diary-md 0.1.1__py3-none-any.whl

diary_md/__init__.py

@@ -0,0 +1,25 @@
+"""diary-md: Tools for managing markdown-based diary entries."""
+
+from diary_md.exceptions import DiaryParseError
+from diary_md.exchange import EXCHANGE_RATES_TO_EUR, get_exchange_rate
+from diary_md.models import DateHeader, ExpenseLine
+from diary_md.parser import (
+    find_or_create_date_section,
+    find_section_end,
+    find_section_in_date,
+    markdown_to_dict,
+)
+
+__version__ = "0.1.0"
+
+__all__ = [
+    "DiaryParseError",
+    "DateHeader",
+    "ExpenseLine",
+    "get_exchange_rate",
+    "EXCHANGE_RATES_TO_EUR",
+    "markdown_to_dict",
+    "find_or_create_date_section",
+    "find_section_in_date",
+    "find_section_end",
+]

diary_md/_version.py

@@ -0,0 +1,34 @@
+# file generated by setuptools-scm
+# don't change, don't track in version control
+
+__all__ = [
+    "__version__",
+    "__version_tuple__",
+    "version",
+    "version_tuple",
+    "__commit_id__",
+    "commit_id",
+]
+
+TYPE_CHECKING = False
+if TYPE_CHECKING:
+    from typing import Tuple
+    from typing import Union
+
+    VERSION_TUPLE = Tuple[Union[int, str], ...]
+    COMMIT_ID = Union[str, None]
+else:
+    VERSION_TUPLE = object
+    COMMIT_ID = object
+
+version: str
+__version__: str
+__version_tuple__: VERSION_TUPLE
+version_tuple: VERSION_TUPLE
+commit_id: COMMIT_ID
+__commit_id__: COMMIT_ID
+
+__version__ = version = '0.1.1'
+__version_tuple__ = version_tuple = (0, 1, 1)
+
+__commit_id__ = commit_id = None

diary_md/cli/__init__.py

@@ -0,0 +1 @@
+"""CLI commands for diary-md."""

diary_md/cli/digest.py

@@ -0,0 +1,321 @@
+"""diary-digest: Analyze and extract information from diary files."""
+
+import fnmatch
+import json
+import re
+import sys
+from collections import defaultdict
+from pathlib import Path
+
+import click
+
+from diary_md.exceptions import DiaryParseError
+from diary_md.exchange import get_exchange_rate
+from diary_md.parser import markdown_to_dict, parse_diary_to_list
+
+DATE_FORMAT = "%Y-%m-%d"
+
+# Default config file location
+DEFAULT_CONFIG_FILE = Path.home() / ".config" / "diary-md" / "config.json"
+
+
+def load_config(config_file: Path | None = None) -> dict:
+    """Load configuration from JSON file.
+
+    Config format (simple):
+    {
+        "allowable_subsections": ["Expenses", "Maintenance", ...]
+    }
+
+    Config format (with diary-specific patterns):
+    {
+        "diary_configs": {
+            "**/solveig/*": {
+                "allowable_subsections": ["Expenses", "Maintenance", ...]
+            },
+            "**/furusetalle9/*": {
+                "allowable_subsections": ["Kostnader", "Tidsbruk", ...]
+            }
+        },
+        "allowable_subsections": ["default", "sections", "..."]
+    }
+    """
+    if config_file is None:
+        config_file = DEFAULT_CONFIG_FILE
+
+    if not config_file.exists():
+        return {}
+
+    try:
+        with open(config_file, encoding='utf-8') as f:
+            return json.load(f)
+    except (OSError, json.JSONDecodeError):
+        return {}
+
+
+def get_config_for_diary(cfg: dict, diary_path: str) -> dict:
+    """Get the configuration for a specific diary file.
+
+    Matches diary path against patterns in diary_configs.
+    Falls back to top-level config if no pattern matches.
+    """
+    diary_configs = cfg.get('diary_configs', {})
+
+    for pattern, diary_cfg in diary_configs.items():
+        if fnmatch.fnmatch(diary_path, pattern):
+            return diary_cfg
+
+    # Return top-level config as default
+    return cfg
+
+
+@click.group()
+@click.option('--start', help='Only show dates at or after this date', type=click.DateTime(formats=[DATE_FORMAT]))
+@click.option('--begin', 'start', help='alias for start', type=click.DateTime(formats=[DATE_FORMAT]))
+@click.option('--since', 'start', help='alias for start', type=click.DateTime(formats=[DATE_FORMAT]))
+@click.option('--from', 'start', help='alias for start', type=click.DateTime(formats=[DATE_FORMAT]))
+@click.option('--end', help='Only show dates up until and including this date', type=click.DateTime(formats=[DATE_FORMAT]))
+@click.option('--to', 'end', help='alias for end', type=click.DateTime(formats=[DATE_FORMAT]))
+@click.option('--until', 'end', help='alias for end', type=click.DateTime(formats=[DATE_FORMAT]))
+@click.option('--diary', type=click.File('r'), default=(sys.stdin,), multiple=True)
+@click.pass_context
+def digest(ctx, diary, start, end):
+    """Analyze and extract information from markdown diary files."""
+    ctx.ensure_object(dict)
+    ctx.obj['md_dict'] = {}
+    ctx.obj['diary_paths'] = []
+    for d in diary:
+        ctx.obj['md_dict'].update(markdown_to_dict(d))
+        # Track diary paths for config lookup
+        if hasattr(d, 'name') and d.name != '<stdin>':
+            ctx.obj['diary_paths'].append(d.name)
+    ctx.obj['diary_list'] = parse_diary_to_list(ctx.obj['md_dict'], start=start, end=end)
+
+
+@digest.command()
+@click.pass_context
+@click.option('--section', multiple=True, help='Section(s) to extract')
+def select_subsection(ctx, section):
+    """Extract specific subsections from diary entries."""
+    header = ""
+    for x in ctx.obj['diary_list']:
+        if x['trip'] != header:
+            click.echo(f"# {x['trip']}")
+            click.echo()
+            header = x['trip']
+        day_print = False
+        for s in section:
+            if s in x:
+                if not day_print:
+                    click.echo(f"## {x['dow']} {x['date']} {x['itenary']}")
+                    click.echo()
+                    day_print = True
+                click.echo(f"### {s}")
+                click.echo(x[s]['__content__'])
+
+
+@digest.command()
+@click.pass_context
+def export_json(ctx):
+    """Export diary as JSON."""
+    click.echo(json.dumps(ctx.obj['diary_list']))
+
+
+@digest.command()
+@click.pass_context
+@click.option('--config', type=click.Path(exists=True, path_type=Path),
+              help=f'Config file (default: {DEFAULT_CONFIG_FILE})')
+def find_all_subsections(ctx, config):
+    """Find all subsection titles used in the diary.
+
+    If a config file defines allowable_subsections, validates against that list.
+    Otherwise, just reports all found subsections.
+
+    Supports diary-specific configs with glob patterns in diary_configs section.
+    """
+    md_dict = ctx.obj['md_dict']
+    diary_paths = ctx.obj.get('diary_paths', [])
+
+    # Load config and get diary-specific settings
+    cfg = load_config(config)
+
+    # If we have diary paths, try to get diary-specific config
+    allowable_from_config = []
+    if diary_paths:
+        # Use first diary's config (could be enhanced to merge configs)
+        diary_cfg = get_config_for_diary(cfg, diary_paths[0])
