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
+

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);
+    }
+}