def format_note_object_for_client(note):
"""
Returns an object that represents note in the format expected by the reader client,
matching the format of links, which are currently handled together.
"""
anchor_oref = Ref(note.ref).padded_ref()
ownerData = public_user_data(note.owner)
com = {
"category": "Notes",
"type": "note",
"owner": note.owner,
"_id": str(note._id),
"anchorRef": note.ref,
"anchorVerse": anchor_oref.sections[-1],
"anchorText": getattr(note, "anchorText", ""),
"public": getattr(note, "public", False),
"commentator": user_link(note.owner),
"text": note.text,
"title": getattr(note, "title", ""),
"ownerName": ownerData["name"],
"ownerProfileUrl": ownerData["profileUrl"],
"ownerImageUrl": ownerData["imageUrl"],
}
return com
def index_sheet(index_name, id):
"""
Index source sheet with 'id'.
"""
sheet = db.sheets.find_one({"id": id})
if not sheet: return False
pud = public_user_data(sheet["owner"])
doc = {
"title": sheet["title"],
"content": make_sheet_text(sheet, pud),
"owner_id": sheet["owner"],
"owner_name": pud["name"],
"owner_image": pud["imageUrl"],
"profile_url": pud["profileUrl"],
"version": "Source Sheet by " + user_link(sheet["owner"]),
"tags": ",".join(sheet.get("tags",[])),
"sheetId": id,
}
try:
es.index(index_name, 'sheet', doc, id)
global doc_count
doc_count += 1
return True
except Exception, e:
print "Error indexing sheet %d" % id
print e
return False
def format_note_object_for_client(note):
"""
Returns an object that represents note in the format expected by the reader client,
matching the format of links, which are currently handled together.
"""
anchor_oref = Ref(note.ref).padded_ref()
ownerData = public_user_data(note.owner)
com = {
"category": "Notes",
"type": "note",
"owner": note.owner,
"_id": str(note._id),
"anchorRef": note.ref,
"anchorVerse": anchor_oref.sections[-1],
"anchorText": getattr(note, "anchorText", ""),
"public": getattr(note, "public", False),
"commentator": user_link(note.owner),
"text": note.text,
"title": getattr(note, "title", ""),
"ownerName": ownerData["name"],
"ownerProfileUrl": ownerData["profileUrl"],
"ownerImageUrl": ownerData["imageUrl"],
}
return com
def index_sheet(index_name, id):
"""
Index source sheet with 'id'.
"""
sheet = db.sheets.find_one({"id": id})
if not sheet: return False
pud = public_user_data(sheet["owner"])
try:
doc = {
"title": strip_tags(sheet["title"]),
"content": make_sheet_text(sheet, pud),
"owner_id": sheet["owner"],
"owner_name": pud["name"],
"owner_image": pud["imageUrl"],
"profile_url": pud["profileUrl"],
"version": "Source Sheet by " + user_link(sheet["owner"]),
"tags": sheet.get("tags", []),
"sheetId": id,
"summary": sheet.get("summary", None),
"group": sheet.get("group", None),
"datePublished": sheet.get("datePublished", None),
"dateCreated": sheet.get("dateCreated", None),
"dateModified": sheet.get("dateCreated", None),
"views": sheet.get("views", 0)
}
es_client.create(index=index_name, doc_type='sheet', id=id, body=doc)
global doc_count
doc_count += 1
return True
except Exception, e:
print "Error indexing sheet %d" % id
print e
return False
def index_sheet(index_name, id):
"""
Index source sheet with 'id'.
"""
sheet = db.sheets.find_one({"id": id})
if not sheet: return False
pud = public_user_data(sheet["owner"])
doc = {
"title": sheet["title"],
"content": make_sheet_text(sheet, pud),
"owner_id": sheet["owner"],
"owner_name": pud["name"],
"owner_image": pud["imageUrl"],
"profile_url": pud["profileUrl"],
"version": "Source Sheet by " + user_link(sheet["owner"]),
"tags": ",".join(sheet.get("tags",[])),
"sheetId": id,
}
try:
es.index(index_name, 'sheet', doc, id)
global doc_count
doc_count += 1
except Exception, e:
print "Error indexing sheet %d" % id
print e
def annotate_user_links(sources): """ Search a sheet for any addedBy fields (containg a UID) and add corresponding user links. """ for source in sources: if "addedBy" in source: source["userLink"] = user_link(source["addedBy"]) return sources
def annotate_user_links(sources):
"""
Search a sheet for any addedBy fields (containg a UID) and add corresponding user links.
"""
for source in sources:
if "addedBy" in source:
source["userLink"] = user_link(source["addedBy"])
return sources
def get_sheets_for_ref(tref, pad=True, context=1):
"""
Returns a list of sheets that include ref,
formating as need for the Client Sidebar.
