Merge pull request 'set up Alembic for handling database migrations' (#1) from alembic into dev

Reviewed-on: #1

.gitignore

@@ -16,3 +16,8 @@ target/
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
+
+# ignorable files in migrations/
+**/__pycache__
+migrations/env/
+migrations/test_db.sqlite

Cargo.lock

@@ -0,0 +1,7 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 4
+
+[[package]]
+name = "outline-rs"
+version = "0.1.0"

Cargo.toml

@@ -0,0 +1,9 @@
+[package]
+name = "outline-rs"
+version = "0.1.0"
+edition = "2024"
+
+[dependencies]
+
+[lib]
+

README.md

@@ -1,2 +1,16 @@
-# outline-rs
+# Outline-rs
 
+lightweight relational database-backed personal knowledge management outliner
+
+*Very* under construction!
+
+## Motivation
+
+Two PKM apps I've tried use Electron frontends, and I want a library that can
+back different frontends depending on the environment. I have been
+using a low-power ARM laptop recently and I can't be running a whole browser
+engine just to take notes.
+Also, containing all note data in a database will allow for extending with
+sync servers as a first-class experience rather than an afterthought.
+
+Using this as a project to learn rust as I go.

migrations/alembic.ini

@@ -0,0 +1,149 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts.
+# this is typically a path given in POSIX (e.g. forward slashes)
+# format, relative to the token %(here)s which refers to the location of this
+# ini file
+script_location = %(here)s/alembic
+
+# template used to generate migration file names; The default value is %%(rev)s_%%(slug)s
+# Uncomment the line below if you want the files to be prepended with date and time
+# see https://alembic.sqlalchemy.org/en/latest/tutorial.html#editing-the-ini-file
+# for all available tokens
+# file_template = %%(year)d_%%(month).2d_%%(day).2d_%%(hour).2d%%(minute).2d-%%(rev)s_%%(slug)s
+# Or organize into date-based subdirectories (requires recursive_version_locations = true)
+# file_template = %%(year)d/%%(month).2d/%%(day).2d_%%(hour).2d%%(minute).2d_%%(second).2d_%%(rev)s_%%(slug)s
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.  for multiple paths, the path separator
+# is defined by "path_separator" below.
+prepend_sys_path = .
+
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the tzdata library which can be installed by adding
+# `alembic[tz]` to the pip requirements.
+# string value is passed to ZoneInfo()
+# leave blank for localtime
+# timezone =
+
+# max length of characters to apply to the "slug" field
+# truncate_slug_length = 40
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+# set to 'true' to allow .pyc and .pyo files without
+# a source .py file to be detected as revisions in the
+# versions/ directory
+# sourceless = false
+
+# version location specification; This defaults
+# to <script_location>/versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path.
+# The path separator used here should be the separator specified by "path_separator"
+# below.
+# version_locations = %(here)s/bar:%(here)s/bat:%(here)s/alembic/versions
+
+# path_separator; This indicates what character is used to split lists of file
+# paths, including version_locations and prepend_sys_path within configparser
+# files such as alembic.ini.
+# The default rendered in new alembic.ini files is "os", which uses os.pathsep
+# to provide os-dependent path splitting.
+#
+# Note that in order to support legacy alembic.ini files, this default does NOT
+# take place if path_separator is not present in alembic.ini.  If this
+# option is omitted entirely, fallback logic is as follows:
+#
+# 1. Parsing of the version_locations option falls back to using the legacy
+#    "version_path_separator" key, which if absent then falls back to the legacy
+#    behavior of splitting on spaces and/or commas.
+# 2. Parsing of the prepend_sys_path option falls back to the legacy
+#    behavior of splitting on spaces, commas, or colons.
+#
+# Valid values for path_separator are:
+#
+# path_separator = :
+# path_separator = ;
+# path_separator = space
+# path_separator = newline
+#
+# Use os.pathsep. Default configuration used for new projects.
+path_separator = os
+
+# set to 'true' to search source files recursively
+# in each "version_locations" directory
+# new in Alembic version 1.10
+# recursive_version_locations = false
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+# database URL.  This is consumed by the user-maintained env.py script only.
+# other means of configuring database URLs may be customized within the env.py
+# file.
+sqlalchemy.url = sqlite+pysqlite:///test_db.sqlite
+
+
+[post_write_hooks]
+# post_write_hooks defines scripts or Python functions that are run
+# on newly generated revision scripts.  See the documentation for further
+# detail and examples
+
+# format using "black" - use the console_scripts runner, against the "black" entrypoint
+# hooks = black
+# black.type = console_scripts
+# black.entrypoint = black
+# black.options = -l 79 REVISION_SCRIPT_FILENAME
+
+# lint with attempts to fix using "ruff" - use the module runner, against the "ruff" module
+# hooks = ruff
+# ruff.type = module
+# ruff.module = ruff
+# ruff.options = check --fix REVISION_SCRIPT_FILENAME
+
+# Alternatively, use the exec runner to execute a binary found on your PATH
+# hooks = ruff
+# ruff.type = exec
+# ruff.executable = ruff
+# ruff.options = check --fix REVISION_SCRIPT_FILENAME
+
+# Logging configuration.  This is also consumed by the user-maintained
+# env.py script only.
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARNING
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARNING
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers =
+qualname = alembic
+
+[handler_console]
+class = StreamHandler
+args = (sys.stderr,)
+level = NOTSET
+formatter = generic
+
+[formatter_generic]
+format = %(levelname)-5.5s [%(name)s] %(message)s
+datefmt = %H:%M:%S

