Compare commits

..

No commits in common. "8097fcef604c1efc2640388dc01aea98c3719cef" and "c1c2c45439834543e0638b6bc28cd3121f9e6a91" have entirely different histories.

7 changed files with 40 additions and 137 deletions

1
.gitignore vendored
View File

@ -1,4 +1,3 @@
.idea .idea
__pycache__ __pycache__
*.code-workspace *.code-workspace
.venv*

View File

@ -1,9 +0,0 @@
from lib import *
def retrieve(id_num):
result = api.get_pages_read({"id": id_num})
print(result)
def insert(id_num, name, text):
pass

View File

@ -1,63 +0,0 @@
{
'post_books_create',
'get_attachments_read',
'get_chapters_list',
'get_content_permissions_read',
'get_chapters_export_markdown',
'post_roles_create',
'put_recycle_bin_restore',
'put_image_gallery_update',
'put_books_update',
'post_shelves_create',
'get_books_read',
'get_attachments_list',
'put_content_permissions_update',
'get_recycle_bin_list',
'delete_users_delete',
'get_users_list',
'get_docs_json',
'get_books_export_html',
'put_chapters_update',
'get_chapters_export_pdf',
'get_pages_export_markdown',
'delete_pages_delete',
'post_attachments_create',
'put_attachments_update',
'get_roles_read',
'get_chapters_export_plain_text',
'get_users_read',
'delete_chapters_delete',
'put_pages_update',
'post_chapters_create',
'get_chapters_read',
'get_pages_list',
'get_pages_export_plain_text',
'get_roles_list',
'get_pages_export_html',
'get_image_gallery_read',
'delete_attachments_delete',
'post_users_create',
'get_audit_log_list',
'get_pages_export_pdf',
'delete_books_delete',
'get_shelves_read',
'delete_roles_delete',
'get_pages_read',
'put_shelves_update',
'get_books_export_plain_text',
'delete_shelves_delete',
'get_books_export_markdown',
'delete_image_gallery_delete',
'get_search_all',
'get_books_list',
'post_image_gallery_create',
'get_books_export_pdf',
'post_pages_create',
'get_shelves_list',
'get_docs_display',
'put_users_update',
'put_roles_update',
'delete_recycle_bin_destroy',
'get_chapters_export_html',
'get_image_gallery_list'
}

View File

@ -1,31 +1,20 @@
import lib import lib
from lib import json_cursor, json_file
existing, inserted, duplicates = 0, 0, 0 # import paperless database export
raw_manifest = open("/mnt/user/media/paperless/media/backup/manifest.json")
manifest = lib.json.load(raw_manifest)
index_num = 1
existing, inserted, big, duplicates = 0, 0, 0, 0
def insert(r): def insert(r):
global inserted lib.db.insert_one({"title": r["title"],
pk = r['pk'] "content": r["content"],
check = r['check'] "checksum": r["check"],
content = r['content'] "index": r["index"]})
title = r['title']
lib.db.insert_one({'title': title,"content": content, def exists(r):
"checksum": check,
"pk": pk})
inserted = inserted + 1
def update_pk(r):
lib.db.update_one(
{
"checksum": r["check"]
},
{
"$set": {"index": r["index"]}
}
)
def rec_exists(r):
global existing, duplicates global existing, duplicates
record = lib.db.find_one({"checksum": r["check"]}) record = lib.db.find_one({"checksum": r["check"]})
dupe = lib.db.find_one({"content": r["content"], "title": r["title"]}) dupe = lib.db.find_one({"content": r["content"], "title": r["title"]})
@ -39,19 +28,25 @@ def rec_exists(r):
else: return False else: return False
def parse(): def parse():
f = json_file() global inserted, big, index_num
print("Parsing manifest json...") print("Parsing manifest json...")
r = {}
# for every document in the export # for every document in the export
for doc in json_cursor(f): for document in manifest:
fields = doc['fields'] #if the title and content tags aren't blank
if 'title' in fields and 'content' in fields: try:
r['pk'] = doc['pk'] record = {"title": document["fields"]["title"],
r['title'] = fields['title'] "content": document["fields"]["content"],
r['content'] = fields['content'] "check": document["fields"]["checksum"],
r['check'] = fields['checksum'] "index": index_num}
if rec_exists(r):
if lib.sys.getsizeof(record["content"]) < 16777216:
if record["content"] != "" and record["title"] != "":
if not exists(record):
insert(record)
inserted = inserted + 1
index_num = index_num + 1
else: big = big + 1
except KeyError:
continue continue
else:
insert(r)
f.close()

2
src/insert.py Normal file
View File

@ -0,0 +1,2 @@
import lib

View File

@ -1,29 +1,6 @@
import pymongo import pymongo
import os import os
import ijson import json
import sys import sys
import bookstack
db = pymongo.MongoClient("localhost", 27017).paperless.content
def json_file():
return open("/mnt/tower/media/paperless/media/backup/test.json")
# import paperless database export
# manifest_path = "/mnt/user/media/paperless/media/manifest.json"
def json_cursor(f):
items = ijson.items(f, 'item')
docs = (doc for doc in items \
if doc['model'] == "documents.document" \
if sys.getsizeof(doc['fields']['content']) < 16777216)
return docs
db = pymongo.MongoClient("10.0.0.59", 27017).paperless.content
url = 'http://10.0.0.59:6875'
token = 'RVSO8xZXOjRYJntNYPRd3E9iT2qXm11C'
secret = 'qR5r2EyKT09ogz8VSolS12ispAV5QrT0'
api = bookstack.BookStack(url, token, secret)
methods = api.generate_api_methods()

View File

@ -1,12 +1,13 @@
import extract import extract
import search import search
import insert
def start(): def start():
extract.parse() extract.parse()
print("Existing:", extract.existing) print("Existing:", extract.existing)
print("Inserted:", extract.inserted) print("Inserted:", extract.inserted)
print("To big:", extract.big)
print("Dupes:", extract.duplicates) print("Dupes:", extract.duplicates)
extract.existing, extract.inserted, extract.duplicates = 0, 0, 0
menu() menu()
@ -16,7 +17,8 @@ def prompt():
def menu(): def menu():
value = prompt() value = prompt()
if value == "reload": if value == "reload":
start() extract.parse()
value = prompt()
while value != "quit" and value != "reload": while value != "quit" and value != "reload":
results = search.query(value) results = search.query(value)
if type(results) == dict: if type(results) == dict: