENAPÁROVÁNO: {doc.get('pi_last_name')} / {doc.get('pi_email')} ({how})")
|
||||
|
||||
if dry:
|
||||
print(" [DRY-RUN] nezapsáno")
|
||||
return {"insert": 0, "update": 0, "unchanged": 0, "wrote": False}
|
||||
|
||||
for q in questions:
|
||||
db[COL_Q].replace_one({"_id": q["_id"]}, q, upsert=True)
|
||||
ts = now_iso()
|
||||
ni = nu = ns = 0
|
||||
for d in docs:
|
||||
cur = db[COL_R].find_one({"_id": d["_id"]})
|
||||
if cur is None:
|
||||
d.update({"first_imported_at": ts, "last_seen_at": ts, "last_updated_at": ts, "history": []})
|
||||
db[COL_R].insert_one(d); ni += 1
|
||||
elif cur.get("content_sha256") != d["content_sha256"]:
|
||||
changes = diff_docs(cur, d)
|
||||
db[COL_R].update_one({"_id": d["_id"]}, {
|
||||
"$set": {**{k: d[k] for k in d if k != "_id"}, "last_seen_at": ts, "last_updated_at": ts},
|
||||
"$push": {"history": {"changed_at": ts, "source_file": source_file, "changes": changes}}})
|
||||
nu += 1
|
||||
else:
|
||||
db[COL_R].update_one({"_id": d["_id"]}, {"$set": {
|
||||
"last_seen_at": ts, "source_file": source_file, "source_exported_at": d["source_exported_at"]}})
|
||||
ns += 1
|
||||
print(f" [APPLY] questions upsert={len(questions)} | responses insert={ni}, update={nu}, beze změny={ns}")
|
||||
return {"insert": ni, "update": nu, "unchanged": ns, "wrote": True}
|
||||
|
||||
|
||||
def move_to_processed(csv_path, folder):
|
||||
dest_dir = os.path.join(folder, PROCESSED_SUBDIR)
|
||||
os.makedirs(dest_dir, exist_ok=True)
|
||||
base = os.path.basename(csv_path)
|
||||
dest = os.path.join(dest_dir, base)
|
||||
if os.path.exists(dest):
|
||||
stem, ext = os.path.splitext(base)
|
||||
n = 1
|
||||
while os.path.exists(os.path.join(dest_dir, f"{stem}_{n}{ext}")):
|
||||
n += 1
|
||||
dest = os.path.join(dest_dir, f"{stem}_{n}{ext}")
|
||||
shutil.move(csv_path, dest)
|
||||
print(f" -> přesunuto do {PROCESSED_SUBDIR}\\{os.path.basename(dest)}")
|
||||
|
||||
|
||||
def main():
|
||||
ap = argparse.ArgumentParser()
|
||||
ap.add_argument("--csv", help="jediný soubor (NEpřesouvá)")
|
||||
ap.add_argument("--folder", default=DEFAULT_FOLDER, help="složka se SIPIQ CSV (přesune do Zpracováno)")
|
||||
ap.add_argument("--scope", choices=["czsk", "all"], default="czsk")
|
||||
ap.add_argument("--apply", action="store_true")
|
||||
ap.add_argument("--dry-run", action="store_true")
|
||||
args = ap.parse_args()
|
||||
dry = not args.apply
|
||||
|
||||
if args.csv:
|
||||
files, move_mode, folder = [args.csv], False, None
|
||||
else:
|
||||
folder = args.folder
|
||||
files = sorted(glob.glob(os.path.join(folder, "*.csv")))
|
||||
move_mode = True
|
||||
print(f"Složka: {folder}\nNalezeno CSV ke zpracování: {len(files)}")
|
||||
if not files:
|
||||
print("Nic ke zpracování (žádné *.csv).")