migrations/alembic/README

@@ -0,0 +1 @@
+Generic single-database configuration.

migrations/alembic/env.py

@@ -0,0 +1,78 @@
+from logging.config import fileConfig
+
+from sqlalchemy import engine_from_config
+from sqlalchemy import pool
+
+from alembic import context
+
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
+config = context.config
+
+# Interpret the config file for Python logging.
+# This line sets up loggers basically.
+if config.config_file_name is not None:
+    fileConfig(config.config_file_name)
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+# from myapp import mymodel
+# target_metadata = mymodel.Base.metadata
+target_metadata = None
+
+# other values from the config, defined by the needs of env.py,
+# can be acquired:
+# my_important_option = config.get_main_option("my_important_option")
+# ... etc.
+
+
+def run_migrations_offline() -> None:
+    """Run migrations in 'offline' mode.
+
+    This configures the context with just a URL
+    and not an Engine, though an Engine is acceptable
+    here as well.  By skipping the Engine creation
+    we don't even need a DBAPI to be available.
+
+    Calls to context.execute() here emit the given string to the
+    script output.
+
+    """
+    url = config.get_main_option("sqlalchemy.url")
+    context.configure(
+        url=url,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def run_migrations_online() -> None:
+    """Run migrations in 'online' mode.
+
+    In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+    connectable = engine_from_config(
+        config.get_section(config.config_ini_section, {}),
+        prefix="sqlalchemy.",
+        poolclass=pool.NullPool,
+    )
+
+    with connectable.connect() as connection:
+        context.configure(
+            connection=connection, target_metadata=target_metadata
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

migrations/alembic/script.py.mako

@@ -0,0 +1,28 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision: str = ${repr(up_revision)}
+down_revision: Union[str, Sequence[str], None] = ${repr(down_revision)}
+branch_labels: Union[str, Sequence[str], None] = ${repr(branch_labels)}
+depends_on: Union[str, Sequence[str], None] = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    ${downgrades if downgrades else "pass"}

migrations/alembic/versions/040713502ba4_initial_outline_rs_schema.py

@@ -0,0 +1,48 @@
+"""initial outline-rs schema
+
+Revision ID: 040713502ba4
+Revises: 
+Create Date: 2026-03-30 10:47:36.255978
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+
+# revision identifiers, used by Alembic.
+revision: str = '040713502ba4'
+down_revision: Union[str, Sequence[str], None] = None
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+
+    # block table holds individual bullet points in the outline
+    op.create_table(
+        "blocks",
+        sa.Column("id", sa.INTEGER, primary_key=True),
+        sa.Column("first_child_id", sa.INTEGER, sa.schema.ForeignKey("blocks.id")),
+        sa.Column("next_sibling_id", sa.INTEGER, sa.schema.ForeignKey("blocks.id")),
+        sa.Column("page_id", sa.INTEGER, sa.schema.ForeignKey("pages.id"), index=True),
+        sa.Column("content", sa.types.UnicodeText)
+    )
+
+    op.create_table(
+        "pages",
+        sa.Column("id", sa.INTEGER, primary_key=True),
+        sa.Column("root_block_id", sa.INTEGER, sa.schema.ForeignKey("blocks.id")),
+        sa.Column("title", sa.types.UnicodeText)
+    )
+    pass
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    op.drop_table("blocks")
+    op.drop_table("pages")
+    pass