"""
oref = model.Ref(tref)
if pad:
oref = oref.padded_ref()
if context:
oref = oref.context_ref(context)
ref_re = oref.regex()
results = []
regex_list = oref.regex(as_list=True)
ref_clauses = [{"sources.ref": {"$regex": r}} for r in regex_list]
sheets = db.sheets.find({"$or": ref_clauses, "status": "public"},
{"id": 1, "title": 1, "owner": 1, "sources.ref": 1, "views": 1}).sort([["views", -1]])
for sheet in sheets:
matched_refs = []
if "sources" in sheet:
for source in sheet["sources"]:
if "ref" in source:
matched_refs.append(source["ref"])
matched_refs = [r for r in matched_refs if regex.match(ref_re, r)]
for match in matched_refs:
try:
match = model.Ref(match)
except InputError:
continue
ownerData = public_user_data(sheet["owner"])
com = {
"category": "Sheets",
"type": "sheet",
"owner": sheet["owner"],
"_id": str(sheet["_id"]),
"anchorRef": match.normal(),
"anchorVerse": match.sections[-1] if len(match.sections) else 1,
"public": True,
"commentator": user_link(sheet["owner"]), # legacy, used in S1
"text": "<a class='sheetLink' href='/sheets/%d'>%s</a>" % (sheet["id"], strip_tags(sheet["title"])), # legacy, used in S1
"title": strip_tags(sheet["title"]),
"sheetUrl": "/sheets/" + str(sheet["id"]),
"ownerName": ownerData["name"],
"ownerProfileUrl": ownerData["profileUrl"],
"ownerImageUrl": ownerData["imageUrl"],
"views": sheet["views"]
}
results.append(com)
return results
def get_sheets_for_ref(tref, pad=True, context=1):
"""
Returns a list of sheets that include ref,
formating as need for the Client Sidebar.
"""
oref = model.Ref(tref)
if pad:
oref = oref.padded_ref()
if context:
oref = oref.context_ref(context)
ref_re = oref.regex()
results = []
regex_list = oref.regex(as_list=True)
ref_clauses = [{"sources.ref": {"$regex": r}} for r in regex_list]
sheets = db.sheets.find({"$or": ref_clauses, "status": "public"},
{"id": 1, "title": 1, "owner": 1, "sources.ref": 1, "views": 1}).sort([["views", -1]])
for sheet in sheets:
matched_refs = []
if "sources" in sheet:
for source in sheet["sources"]:
if "ref" in source:
matched_refs.append(source["ref"])
matched_refs = [r for r in matched_refs if regex.match(ref_re, r)]
for match in matched_refs:
try:
match = model.Ref(match)
except InputError:
continue
ownerData = public_user_data(sheet["owner"])
com = {
"category": "Sheets",
"type": "sheet",
"owner": sheet["owner"],
"_id": str(sheet["_id"]),
"anchorRef": match.normal(),
"anchorVerse": match.sections[-1] if len(match.sections) else 1,
"public": True,
"commentator": user_link(sheet["owner"]), # legacy, used in S1
"text": "<a class='sheetLink' href='/sheets/%d'>%s</a>" % (sheet["id"], strip_tags(sheet["title"])), # legacy, used in S1
"title": strip_tags(sheet["title"]),
"sheetUrl": "/sheets/" + str(sheet["id"]),
"ownerName": ownerData["name"],
"ownerProfileUrl": ownerData["profileUrl"],
"ownerImageUrl": ownerData["imageUrl"],
"views": sheet["views"]
}
results.append(com)
return results
def get_reviews(tref, lang, version):
"""
Returns a list of reviews pertaining to ref/lang/version
"""
reviews = []
tref = model.Ref(tref).normal()
refRe = '^%s$|^%s:' % (tref, tref)
cursor = db.history.find({"ref": {"$regex": refRe}, "language": lang, "version": version, "rev_type": "review"}).sort([["date", -1]])
for r in cursor:
r["_id"] = str(r["_id"])
r["userLink"] = user_link(r["user"])
reviews.append(r)
return reviews
def index_sheet(index_name, id):
"""
Index source sheet with 'id'.
