diff --git a/extract_notes.py b/extract_notes.py
index 6dabbb0cae21098a90f504e9e6200d4733aa5c21..286800bed4558499cf612dfc71bccd42949d2dee 100755
--- a/extract_notes.py
+++ b/extract_notes.py
@@ -6,7 +6,7 @@ import os, sys, os.path
import getpass
import sqlite3
import json
-import bisect
+#import bisect
import re #regular expression
parser = argparse.ArgumentParser(description="Extraire les notes d'une liseuse Vivlio")
@@ -19,19 +19,34 @@ args = parser.parse_args()
def getPage(anchor):
output = re.search("page\=(\d+)",anchor)
if output is not None:
- output = output.group(1)
- return int(output)
+ output = int(output.group(1))+1
+ return output
+
+def startChar(anchor):
+ output = re.search("offs\=(\d+)",anchor)
+ if output is not None:
+ output = int(output.group(1))
+ return output
+
+def endChar(anchor):
+ output = re.search("over\=(\d+)",anchor)
+ if output is not None:
+ output = int(output.group(1))
+ return output
class Note:
BM = 1 #bookmark
QUOTE = 2 #citation
NOTE = 3 #note
- def __init__(self, dbString):
+ def __init__(self, id, dbString):
tmp = json.loads(dbString)
self.text = None
self.endP = None
self.note = None
+ self.startChar = None
+ self.endChar = None
+ self.id = id
if len(tmp)==3:
self.type = Note.NOTE
tmp[0].update(tmp[1])
@@ -47,54 +62,68 @@ class Note:
self.p = getPage(tmp[0]["anchor"])
if "begin" in tmp[0] :
self.p = getPage(tmp[0]["begin"])
+ self.startChar = startChar(tmp[0]["begin"])
if "end" in tmp[0] :
self.endP = getPage(tmp[0]["end"])
+ self.endChar = endChar(tmp[0]["end"])
if "text" in tmp[0] :
self.text = tmp[0]["text"].replace("\n","")
+ #for comparison
+ def endP_int(self):
+ res = self.endP
+ if res == None:
+ res=-1
+ return res
+ def startChar_int(self):
+ res = self.startChar
+ if res == None:
+ res=-1
+ return res
+ def endChar_int(self):
+ res = self.endChar
+ if res == None:
+ res=-1
+ return res
+
def __lt__(self, note2):
- if self.p > note2.p:
- res = -1
- elif self.p < note2.p:
- res = 1
- elif self.endP == note2.endP:
- if self.type > note2.type:
- res = -1
- elif self.type < note2.type:
- res = 1
- else:
- res = 0
- elif self.endP == None:
- res = 1
- elif note2.endP == None:
- res = -1
- elif self.endP > note2.endP:
- res = -1
+ return (self.p, self.startChar_int(), self.endP_int(), self.endChar_int(), self.type, self. id) < (note2.p, note2.startChar_int(), note2.endP_int(), note2.endChar_int(), note2.type, note2. id)
+
+ def getType(self):
+ if self.type == Note.BM:
+ res = "Bookmark"
+ elif self.type == Note.QUOTE:
+ res = "Quote"
else:
- res = 1
+ res = "Note"
return res
def toJSON(self):
- json_note = {"type":self.type,"p":self.p}
+ json_note = {"id":self.id, "type":self.getType(),"p":self.p}
+ if self.startChar!=None:
+ json_note["startChar"] = self.startChar
if self.endP != None :
json_note["endP"] = self.endP
+ if self.endChar!=None:
+ json_note["endChar"] = self.endChar
if self.text != None :
json_note["text"] = self.text
json_note["raw"] = self.raw
return json_note
- def toWiki(self):
- wiki_note = ""
+ def toWiki(self, writePageNumber = True):
+ wiki_note = "<p id='"+self.getType()+"_"+str(self.id)+"'>"
if self.type != Note.BM:
- wiki_note = "{{p|"+str(self.p)
- if self.endP != None and self.p!=self.endP:
- wiki_note += "–"+str(self.endP)
- wiki_note+="}}\n"
+ if writePageNumber:
+ wiki_note += "{{p|"+str(self.p)
+ if self.endP != None and self.p!=self.endP:
+ wiki_note += "–"+str(self.endP)
+ wiki_note+="}}\n"
if self.text != None:
- wiki_note += "«"+self.text+"»\n"
+ wiki_note += "«"+self.text+"»"
if self.note != None:
- wiki_note += "{{commentaire|"+self.note+"}}\n"
- return wiki_note
+ wiki_note += " {{commentaire|"+self.note+"}}"
+ return wiki_note+"</p>"
class Book:
def __init__(self, author=None, title=None):
@@ -112,7 +141,8 @@ class Book:
self.data = []
def addNote(self, note):
- bisect.insort_left(self.data,note)
+ #bisect.insort_left(self.data,note)
+ self.data.append(note)
def fileName(self, directory="."):
res = False
@@ -128,6 +158,7 @@ class Book:
return directory+"/"+res
def store(self, directory=".", format="json"):
+ self.data.sort()
if format == "json":
self.JSON_store(self.fileName(directory)+".json")
elif format == "wiki":
@@ -146,9 +177,12 @@ class Book:
def wiki_store(self, fileName):
out_file = open(fileName, "w")
out_file.write("="+self.author+" — "+self.title+"=\n")
+ last_note = None
for note in self.data:
- out_file.write(note.toWiki())
+ writePageNumber = not isinstance(last_note,Note) or (last_note.p != note.p or last_note.endP != note.endP)
+ out_file.write(note.toWiki(writePageNumber))
out_file.write("\n")
+ last_note = note
out_file.close()
@@ -184,7 +218,7 @@ def connect(sourceDir):
return conn
def retrieveData(conn):
- query = "SELECT `Books`.`Title` as `title`, `Books`.`Authors` as `author`, '['||GROUP_CONCAT(`Tags`.`Val`, ',')||']' as `data` FROM `Books`, `Items`, `Tags` WHERE (`Tags`.`TagID` = 101 OR `Tags`.`TagID` = 104 OR `Tags`.`TagID` = 105) AND `Tags`.`ItemID`= `Items`.`OID` AND `Items`.`ParentID`=`Books`.`OID` GROUP BY `Items`.`OID` ORDER BY `author`, `title`;"
+ query = "SELECT `Books`.`Title` as `title`, `Books`.`Authors` as `author`, '['||GROUP_CONCAT(`Tags`.`Val`, ',')||']' as `data`, `Tags`.`ItemID` as `id` FROM `Books`, `Items`, `Tags` WHERE (`Tags`.`TagID` = 101 OR `Tags`.`TagID` = 104 OR `Tags`.`TagID` = 105) AND `Tags`.`ItemID`= `Items`.`OID` AND `Items`.`ParentID`=`Books`.`OID` GROUP BY `Items`.`OID` ORDER BY `author`, `title`, `Tags`.`TimeEdt`;"
cur = conn.cursor()
cur.execute(query)
return cur.fetchall()
@@ -198,7 +232,7 @@ def export_data(data, directory, format="json"):
curbook.store(directory, format)
curbook.empty()
curbook = Book(comment[1],comment[0])
- curbook.addNote(Note(comment[2]))
+ curbook.addNote(Note(comment[3],comment[2]))
if curbook.is_empty():
curbook.store(directory, format)