migrations/requirements.txt

@@ -0,0 +1,2 @@
+alembic
+

rustseq/Cargo.lock

@@ -1,111 +0,0 @@
-# This file is automatically @generated by Cargo.
-# It is not intended for manual editing.
-version = 4
-
-[[package]]
-name = "bitflags"
-version = "2.9.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5c8214115b7bf84099f1309324e63141d4c5d7cc26862f97a0a857dbefe165bd"
-
-[[package]]
-name = "fallible-iterator"
-version = "0.3.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2acce4a10f12dc2fb14a218589d4f1f62ef011b2d0cc4b3cb1bba8e94da14649"
-
-[[package]]
-name = "fallible-streaming-iterator"
-version = "0.1.9"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7360491ce676a36bf9bb3c56c1aa791658183a54d2744120f27285738d90465a"
-
-[[package]]
-name = "foldhash"
-version = "0.1.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d9c4f5dac5e15c24eb999c26181a6ca40b39fe946cbe4c263c7209467bc83af2"
-
-[[package]]
-name = "hashbrown"
-version = "0.15.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bf151400ff0baff5465007dd2f3e717f3fe502074ca563069ce3a6629d07b289"
-dependencies = [
- "foldhash",
-]
-
-[[package]]
-name = "hashlink"
-version = "0.10.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7382cf6263419f2d8df38c55d7da83da5c18aef87fc7a7fc1fb1e344edfe14c1"
-dependencies = [
- "hashbrown",
-]
-
-[[package]]
-name = "libsqlite3-sys"
-version = "0.32.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fbb8270bb4060bd76c6e96f20c52d80620f1d82a3470885694e41e0f81ef6fe7"
-dependencies = [
- "pkg-config",
- "vcpkg",
-]
-
-[[package]]
-name = "pkg-config"
-version = "0.3.32"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7edddbd0b52d732b21ad9a5fab5c704c14cd949e5e9a1ec5929a24fded1b904c"
-
-[[package]]
-name = "rusqlite"
-version = "0.34.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "37e34486da88d8e051c7c0e23c3f15fd806ea8546260aa2fec247e97242ec143"
-dependencies = [
- "bitflags",
- "fallible-iterator",
- "fallible-streaming-iterator",
- "hashlink",
- "libsqlite3-sys",
- "smallvec",
-]
-
-[[package]]
-name = "rustseq"
-version = "0.1.0"
-dependencies = [
- "rusqlite",
- "streaming-iterator",
- "tree_iterators_rs",
-]
-
-[[package]]
-name = "smallvec"
-version = "1.15.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8917285742e9f3e1683f0a9c4e6b57960b7314d0b08d30d1ecd426713ee2eee9"
-
-[[package]]
-name = "streaming-iterator"
-version = "0.1.9"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2b2231b7c3057d5e4ad0156fb3dc807d900806020c5ffa3ee6ff2c8c76fb8520"
-
-[[package]]
-name = "tree_iterators_rs"
-version = "3.1.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "93243e2901d558d73622302dfb013dc698e291a707a423435cd5feb8805b966f"
-dependencies = [
- "streaming-iterator",
-]
-
-[[package]]
-name = "vcpkg"
-version = "0.2.15"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "accd4ea62f7bb7a82fe23066fb0957d48ef677f6eeb8215f372f52e48bb32426"

rustseq/Cargo.toml

@@ -1,9 +0,0 @@
-[package]
-name = "rustseq"
-version = "0.1.0"
-edition = "2024"
-
-[dependencies]
-rusqlite = "0.34.0"
-streaming-iterator = "0.1.9"
-tree_iterators_rs = "3.1.0"