|
||||
return
|
||||
|
||||
client = MongoClient(MONGO_URI, serverSelectionTimeoutMS=8000)
|
||||
db = client[DB_NAME]
|
||||
client.admin.command("ping")
|
||||
inv, by_email, by_name = load_investigators(db)
|
||||
print(f"Investigatorů CZ+SK v DB: {len(inv)}")
|
||||
|
||||
total = {"insert": 0, "update": 0, "unchanged": 0}
|
||||
for f in files:
|
||||
res = process_file(db, f, args.scope, dry, by_email, by_name)
|
||||
for k in total:
|
||||
total[k] += res[k]
|
||||
if move_mode and res["wrote"]:
|
||||
move_to_processed(f, folder)
|
||||
|
||||
print(f"\n=== CELKEM: insert={total['insert']}, update={total['update']}, beze změny={total['unchanged']} ===")
|
||||
if dry:
|
||||
print("[DRY-RUN] Nic se nezapsalo ani nepřesunulo. Ostrý běh: --apply")
|
||||
client.close()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -144,7 +144,9 @@ def main():
|
||||
f'{body}</body></html>')
|
||||
msg.set_content(html, subtype="html", charset="utf-8", cte="base64")
|
||||
os.makedirs(OUT_DIR, exist_ok=True)
|
||||
fn = f"pripominka_sipiq_{ascii_slug(d['prijmeni'])}_18JUN2026.eml"
|
||||
_t = date.today()
|
||||
_dd = _t.strftime("%d") + ["JAN","FEB","MAR","APR","MAY","JUN","JUL","AUG","SEP","OCT","NOV","DEC"][_t.month-1] + _t.strftime("%Y")
|
||||
fn = f"pripominka_sipiq_{ascii_slug(d['prijmeni'])}_{_dd}.eml"
|
||||
with open(os.path.join(OUT_DIR, fn), "wb") as fh:
|
||||
fh.write(bytes(msg))
|
||||
done.append(fn)
|
||||
|
||||
@@ -1,38 +0,0 @@
|
||||
# store_cda_seaweed_v1.0.py
|
||||
|
||||
**Verze:** 1.0 · **Datum:** 2026-06-17
|
||||
|
||||
## Účel
|
||||
Uloží podepsané CDA (PDF) z e-mailů asistentek (CTA) do Mongo
|
||||
`feasibility.investigators` do pole `cda.*` a posune lékaře na
|
||||
`KROK "5 - CDA podepsano"`.
|
||||
|
||||
Na rozdíl od `store_cda_batch` (stahuje `.msg` přes SFTP z Toweru a tahá přílohu
|
||||
přes `extract_msg`) tahle verze stahuje PDF **přímo ze SeaweedFS** přes
|
||||
`seaweed_url`, který parser ukládá k příloze v `emaily."vbuzalka@its.jnj.com"`
|
||||
(`attachments[].seaweed_url` + `sha256`). Jednodušší, bez SFTP.
|
||||
|
||||
## Jak to funguje
|
||||
- `MAPPING` = explicitní párování `investigator _id → (seaweed_url, filename, sha256, size, source_msg_id)`.
|
||||
- Pro každý záznam: stáhne PDF (urllib), ověří **SHA256 + velikost + PDF hlavičku**,
|
||||
base64-zakóduje a uloží do `cda`:
|
||||
`data_base64, data_sha256, data_filename, data_mime, data_size, data_stored_at,
|
||||
data_source_msg` + metadata `stav="podepsano", soubor, zdroj`.
|
||||
- Nastaví `KROK = "5 - CDA podepsano"` a předřadí řádek do `STATUS`.
|
||||
- `_id` se konvertuje na `ObjectId` (čisté pymongo nekonvertuje string→ObjectId samo).
|
||||
|
||||
## Použití
|
||||
```
|
||||
.venv\Scripts\python.exe Feasibility\store_cda_seaweed_v1.0.py # dry-run (ověří stažení+SHA, nezapisuje)
|
||||
.venv\Scripts\python.exe Feasibility\store_cda_seaweed_v1.0.py --apply # zapíše do Mongo
|
||||
```
|
||||
|
||||
## Běh 17JUN2026 (--apply)
|
||||
Uloženo 5/5 (všechny SHA256 OK), KROK 4 → 5:
|
||||
Závada Filip, Bruncák Michal (FNsP B. Bystrica), Machytka Evžen (Asclepiades),
|
||||
Pumprla Jiří (PreventaMed), Zapotocká Júlia (PAV-MED).
|
||||
GASTROMART/Molnár přeskočen (už KROK 6, CDA dříve uloženo).
|
||||
|
||||
## Závislosti
|
||||
`pymongo`, `bson` (+ stdlib). SeaweedFS volume server `192.168.1.50:8888`.
|
||||
Mongo `192.168.1.76:27017`.