"""
sheet = db.sheets.find_one({"id": id})
if not sheet: return False
pud = public_user_data(sheet["owner"])
tag_terms_simple = make_sheet_tags(sheet)
tags = [t["en"] for t in tag_terms_simple]
topics = []
for t in sheet.get('topics', []):
topic_obj = Topic.init(t['slug'])
if not topic_obj:
continue
topics += [topic_obj]
collections = CollectionSet({"sheets": id, "listed": True})
collection_names = [c.name for c in collections]
try:
doc = {
"title": strip_tags(sheet["title"]),
"content": make_sheet_text(sheet, pud),
"owner_id": sheet["owner"],
"owner_name": pud["name"],
"owner_image": pud["imageUrl"],
"profile_url": pud["profileUrl"],
"version": "Source Sheet by " + user_link(sheet["owner"]),
"tags": tags,
"topic_slugs": [topic_obj.slug for topic_obj in topics],
"topics_en": [topic_obj.get_primary_title('en') for topic_obj in topics],
"topics_he": [topic_obj.get_primary_title('he') for topic_obj in topics],
"sheetId": id,
"summary": sheet.get("summary", None),
"collections": collection_names,
"datePublished": sheet.get("datePublished", None),
"dateCreated": sheet.get("dateCreated", None),
"dateModified": sheet.get("dateModified", None),
"views": sheet.get("views", 0)
}
es_client.create(index=index_name, doc_type='sheet', id=id, body=doc)
global doc_count
doc_count += 1
return True
except Exception as e:
print("Error indexing sheet %d" % id)
print(e)
return False
def index_sheet(index_name, id):
"""
Index source sheet with 'id'.
"""
sheet = db.sheets.find_one({"id": id})
if not sheet: return False
pud = public_user_data(sheet["owner"])
tag_terms_simple = make_sheet_tags(sheet)
tags = [t["en"] for t in tag_terms_simple]
tags_he_and_en = [
u"{}|||{}".format(t["en"], t["he"]) for t in tag_terms_simple
]
try:
doc = {
"title": strip_tags(sheet["title"]),
"content": make_sheet_text(sheet, pud),
"owner_id": sheet["owner"],
"owner_name": pud["name"],
"owner_image": pud["imageUrl"],
"profile_url": pud["profileUrl"],
"version": "Source Sheet by " + user_link(sheet["owner"]),
"tags": tags,
"tags_he_and_en": tags_he_and_en,
"sheetId": id,
"summary": sheet.get("summary", None),
"group": sheet.get("group", None),
"datePublished": sheet.get("datePublished", None),
"dateCreated": sheet.get("dateCreated", None),
"dateModified": sheet.get("dateCreated", None),
"views": sheet.get("views", 0)
}
es_client.create(index=index_name, doc_type='sheet', id=id, body=doc)
global doc_count
doc_count += 1
return True
except Exception, e:
print "Error indexing sheet %d" % id
print e
return False
def get_reviews(tref, lang, version):
"""
Returns a list of reviews pertaining to ref/lang/version
"""
reviews = []
tref = model.Ref(tref).normal()
refRe = '^%s$|^%s:' % (tref, tref)
cursor = db.history.find({
"ref": {
"$regex": refRe
},
"language": lang,
"version": version,
"rev_type": "review"
}).sort([["date", -1]])
for r in cursor:
r["_id"] = str(r["_id"])
r["userLink"] = user_link(r["user"])
reviews.append(r)
return reviews
def index_sheet(id):
"""
Index source sheet with 'id'.
"""
sheet = db.sheets.find_one({"id": id})
if not sheet: return False
doc = {
"title": sheet["title"],
"content": make_sheet_text(sheet),
"version": "Source Sheet by " + user_link(sheet["owner"]),
"tags": ",".join(sheet.get("tags", [])),
"sheetId": id,
}
try:
es.index('sefaria', 'sheet', doc, id)
global doc_count
doc_count += 1
except Exception, e:
print "Error indexing sheet %d" % id
print e
def get_sheets_for_ref(tref, uid=None):
"""
Returns a list of sheets that include ref,
formating as need for the Client Sidebar.
If `uid` is present return user sheets, otherwise return public sheets.