rustseq/src/db.rs

@@ -1,140 +0,0 @@
-use std::result;
-
-use rusqlite;
-
-pub struct DB {
-    connection: rusqlite::Connection
-}
-
-impl DB {
-    pub fn connect(path: &str) -> Self {
-        let connection = rusqlite::Connection::open(path).expect("failed to open DB");
-        DB {
-            connection: connection
-        }
-    }
-
-    pub fn create_tables(&self) {
-        self.connection.execute_batch(
-            "CREATE TABLE blocks (
-            id	INTEGER NOT NULL UNIQUE,
-            content	TEXT,
-            parent	INTEGER,
-            next_sibling	INTEGER,
-            page INTEGER,
-            PRIMARY KEY(id AUTOINCREMENT),
-            FOREIGN KEY(next_sibling) REFERENCES blocks(id) ON DELETE SET NULL,
-            FOREIGN KEY(parent) REFERENCES blocks(id) ON DELETE SET NULL
-            FOREIGN KEY(page) REFERENCES pages(id) ON DELETE SET NULL);
-            
-            CREATE TABLE pages (
-            id INTEGER NOT NULL UNIQUE,
-            title TEXT,
-            first_block INTEGER,
-            PRIMARY KEY(id AUTOINCREMENT));
-            ").expect("failed to create table");
-    }
-
-    /// insert a new block into the database, and get back its ID
-    pub fn insert_block(&mut self, new_block: &mut BlockRow) -> Result<i64, rusqlite::Error> {
-
-        let transaction = self.connection.transaction()?;
-
-        transaction.execute("INSERT INTO blocks (content, parent, next_sibling, page) VALUES (?1, ?2, ?3, ?4);", 
-                            (&new_block.content, &new_block.parent_id, &new_block.sibling_id, &new_block.page_id))?;
-
-        new_block.id = Some(transaction.last_insert_rowid());
-        transaction.commit()?;
-
-        Ok(new_block.id.expect("no block ID"))  
-    }
-
-    pub fn update_block(&mut self, updated_block: &BlockRow) -> Result<(), rusqlite::Error> {
-        let transaction = self.connection.transaction()?;
-
-        transaction.execute("UPDATE blocks SET content=?1, parent=?2, next_sibling=?3, page=?4 WHERE id=?5",
-            (&updated_block.content, updated_block.parent_id, updated_block.sibling_id, updated_block.page_id, updated_block.id))?;
-
-        transaction.commit()?;
-
-        return Ok(());
-    }
-
-    /// insert a new page into the database, and get back its ID
-    pub fn insert_page(&mut self, new_page: &mut PageRow) -> Result<i64, rusqlite::Error> {
-        let transaction = self.connection.transaction()?;
-
-        transaction.execute("INSERT INTO pages (title, first_block) VALUES (?1, ?2);",
-                            (&new_page.title, &new_page.root_block_id))?;
-
-        new_page.id = Some(transaction.last_insert_rowid());
-
-        transaction.commit()?;
-        Ok(new_page.id.expect("no page ID"))
-    }
-
-    pub fn update_page(&mut self, updated_page: &PageRow) -> Result<(), rusqlite::Error> {
-        let transaction = self.connection.transaction()?;
-
-        transaction.execute("UPDATE blocks SET title=?1, first_block=?2 WHERE id=?3",
-            (&updated_page.title, &updated_page.root_block_id))?;
-
-        transaction.commit()?;
-
-        return Ok(());
-    }
-
-    pub fn get_page_blocks(&mut self, page: &PageRow) -> Result<Vec<BlockRow>, rusqlite::Error> {
-        let transaction = self.connection.transaction()?;
-
-        let mut statement = transaction.prepare("SELECT * FROM blocks WHERE page=?1")?;
-
-        let rows = statement.query_map((page.id.unwrap(),), |row| {
-            Ok(BlockRow{
-                id: row.get(0)?,
-                content: row.get(1)?,
-                parent_id: row.get(2)?,
-                sibling_id: row.get(3)?,
-                page_id: row.get(4)?
-            })
-        })?;
-
-        let mut row_block_vector = Vec::new();
-
-        for row in rows {
-            row_block_vector.push(row.unwrap());
-        }
-
-        return Ok(row_block_vector);
-
-    }
-}
-
-/// a BlockRow is a direct translation of a block row from the 
-/// database. It will be used to create a tree of Block objects
-/// in memory.
-#[derive(Debug)]
-pub struct BlockRow {
-    pub id: Option<i64>,
-    pub content: String,
-
-    pub parent_id: Option<i64>,
-    pub sibling_id: Option<i64>,
-
-    pub page_id: Option<i64>
-}
-
-impl BlockRow {
-    pub fn new(content: &str, parent_id: Option<i64>, sibling_id: Option<i64>, page_id: Option<i64>) -> Self {
-        BlockRow { id: None, content: String::from(content), parent_id: parent_id, sibling_id: sibling_id, page_id: page_id }
-    }
-}
-
-#[derive(Debug)]
-pub struct PageRow {
-   pub id: Option<i64>,
-   pub title: String,
-
-   pub root_block_id: Option<i64> 
-}
-