|
||||
@@ -1,126 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
# =============================================================================
|
||||
# Nazev: store_cda_seaweed_v1.0.py
|
||||
# Verze: 1.0
|
||||
# Datum: 2026-06-17
|
||||
# Popis: Ulozi podepsane CDA (PDF) z e-mailu asistentek do Mongo
|
||||
# feasibility.investigators do pole cda.* a posune lekare na
|
||||
# KROK "5 - CDA podepsano". PDF se stahuji primo ze SeaweedFS
|
||||
# (seaweed_url z attachments v emaily."vbuzalka@its.jnj.com"),
|
||||
# overuje se SHA256 proti metadatum z Mongo.
|
||||
# Pouziti: python store_cda_seaweed_v1.0.py (dry-run / nahled)
|
||||
# python store_cda_seaweed_v1.0.py --apply (zapise do Mongo)
|
||||
# Pozn.: MAPPING nize = explicitni parovani investigator -> CDA priloha.
|
||||
# Jen stdlib + pymongo. SeaweedFS host 192.168.1.50:8888.
|
||||
# =============================================================================
|
||||
|
||||
import sys
|
||||
import base64
|
||||
import hashlib
|
||||
import urllib.request
|
||||
from datetime import datetime, timezone
|
||||
from pymongo import MongoClient
|
||||
from bson import ObjectId
|
||||
|
||||
MONGO_URI = "mongodb://192.168.1.76:27017"
|
||||
DBN, COL = "feasibility", "investigators"
|
||||
|
||||
# (investigator _id, seaweed_url, filename, sha256, size, source_msg_id, label)
|
||||
MAPPING = [
|
||||
("6a198b661218c31ab0f5ba57",
|
||||
"http://192.168.1.50:8888/mail-attachments/1a/86/1a86e987b9d3da57c1d863b47734133f2e2d7eae3f5cfe91112c475eb86d86e9",
|
||||
"CZ_CDA PI_MUDr. Filip Zavada_fully signed_16Jun2026.pdf",
|
||||
"1a86e987b9d3da57c1d863b47734133f2e2d7eae3f5cfe91112c475eb86d86e9",
|
||||
479026, "<CH2PR07MB7190A5538ACDC1D49F8B430780E52@CH2PR07MB7190.namprd07.prod.outlook.com>",
|
||||
"Zavada Filip"),
|
||||
("6a19832b5fc2213518257957",
|
||||
"http://192.168.1.50:8888/mail-attachments/64/b0/64b06d48bfe3c49095e326988f14c04fd5849728b227647f6653b2e3c3095538",
|
||||
"SK_CDA PI_Bruncak_FNsP BBystrica_fully signed 16Jun2026.pdf",
|
||||
"64b06d48bfe3c49095e326988f14c04fd5849728b227647f6653b2e3c3095538",
|
||||
498069, "<SA1PR07MB952874B8654156369CDE44448CE52@SA1PR07MB9528.namprd07.prod.outlook.com>",
|
||||
"Bruncak Michal"),
|
||||
("6a19832b5fc2213518257961",
|
||||
"http://192.168.1.50:8888/mail-attachments/c2/72/c272ca62bd27ca10aed35cb54054d880f4f0e2f59940ed3b067b17d51a9ac041",
|
||||
"CZ_CDA Institution_Asclepiades s.r.o._MUDr. Machytka_16Jun2026.pdf",
|
||||
"c272ca62bd27ca10aed35cb54054d880f4f0e2f59940ed3b067b17d51a9ac041",
|
||||
460977, "<PH0PR07MB97879A9C9BF9C00D38D4798A9FE52@PH0PR07MB9787.namprd07.prod.outlook.com>",
|
||||
"Machytka Evzen (Asclepiades)"),
|
||||
("6a19832b5fc2213518257967",
|
||||
"http://192.168.1.50:8888/mail-attachments/99/37/99372c399be3b001428ef4b36d43e250dedced5955de5d1f3a2d63a9f0c1728b",
|
||||
"CZ_CDA institution_PreventaMed sro_fully signed_16Jun2026.pdf",
|
||||
"99372c399be3b001428ef4b36d43e250dedced5955de5d1f3a2d63a9f0c1728b",
