Add python file - bookdarts - Extract KOReader generated highlights and publish them in a variety of formats↵
DIR Log
DIR Files
DIR Refs
---
DIR commit a2eec07ead104ba756d1abb0b6f727cd4e369632
DIR parent 75968d58e15a9c4c2fb15036ac2d33547641964f
HTML Author: Scarlett McAllister <no+reply@roygbyte.com>
Date: Thu, 28 Sep 2023 20:05:40 -0300
Add python file
Decided to implement this in Python. It's been much easier and
enjoyable than shell.
Diffstat:
A bookdarts.py | 83 +++++++++++++++++++++++++++++++
1 file changed, 83 insertions(+), 0 deletions(-)
---
DIR diff --git a/bookdarts.py b/bookdarts.py
@@ -0,0 +1,83 @@
+#############################################
+# Dependencies
+import sys
+import fileinput
+import json
+from json import JSONDecodeError
+import subprocess
+from subprocess import CalledProcessError
+from datetime import datetime
+import re
+
+#############################################
+# Configuration variables
+EXPORT = dict()
+EXPORT['DOC_WIDTH'] = 70
+
+#############################################
+# Function definitions
+def format_entry(entry):
+ try:
+ completed_proc = subprocess.run(["fmt","-w", str(EXPORT['DOC_WIDTH'])],
+ check=True,
+ input=entry['text'].encode('UTF-8'),
+ capture_output=True)
+ # Prefix each line of highlight with a pipe and space, eg.:
+ # | example of highlight
+ # Learned about re.sub from distutils/command/install_egg_info.py
+ highlight = "\n".join(re.sub('^', '| ', completed_proc.stdout.decode('UTF-8'))\
+ .replace("\n","\n| ")\
+ .split("\n")[:-1])
+ chapter = "Chapter: " + entry['chapter']
+ date = "Date: " + datetime.fromtimestamp(entry['time'])\
+ .strftime('%Y-%m-%d')
+ # Learned this function with the % from /usr/lib/python.../timeit.py
+ # which I found through find . -type f -name "*.py" |
+ # xargs -n 1 grep -Hn "map"
+ return "%s\n%s\n%s\n" % (date, highlight, chapter)
+ except CalledProcessError as e:
+ print("CalledProcessError:", e)
+ except Exception as e:
+ print("Exception", e)
+
+def format_document(document):
+ formatted_document = []
+ try:
+ completed_proc = subprocess.run(["sed", "-E", "s/[^a-zA-Z0-9?=&\-\ ]//g"],
+ check=True,
+ input=document['title'].encode('UTF-8'),
+ capture_output=True)
+ document['filename'] = completed_proc.stdout\
+ .decode('UTF-8')\
+ .lower()\
+ .replace(' ', '_')
+ except CalledProcessError as e:
+ print("Exception:", e)
+
+ document['link_label'] = document['title']
+ document['entries'] = map(format_entry,
+ list(document['entries']))
+ # Trim link label to doc size
+ # document['link_label'] = document['title'][:EXPORT['DOC_WIDTH']] + "..."
+ return document
+
+#############################################
+# Main control flow
+# # The program starts here.
+#
+# Collect the standard input into a string.
+strin = ""
+documents = []
+for line in fileinput.input(encoding="utf-8"):
+ strin += line
+
+try:
+ documents = json.loads(strin)['documents']
+except JSONDecodeError as e:
+ print("Error decoding JSON. Exiting.",
+ f'{e.msg=} {e.pos=} {e.lineno=}')
+ exit
+
+for document in list(map(format_document, documents)):
+ print("\n#",document['title'])
+ print("\n\n".join(document['entries']))