rustseq/src/main.rs

@@ -1,68 +0,0 @@
-mod page;
-mod db;
-
-use std::fs;
-
-use db::{DB, PageRow, BlockRow};
-use page::Page;
-
-const TEST_DB_PATH: &str = "test_db.sqlite";
-
-fn init_test_db() -> DB {
-    // delete the existing test db
-    fs::remove_file(TEST_DB_PATH).unwrap_or_default();
-
-    // connect to the DB which creates the file
-    let database = DB::connect(TEST_DB_PATH);
-
-    // run SQL to create the tables defined for rustseq
-    database.create_tables();
-
-    return database;
-}
-
-fn main() {
-    let mut database = init_test_db();
-
-    // put a page in the database
-    let mut page_row = PageRow{id: None, title: String::from("test page"), root_block_id: None};
-    database.insert_page(&mut page_row).unwrap();
-
-    // put some blocks in the database
-    let mut block1 = BlockRow::new("Hello World", None, None, page_row.id);
-    let mut block2 = BlockRow::new("This is a child block", None, None, page_row.id);
-    let mut block3 = BlockRow::new("this is a sibling", None, None, page_row.id);
-    let mut block4 = BlockRow::new("this is a sub-sibling", None, None, page_row.id);
-
-    
-    database.insert_block(&mut block1).unwrap();
-    database.insert_block(&mut block2).unwrap();
-    database.insert_block(&mut block3).unwrap();
-    database.insert_block(&mut block4).unwrap();
-
-    block2.parent_id = block1.id;
-    block3.parent_id = block1.id;
-    block4.parent_id = block3.id;
-
-    //        1
-    //      /  \
-    //     2    3
-    //         / 
-    //        4
-
-    database.update_block(&block2).unwrap();
-    database.update_block(&block3).unwrap();
-    database.update_block(&block4).unwrap();
-
-    // get the page's blocks from the database
-    let page_blocks = database.get_page_blocks(&page_row).unwrap();
-
-    println!("{:#?}", page_blocks);
-
-    // put those blocks into the Page tree structure
-    let mut internal_page = Page::new(page_row, page_blocks);
-    internal_page.build_tree();
-    // internal_page.set_root_block(internal_page.get_block_data_ref()[0].id);
-    internal_page.print_tree();
-
-}

