feat(books): start collection

.gitmodules

@@ -4,3 +4,12 @@
 [submodule "blog"]
 	path = blog
 	url = https://sauce.pizzawednes.day/ktyl/blog.git
+[submodule "journal"]
+	path = sr/garden/journal
+	url = git@sauce.pizzawednes.day:ktyl/journal.git
+[submodule "src/garden/period3.xyz"]
+	path = src/garden/period3.xyz
+	url = git@sauce.pizzawedney.day:ktyl/period3.xyz
+[submodule "src/garden/journal"]
+	path = src/garden/journal
+	url = git@sauce.pizzawednes.day:ktyl/journal

src/garden/book-collecting.md

@@ -0,0 +1,106 @@
+how do you define a book collection?
+my book collection is the set of all books.
+
+i prefer physical books to e-readers.
+unfortunately i have quite a few these days.
+
+i want to read them all eventually!
+i also tend to live in quite small places
+and i want to be able to move city easily!
+
+so here's my system for organising my physical book collection.
+
+i want to:
+*   read books i already have
+*   read as many different books as possible
+*   minimise physical storage requirements
+*   keep track of books i've read
+*   gather books i don't already have
+
+constraints
+*   i don't know for sure what book i will want to read next
+
+for every book in the world
+*   i either have or have not read it
+*   i have access to it or i don't
+
+so i sort my book collection with 4 categories
+
+*-------------------*-----------------------*
+|                   |                       |
+|       unread      |          read         |
+|        have       |          have         |
+|                   |                       |
+|   37º2 le matin   |   L'Homme des Jeux    |
+|                   |                       |
+*-------------------*-----------------------*
+|                   |                       |
+|       unread      |         read          |
+|       haven't     |        haven't        |
+|                   |                       |
+|    Das Kapital    |      Frankisstein     |
+|                   |                       |
+*-------------------*-----------------------*
+
+i can then begin to optimise my collection.
+
+*   i do not have this book, and i have read it.
+*   i have this book, but i have not read it.
+*   i have this book, and i have read it.
+*   i do not have this book, but i have not read it.
+
+the books i am most interested in having nearby are unread ones, as i would like to read as many different books as possible.
+
+books i have already read i don't need nearby anymore.
+i might pass it on, or store it somewhere with less of a premium on space.
+i could also attempt to track where it is!
+
+based on my requirements and my categories, i create four lists for the books
+
+*   ready
+*   all done
+*   read and gone
+*   hunted
+
+that looks like a decent start to the system, so i suppose now i'll start collecting!
+
+so i'll use markdown lists in the format
+
+```
+* [x] author - title    # reading
+* [ ] author - title    # nearby
+```
+when collecting music i use artist - year - name
+however, publication year is an extra step that will slow data entry, so won't use this to start with - i have a lot of books
+
+i realised i had a gpt-4 sub and that it could look at pictures now so i gave it a go
+i fed it some photos and some formatting preferences and i got out perfect markdown lists
+
+```
+- [ ] Doctorow, Cory - Walkaway
+- [ ] Ferreira, Pedro G. - The Perfect Theory
+- [ ] Hadfield, Chris - An Astronaut's Guide to Life on Earth
+- [ ] Heinlein, Robert A. - Beyond This Horizon
+```
+
+books are lovely are great to look at, but the mishmash of fonts and presentation are a nightmare for indexing.
+now we have some good and lovely metadata :)
+this is an imperfect method, as the only way i can check it is still by combing through the physical books manually
+but it does let me target my combing after identifying problems in the index
+and in the meantime gives us a bunch of data to play with
+
+markdown lists also allow me to mark some items in a list
+this is looks flexible, so i think in my 'ready' list i will mark which book(s) i am currently reading
+
+```
+- [ ] Doctorow, Cory - Walkaway
+- [ ] Ferreira, Pedro G. - The Perfect Theory
+- [ ] Hadfield, Chris - An Astronaut's Guide to Life on Earth
+- [ ] Heinlein, Robert A. - Beyond This Horizon
+```
+
+the other lists i will leave unmarked for now, until i think of something to do with them.
+
+as for doing things with them, i wrote a [python script](#) which processes the data in the now-populated all-done and ready lists to yield some interesting (?) and fun (?) results?
+
+[example output](#)