|
||||
457745, "<CH2PR07MB719008DB0B3CAFD764AE2E8280E52@CH2PR07MB7190.namprd07.prod.outlook.com>",
|
||||
"Pumprla Jiri (PreventaMed)"),
|
||||
("6a1c4275aa46d8b608065ce9",
|
||||
"http://192.168.1.50:8888/mail-attachments/94/95/9495c742407873efd8dd9713e1dc962cb08e55e0d3690e4a79a90132ee358dee",
|
||||
"SK_CDA Institution_PAV-MED s r.o_fully signed_15Jun2026.pdf",
|
||||
"9495c742407873efd8dd9713e1dc962cb08e55e0d3690e4a79a90132ee358dee",
|
||||
460246, "<CH2PR07MB719008DB0B3CAFD764AE2E8280E52@CH2PR07MB7190.namprd07.prod.outlook.com>",
|
||||
"Zapotocka Julia (PAV-MED)"),
|
||||
]
|
||||
|
||||
|
||||
def fetch(url):
|
||||
with urllib.request.urlopen(url, timeout=30) as r:
|
||||
return r.read()
|
||||
|
||||
|
||||
def main():
|
||||
apply = "--apply" in sys.argv
|
||||
cli = MongoClient(MONGO_URI)
|
||||
col = cli[DBN][COL]
|
||||
now = datetime.now(timezone.utc).isoformat()
|
||||
|
||||
ok = 0
|
||||
for _id, url, fname, sha, size, src, label in MAPPING:
|
||||
oid = ObjectId(_id)
|
||||
doc = col.find_one({"_id": oid}, {"STATUS": 1, "KROK": 1, "cda.stav": 1})
|
||||
if not doc:
|
||||
print(f" !! {label}: investigator _id={_id} NENALEZEN"); continue
|
||||
try:
|
||||
raw = fetch(url)
|
||||
except Exception as e:
|
||||
print(f" !! {label}: stazeni selhalo: {e}"); continue
|
||||
got = hashlib.sha256(raw).hexdigest()
|
||||
sha_ok = (got == sha)
|
||||
size_ok = (len(raw) == size)
|
||||
head_ok = raw[:5] == b"%PDF-"
|
||||
print(f" [{label}]")
|
||||
print(f" soubor : {fname}")
|
||||
print(f" stazeno : {len(raw)} B (ocek. {size}) {'OK' if size_ok else 'MISMATCH'}")
|
||||
print(f" sha256 : {'OK' if sha_ok else 'MISMATCH! ' + got}")
|
||||
print(f" PDF hdr : {'OK' if head_ok else 'NENI PDF'}")
|
||||
print(f" KROK : {doc.get('KROK')} -> 5 - CDA podepsano")
|
||||
if not (sha_ok and size_ok and head_ok):
|
||||
print(" >> PRESKAKUJI (kontrola selhala)"); continue
|
||||
if not apply:
|
||||
ok += 1; continue
|
||||
|
||||
b64 = base64.b64encode(raw).decode("ascii")
|
||||
old_status = doc.get("STATUS", "") or ""
|
||||
new_line = (f"17JUN2026: podepsane CDA ULOZENO do Mongo (cda.data) — {fname} "
|
||||
f"(z e-mailu asistentky). KROK 5, pripraveno na SIPIQ.")
|
||||
col.update_one({"_id": oid}, {"$set": {
|
||||
"KROK": "5 - CDA podepsano",
|
||||
"STATUS": new_line + "\n" + old_status,
|
||||
"cda.stav": "podepsano",
|
||||
"cda.soubor": fname,
|
||||
"cda.zdroj": "e-mail asistentky (SeaweedFS)",
|
||||
"cda.data_base64": b64,
|
||||
"cda.data_sha256": sha,
|
||||
"cda.data_filename": fname,
|
||||
"cda.data_mime": "application/pdf",
|
||||
"cda.data_size": len(raw),
|
||||
"cda.data_stored_at": now,
|
||||
"cda.data_source_msg": src,
|
||||
}})
|
||||
ok += 1
|
||||
print(" >> ULOZENO + KROK 5")
|
||||
|
||||
print(f"\n{'ZAPSANO' if apply else 'DRY-RUN OK'}: {ok}/{len(MAPPING)}")
|
||||
if not apply:
|
||||
print(">>> Pro zapis spust s --apply")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in New Issue
Block a user