rustseq/src/page.rs

@@ -1,244 +0,0 @@
-
-use std::{collections::HashMap};
-
-
-use tree_iterators_rs::prelude::*;
-use streaming_iterator::StreamingIteratorMut;
-
-use crate::db::{BlockRow, PageRow};
-
-/// A page is represented by a page object from the
-/// database, and a tree of block objects with the data
-/// for each node contained in the block_data `HashMap`
-#[derive(Debug)]
-pub struct Page {
-    page_data: PageRow,
-    block_data: HashMap<i64, BlockRow>,
-    block_tree: Tree<i64>,
-}
-
-impl Page {
-    pub fn new(page_row: PageRow, block_data: Vec<BlockRow>) -> Self {
-
-        let mut block_map = HashMap::new();
-        
-        for block in block_data.into_iter() {
-            block_map.insert(block.id.unwrap(), block);
-        }
-        
-        Page {
-            page_data: page_row,
-            block_data: block_map,
-            block_tree: Tree {
-                value: 0,
-                children: Vec::new()
-            }
-        }
-    }
-
-    /// create a tree of `Tree<usize>` nodes representing the blocks of the page.
-    /// Each node contains the ID of a block and a vector of child `Tree<usize>`
-    /// nodes.
-    pub fn build_tree(&mut self) {
-
-        let leaf_block_ids = self.get_leaves();
-
-        // key is tree parent ID, value is the subtree itself
-        let mut leaves: Vec<Tree<i64>> = Vec::new();
-
-        // each leaf block becomes a Tree node owned by the leaves vector
-        for block_id in leaf_block_ids {
-            leaves.push(
-                Tree {
-                    value: block_id,
-                    children: Vec::new()
-                }
-            );
-        }
-
-        // vector of complete subtrees
-        let mut subtrees: Vec<Tree<i64>> = Vec::new();
-
-        // store which subtree each block's node is in
-        // key: block id, value: subtree vector index
-        let mut known_nodes: HashMap<i64, usize> = HashMap::new();
-
-        // OK, now try for each leaf getting to the root before going to another leaf
-        // subtrees from `subtrees` will be joined into new subtrees here
-        // attach subtrees to their parents up until they reach the root
-
-        // Take the leaf from the vector
-        for (subtree_index, leaf) in leaves.into_iter().enumerate() {
-            // go from the leaf until reaching the root or until reaching an already visited node
-            let mut current_node_opt: Option<Tree<i64>> = Some(leaf);
-
-            while let Some(ref current_node) = current_node_opt {
-                // build the subtree up until reaching the root or a known node
-
-                // store the current node value in the known_nodes map
-                known_nodes.insert(current_node.value, subtree_index);
-
-                // get the block data of the current node
-                let current_node_block_data = self.block_data.get(&current_node.value).expect("the current node must refer to a block in block_data");
-
-                // the parent ID is a value, and if not it's a child of the root node
-                let parent_id_opt = current_node_block_data.parent_id;
-
-                match parent_id_opt {
-                    Some(parent_id) => {
-                        // we are not yet at the root node
-                        // is the parent node a known node?
-                        if let Some(known_node_subtree_index) = known_nodes.get(&parent_id) {
-                            // iterate the indicated subtree to find the node, append the current node
-                            // to its children and break
-                            let known_node_subtree = subtrees.get_mut(*known_node_subtree_index).expect("if it's a known node, the subtree must exist in subtrees");
-                            let mut known_node_iter = known_node_subtree.dfs_preorder_iter_mut().attach_context();
-
-                            while let Some(context) = known_node_iter.next_mut() {
-
-                                // the context ancestors field includes the current node's value
-                                let current_node_value = context.ancestors().last().unwrap();
-                                if **current_node_value !=  parent_id { continue; }
-
-                                let children = context.children_mut();
-                                children.push(current_node.clone());
-                                current_node_opt = None;
-                                break;
-                            }
-
-                        } else {
-                            // create the parent node, update current_node and continue
-                            let parent_node = Tree {
-                                value: parent_id,
-                                children: vec![current_node.clone()]
-                            };