"""
oref = model.Ref(tref)
# perform initial search with context to catch ranges that include a segment ref
regex_list = oref.context_ref().regex(as_list=True)
ref_clauses = [{"sources.ref": {"$regex": r}} for r in regex_list]
query = {"$or": ref_clauses}
if uid:
query["owner"] = uid
else:
query["status"] = "public"
sheets = db.sheets.find(
query, {
"id": 1,
"title": 1,
"owner": 1,
"sources.ref": 1,
"views": 1,
"tags": 1,
"status": 1
}).sort([["views", -1]])
results = []
for sheet in sheets:
matched_refs = []
for source in sheet.get("sources", []):
if "ref" in source:
matched_refs.append(source["ref"])
for match in matched_refs:
try:
match = model.Ref(match)
if not oref.overlaps(match):
continue
except InputError:
continue
ownerData = public_user_data(sheet["owner"])
sheet_data = {
"owner":
sheet["owner"],
"_id":
str(sheet["_id"]),
"anchorRef":
match.normal(),
"anchorVerse":
match.sections[-1] if len(match.sections) else 1,
"public":
sheet["status"] == "public",
"text":
"<a class='sheetLink' href='/sheets/%d'>%s</a>" %
(sheet["id"], strip_tags(
sheet["title"])), # legacy, used in S1
"title":
strip_tags(sheet["title"]),
"sheetUrl":
"/sheets/" + str(sheet["id"]),
"ownerName":
ownerData["name"],
"ownerProfileUrl":
ownerData["profileUrl"],
"ownerImageUrl":
ownerData["imageUrl"],
"status":
sheet["status"],
"views":
sheet["views"],
"tags":
sheet.get("tags", []),
"commentator":
user_link(sheet["owner"]), # legacy, used in S1
"category":
"Sheets", # ditto
"type":
"sheet", # ditto
}
results.append(sheet_data)
return results
def sheet_spam_dashboard(request):
from django.contrib.auth.models import User
if request.method == 'POST':
return jsonResponse({"error": "Unsupported Method: {}".format(request.method)})
else:
date = request.GET.get("date", None)
if date:
date = datetime.strptime(date, '%Y-%m-%d')
else:
date = request.GET.get("date", datetime.now() - timedelta(days=30))
earliest_new_user_id = User.objects.filter(date_joined__gte=date).order_by('date_joined')[0].id
regex = r'.*(?!href=[\'"](\/|http(s)?:\/\/(www\.)?sefaria).+[\'"])(href).*'
sheets = db.sheets.find({"sources.ref": {"$exists": False}, "dateCreated": {"$gt": date.strftime("%Y-%m-%dT%H:%M:%S.%f")}, "owner": {"$gt": earliest_new_user_id}, "includedRefs": {"$size": 0}, "reviewed": {"$ne": True}, "$or": [{"sources.outsideText": {"$regex": regex}}, {"sources.comment": {"$regex": regex}}, {"sources.outsideBiText.en": {"$regex": regex}}, {"sources.outsideBiText.he": {"$regex": regex}}]})
sheets_list = []
for sheet in sheets:
sheets_list.append({"id": sheet["id"], "title": strip_tags(sheet["title"]), "owner": user_link(sheet["owner"])})
return render_template(request, 'spam_dashboard.html', None, {
"title": "Potential Spam Sheets since %s" % date.strftime("%Y-%m-%d"),
"sheets": sheets_list,
"type": "sheet",
})
def spam_dashboard(request):
from django.contrib.auth.models import User
if request.method == 'POST':
spam_sheet_ids = list(
map(int, request.POST.getlist("spam_sheets[]", [])))
reviewed_sheet_ids = list(
map(int, request.POST.getlist("reviewed_sheets[]", [])))
db.sheets.update_many({"id": {
"$in": reviewed_sheet_ids
}}, {"$set": {
"reviewed": True
}})
spammers = db.sheets.find({
"id": {
"$in": spam_sheet_ids
}
}, {
"owner": 1
}).distinct("owner")
for spammer in spammers:
try:
spammer_account = User.objects.get(id=spammer)
spammer_account.is_active = False
spammer_account.save()
except:
continue
db.sheets.delete_many({"id": {"$in": spam_sheet_ids}})
return render(
request, 'spam_dashboard.html', {
"deleted_sheets": len(spam_sheet_ids),
"sheet_ids": spam_sheet_ids,
"reviewed_sheets": len(reviewed_sheet_ids),
"spammers_deactivated": len(spammers)
})
else:
date = request.GET.get("date", None)
if date:
date = datetime.strptime(date, '%Y-%m-%d')
else:
date = request.GET.get("date", datetime.now() - timedelta(days=30))
earliest_new_user_id = User.objects.filter(date_joined__gte=date)[0].id
regex = r'.*(?!href=[\'"](\/|http(s)?:\/\/(www\.)?sefaria).+[\'"])(href).*'
sheets = db.sheets.find({
"sources.ref": {
"$exists": False
},
"dateCreated": {
"$gt": date.strftime("%Y-%m-%dT%H:%M:%S.%f")
},
"owner": {
"$gt": earliest_new_user_id
},
"includedRefs": {
"$size": 0
},
"reviewed": {
"$ne": True
},
"$or": [{
"sources.outsideText": {
"$regex": regex
}
}, {
"sources.comment": {
"$regex": regex
}
}, {
"sources.outsideBiText.en": {
"$regex": regex
}
}, {
"sources.outsideBiText.he": {
"$regex": regex
}
}]
})
sheets_list = []
for sheet in sheets:
sheets_list.append({
"id": sheet["id"],
"title": strip_tags(sheet["title"]),
"owner": user_link(sheet["owner"])
})
return render(
request, 'spam_dashboard.html', {
"title":
"Potential Spam Sheets since %s" % date.strftime("%Y-%m-%d"),
"sheets":
sheets_list,
})