src/garden/books.py

@@ -0,0 +1,87 @@
+import sys
+import os
+import re
+
+def print_usage():
+    print(f"usage: python {sys.argv[0]} DIR")
+    print(f"")
+    print(f"\tDIR\tdirectory containing markdown lists in files.")
+
+
+if len(sys.argv) != 2:
+    print_usage()
+    exit(1)
+
+base_path = os.path.abspath(sys.argv[1])
+ready_list_name = "ready.md"
+done_list_name = "all-done.md"
+
+def get_path(list_name : str) -> str:
+    return os.path.join(base_path, list_name)
+
+
+def get_matches(list_name : str) -> list[re.Match]:
+    # Matches a markdown list item
+    entry_pattern = re.compile(r"^[*-] \[([ *x])\] (.+) - (.+)")
+
+    matches = []
+    with open(get_path(list_name)) as f:
+        matches = [entry_pattern.match(l) for l in f.readlines()]
+    return [m for m in matches if m is not None]
+
+
+class Book:
+    def __init__(self, match : re.Pattern):
+        self.mark = match.group(1) != " "
+        self.author = match.group(2)
+        self.title = match.group(3)
+
+    def is_metadata_complete(self):
+        if not self.title or not self.author:
+            return False
+
+        if self.title == "???" or self.author == "???":
+            return False
+
+        return True
+
+    @staticmethod
+    def get_list(list_name : str, filter_partial_metadata = True) -> []:
+        books = [Book(m) for m in get_matches(list_name)] 
+
+        if filter_partial_metadata:
+            books = [b for b in books if b.is_metadata_complete()]
+
+        return books
+
+
+def print_section(title : str, books : list[str]):
+    print(f"# {title} ({len(books)})\n")
+
+    longest_title = max([len(b.title) for b in books])
+    title_column_width = longest_title + 2
+
+    for book in books:
+        row = [book.title, book.author]
+        format_str = "{: <" + str(title_column_width) + "} {: <20}"
+        print(format_str.format(*row))
+    print()
+
+def print_in_progress():
+    books = [b for b in Book.get_list(ready_list_name, False) if b.mark]
+    print_section("in progress", books)
+
+def print_completed():
+    books = Book.get_list(done_list_name)
+    print_section("up for borrowing", books)
+
+def print_partial_metadata():
+    books = Book.get_list(ready_list_name, False)
+    books += Book.get_list(done_list_name, False)
+    books = [b for b in books if not b.is_metadata_complete()]
+
+    print_section("metadata incomplete", books)
+
+print_in_progress()
+print_completed()
+print_partial_metadata()

src/garden/feed.py

@@ -5,21 +5,20 @@ import pathlib
 import sys
 import re
 import glob
+import os
 
 def print_usage():
     print("\nusage: python feed.py ROOT\n")
     print("\n")
     print("\t\ROOT\tbase folder")
 
-def validate():
-    # check args for at least one file path
-    if len(sys.argv) < 2:
+# check args for at most one file paths
+if len(sys.argv) > 2:
     print_usage()
     sys.exit(1)
 
-validate()
-
-base_folder = sys.argv[1]
+base_folder = sys.argv[1] if len(sys.argv) == 2 else os.getcwd()
+print(base_folder)
 
 def get_paths() -> [str]:
     return [x for x in glob.glob(f"{base_folder}/*.md")]
@@ -31,14 +30,20 @@ def get_text(path):
 #def to_html(md : str) -> str:
 #    return markdown.markdown(md, extensions=["fenced_code"])
 
+def get_title(md):
+    m = re.compile(r"^# (.+)\n").match(md)
+    if m is not None:
+        return m.groups(1)[0]
+
+    # truncated first line of file for auto-title
+    return md.splitlines()[0][0:30]
+
 def get_entry(path):
     return get_title(get_text(path))
 
-def get_title(md):
-    return re.compile(r"^# (.+)\n").match(md).group(1)
-
 def get_entries() -> [str]:
-    return "\n\n".join([get_entry(p) for p in get_paths()])
+    entries = [get_entry(p) for p in get_paths()]
+    return "\n\n".join(entries)
 
 def get_header() -> str:
     return """<?xml version="1.0" encoding="utf-8" ?>

src/garden/journal

@@ -0,0 +1 @@
+Subproject commit 95f85eaa95c875d2aa7897c0120f72bf31ade907