-
-                            current_node_opt = Some(parent_node);
-                        }
-                    }
-                    None => {
-                        // the current node is a child of the root node
-                        // store this subtree in subtrees
-                        subtrees.push(current_node.clone());
-                        break;
-                    }
-                    
-                }
-            }
-        }
-        //make all final subtrees the children of a single 0-value node
-        let mut root_node = Tree{value: 0, children: Vec::with_capacity(subtrees.len())};
-        for subtree in subtrees.into_iter() {
-            root_node.children.push(subtree);
-        }
-        let unsorted_tree = root_node;
-        // self.block_tree = self.sort_children(unsorted_tree);
-        self.block_tree = unsorted_tree;
-    }
-
-    /// traverse the tree depth-first and print the value of each node along the way
-    pub fn print_tree(&self) {
-        let nodes: Vec<&i64> = self.block_tree.dfs_preorder_iter().collect();
-        println!("{nodes:?}");
-    }
-
-    /// find the leaf nodes for the tree.
-    /// these are the blocks which no other block calls parent
-    fn get_leaves(&self) -> Vec<i64> {
-        // hash map containing child block ID vectors for each parent ID
-        let mut blocks_by_parent: HashMap<i64, Vec<i64>> = HashMap::new();
-
-        for (block_id, block) in self.block_data.iter() {
-            let parent_id = block.parent_id.unwrap_or(0);
-            if let None = blocks_by_parent.get_mut(&parent_id) {
-                blocks_by_parent.insert(parent_id, Vec::new());
-            }
-            blocks_by_parent.get_mut(&parent_id).unwrap().push(*block_id);
-        }
-
-        let mut leaf_block_ids = Vec::new();
-        
-        for (block_id, _block) in self.block_data.iter() {
-            // check that no block has this block as a parent
-            if let None = blocks_by_parent.get(block_id) {
-                leaf_block_ids.push(*block_id)
-            }
-        }
-
-        return leaf_block_ids;
-    }
-
-    /// iterate through the built tree and sort child nodes by their
-    /// next_sibling fields
-    /// return a properly sorted tree
-    fn sort_children(&self, mut built_tree: Tree<i64>) -> Tree<i64> {
-        let mut tree_iter = built_tree.dfs_preorder_iter_mut().attach_context();
-
-        // for each node in the tree, sort its children
-        while let Some(node) = tree_iter.next_mut() {
-            let children = node.children_mut();
-            let mut sorted_children = Vec::new();
-            // find the child with no next sibling
-            let last_sibling = children.iter().find(|node| {
-                self.block_data.get(&node.value).unwrap().sibling_id.is_none()
-            });
-            sorted_children.push(last_sibling);
-        }
-
-        Tree{value: 0, children:Vec::new()}
-    }
-
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    
-    fn setup_tree() -> Tree<i64> {
-        Tree{value: 1, children: vec![
-            Tree{value: 2, children: vec![]},
-            Tree{value: 3, children: vec![
-                Tree{value: 4, children: vec![]}
-            ]}
-        ]}
-    }
-
-    fn setup_blocks() -> Vec<BlockRow> {
-        vec![
-            BlockRow{id: Some(1), content: String::from("I'm block 1"), parent_id: None, sibling_id: None, page_id: None},
-            BlockRow{id: Some(2), content: String::from("I'm block 2"), parent_id: Some(1), sibling_id: Some(3), page_id: None},
-            BlockRow{id: Some(3), content: String::from("I'm block 3"), parent_id: Some(1), sibling_id: None, page_id: None},
-            BlockRow{id: Some(4), content: String::from("I'm block 4"), parent_id: Some(3), sibling_id: None, page_id: None},
-            BlockRow{id: Some(5), content: String::from("I'm block 5"), parent_id: None, sibling_id: Some(1), page_id: None}
-        ]
-    }
-
-    fn setup_page() -> Page {
-        Page::new(PageRow{id:None, title:String::from(""), root_block_id: None}, setup_blocks())
-    }
-
-    fn iterate_tree(page: &Page) -> Vec<i64> {
-        let tree = page.block_tree.clone();
-        tree.dfs_preorder().collect()
-    }
-
-    #[test]
-    fn all_nodes_in_tree() {
-        let mut page = setup_page();
-        page.build_tree();
-
-        // check the length of the iterated tree is equal to the number of blocks plus one for the root node
-        let iterated_tree = iterate_tree(&page);
-        assert_eq!(page.block_data.len() + 1, iterated_tree.len())
-    }
-
-    #[test]
-    fn tree_siblings_sorted() {
-        let mut page = setup_page();
-        page.build_tree();
-
-        let iterated_tree = iterate_tree(&page);
-        assert_eq!(vec![0, 5, 1, 2, 3, 4], iterated_tree);
-    }
-}

src/blocktree.rs

@@ -0,0 +1,163 @@
+
+use std::collections::HashMap;
+
+#[derive(Debug, Clone)]
+pub struct NoteBlock {
+    // IDs are int64 as this is the datatype of rowids in sqlite
+    id: i128,
+    pub first_child_id: Option<i128>,
+    pub next_sibling_id: Option<i128>,
+    
+    content: String
+}
+
+impl NoteBlock {
+    pub fn new(id: i128, first_child_id: Option<i128>, next_sibling_id: Option<i128>, content: String) -> Self {
+        Self {id, first_child_id, next_sibling_id, content}
+    }
+}
+
+#[derive(Debug)]
+pub struct BlockTreeNode {
+    // a tree of nodes, where each node refers to its block by id.
+    // the id is used as the key in a page's block table.
+    block_id: i128,
+    block_level: Option<usize>,
+    first_child_node: Option<Box<BlockTreeNode>>,
+    next_sibling_node: Option<Box<BlockTreeNode>>
+}
+
+impl BlockTreeNode {
+    fn new(block_id: i128) -> Self {
+        BlockTreeNode {
+            block_id,
+            block_level: None,
+            first_child_node: None,
+            next_sibling_node: None
+        }
+    }
+}
+
+pub struct BlockTreeIterator<'a> {
+    node_stack: Vec<&'a BlockTreeNode>
+}
+
+impl<'a> BlockTreeIterator<'a> {
+    pub fn new(root_node: &'a BlockTreeNode) -> Self {
+        Self {
+            node_stack: vec![root_node]
+        }
+    }
+}
+
+impl<'a> Iterator for BlockTreeIterator<'a> {
+    type Item = i128;
+    fn next(&mut self) -> Option<Self::Item> {
+
+        // stack is empty, we are done otherwise continue with current_node
+        let Some(current_node) = self.node_stack.pop() else {
+            return None;
+        };
+
+        // if the current node has a next sibling, stack it.
+        if let Some(next_sibling_node) = &current_node.next_sibling_node {
+            self.node_stack.push(next_sibling_node);
+        }
+
+        // if the current node has a first child, stack it.
+        if let Some(first_child_node) = &current_node.first_child_node {
+            self.node_stack.push(first_child_node);
+        }
+
+        // yield a clone of the block pointed to by current_node
+        Some(current_node.block_id)
+    }
+}
+
+#[derive(Debug)]
+pub struct NotePage {
+    title: String,
+    id: i128,
+    pub block_tree_root: BlockTreeNode,
+    
+    block_table: HashMap<i128, NoteBlock>
+}
+
+impl NotePage {
+    pub fn new(title: String, id: i128, root_block: NoteBlock) -> Self {
+        let mut new_page = Self {
+            title, 
+            id, 
+            block_tree_root: BlockTreeNode::new(root_block.id),
+            block_table: HashMap::new()
+        };
+        new_page.block_tree_root.block_level = Some(0);
+        new_page.block_table.insert(root_block.id, root_block);
+        new_page
+    }
+    
+    pub fn insert(self: &mut Self, block: NoteBlock) {
+        self.block_table.insert(block.id, block);
+    }
+    
+    pub fn build_tree(self: &mut Self) {
+        let mut node_stack = Vec::new();
+        node_stack.push(&mut self.block_tree_root);
+        while !node_stack.is_empty() {
+            println!("{:?}", node_stack);
+            let current_node = node_stack.pop().unwrap();
+            let current_block = self.block_table.get(&current_node.block_id).unwrap();
+            if let Some(next_sibling_id) = current_block.next_sibling_id {
+                let mut sibling_node = BlockTreeNode::new(next_sibling_id);
+                sibling_node.block_level = current_node.block_level;
+                current_node.next_sibling_node = Some(Box::new(sibling_node));
+                node_stack.push(current_node.next_sibling_node.as_mut().unwrap());
+            }
+            if let Some(first_child_id) = current_block.first_child_id {
+                let mut child_node = BlockTreeNode::new(first_child_id);
+                child_node.block_level = Some(current_node.block_level.unwrap() + 1);
+                current_node.first_child_node = Some(Box::new(child_node));
+                node_stack.push(current_node.first_child_node.as_mut().unwrap());
+            }
+        }
+    }
+}
+
+struct NotePageIterator<'a> {
+    page: &'a NotePage,
+    node_stack: Vec<&'a BlockTreeNode>
+}
+
+impl<'a> NotePageIterator<'a> {
+    fn new(page: &'a NotePage) -> Self {
+        Self {
+            page: page,
+            node_stack: vec![&page.block_tree_root]
+        }
+    }
+}
+
+impl<'a> Iterator for NotePageIterator<'a> {
+    type Item = NoteBlock;
+    fn next(&mut self) -> Option<Self::Item> {
+
+        // stack is empty, we are done otherwise continue with current_node
+        let Some(current_node) = self.node_stack.pop() else {
+            return None;
+        };
+
+        // if the current node has a next sibling, stack it.
+        if let Some(next_sibling_node) = &current_node.next_sibling_node {
+            self.node_stack.push(next_sibling_node);
+        }
+
+        // if the current node has a first child, stack it.
+        if let Some(first_child_node) = &current_node.first_child_node {
+            self.node_stack.push(first_child_node);
+        }
+
+        // yield a clone of the block pointed to by current_node
+        Some(self.page.block_table.get(&current_node.block_id).unwrap().clone())
+    }
+
+}

src/lib.rs

@@ -0,0 +1 @@
+pub mod blocktree;

src/main.rs

@@ -0,0 +1,44 @@
+use std::collections::HashMap;
+
+use outline_rs::blocktree::{NoteBlock, NotePage, BlockTreeIterator};
+
+fn main() {
+    let root_block = NoteBlock::new(0,Some(1),None,String::from("hello"));
+
+    let mut block_map = HashMap::new();
+    for idx in 1..=5 {
+        let new_block = NoteBlock::new(idx,None, None, String::from("I'm block {idx}"));
+        block_map.insert(idx,new_block);
+    }
+
+    let mut page = NotePage::new(String::from("page 1"), 0, root_block);
+
+    // take each new block and give it some children/siblings
+    let mut block1 = block_map.remove(&1).unwrap();
+    block1.next_sibling_id = Some(2);
+    page.insert(block1);
+
+    let mut block2 = block_map.remove(&2).unwrap();
+    block2.first_child_id = Some(3);
+    block2.next_sibling_id = Some(4);
+    page.insert(block2);
+
+    let mut block3 = block_map.remove(&3).unwrap();
+    page.insert(block3);
+
+    let mut block4 = block_map.remove(&4).unwrap();
+    block4.first_child_id = Some(5);
+    page.insert(block4);
+
+    let mut block5 = block_map.remove(&5).unwrap();
+    page.insert(block5);
+
+    page.build_tree();
+
+    println!("{:?}", page);
+//    println!("{:?}", page.block_tree_root.first_child_node)
+    let iter = BlockTreeIterator::new(&page.block_tree_root);
+    for id in iter {
+        println!("{}", id);
+    }
+}