+        allowable_from_config = diary_cfg.get('allowable_subsections', [])
+    else:
+        allowable_from_config = cfg.get('allowable_subsections', [])
+
+    # Always allow internal keys
+    allowable_subsection_titles = {'__content__', '__file_position__', '__file_name__'}
+    allowable_subsection_titles.update(allowable_from_config)
+
+    subsection_titles = set()
+
+    def _looks_like_date(key: str) -> bool:
+        """Check if key looks like a date header."""
+        import re
+        return bool(re.match(r'^[A-Za-zæøåÆØÅ]+ 20\d\d-\d\d-\d\d', key))
+
+    # Check if top-level keys are date headers (no trip wrapper)
+    non_meta_keys = [k for k in md_dict if not k.startswith('__')]
+    direct_dates = non_meta_keys and all(_looks_like_date(k) for k in non_meta_keys)
+
+    if direct_dates:
+        # Top-level is date headers directly
+        for day in md_dict:
+            if not isinstance(day, str) or day.startswith('__'):
+                continue
+            day_data = md_dict[day]
+            if not isinstance(day_data, dict):
+                continue
+            for subtitle in day_data:
+                if not isinstance(subtitle, str) or subtitle.startswith('__'):
+                    continue
+                subsection_titles.add(subtitle)
+                if allowable_from_config and subtitle not in allowable_subsection_titles:
+                    click.echo(f"Not allowed: {subtitle} in {day}")
+    else:
+        # Normal structure: trip headers containing date headers
+        for headline in md_dict:
+            if not isinstance(md_dict[headline], dict):
+                continue
+            for day in md_dict[headline]:
+                if not isinstance(day, str) or day.startswith('__'):
+                    continue
+                day_data = md_dict[headline][day]
+                if not isinstance(day_data, dict):
+                    continue
+                for subtitle in day_data:
+                    if not isinstance(subtitle, str) or subtitle.startswith('__'):
+                        continue
+                    subsection_titles.add(subtitle)
+                    if allowable_from_config and subtitle not in allowable_subsection_titles:
+                        click.echo(f"Not allowed: {subtitle} in {headline}->{day}")
+
+    if allowable_from_config:
+        user_allowable = set(allowable_from_config)
+        click.echo(f"Allowable, but missing: {user_allowable - subsection_titles!r}")
+        click.echo(f"Not allowable, but found: {subsection_titles - user_allowable!r}")
+    else:
+        click.echo(f"Found subsections: {subsection_titles!r}")
+        click.echo(f"(No config file found at {DEFAULT_CONFIG_FILE} - showing all found sections)")
+
+
+@digest.command()
+@click.pass_context
+def expenses(ctx):
+    """Summarize expenses from diary entries."""
+    unaccounted_content = []
+    accounted = []
+
+    for entry in ctx.obj['diary_list']:
+        if 'Expenses' not in entry:
+            continue
+
+        unaccounted = ""
+        if '__content__' not in entry['Expenses']:
+            raise DiaryParseError(
+                "Expenses section has no content",
+                file_name=entry.get('__file_name__'),
+                file_position=entry.get('__file_position__'),
+                section=f"{entry['dow']} {entry['date']} {entry.get('itenary', '')}",
+                date=entry['date']
+            )
+
+        expense_date = entry['date']  # YYYY-MM-DD format
+        expenses_text = entry['Expenses']['__content__'].strip().split('\n')
+
+        for expense in expenses_text:
+            if not unaccounted:
+                expense = expense.strip()
+                if not expense:
+                    continue
+            findings = re.match(r"^\* ([A-Z]{3}) (-?\d+(?:\.\d+)?) - (.*)$", expense)
+            if findings:
+                accounted.append((findings.group(1), findings.group(2), findings.group(3), expense_date))
+            else:
+                unaccounted += expense
+
+        if unaccounted:
+            unaccounted_content.append(f"## {entry['dow']} {entry['date']} {entry['itenary']}\n")
+            unaccounted_content.append(unaccounted)
+
+    base_currency = 'EUR'
+
+    my_expenses = 0
+    total_expenses = 0
+    shared_expenses_per_head = 0
+    paid_by = defaultdict(float)
+    expenses_by_category = defaultdict(float)
+    conversion_warnings = []
+
+    for expense in accounted:
+        (currency, amount, details, expense_date) = expense
+        amount = float(amount)
+
+        if currency != base_currency:
+            rate = get_exchange_rate(currency, expense_date)
+            if rate is None:
+                conversion_warnings.append(f"Unknown currency {currency} on {expense_date}")
+                continue
+            amount = amount * rate
+            currency = base_currency
+
+        total_expenses += amount
+        category = details.split(' - ')[0]
+        if ' (' in category:
+            category = category.split(' (')[0]
+
+        paidbyf = re.search(r"- paid by ([^ ]*)", details)
+        if paidbyf:
+            paid_by[paidbyf.group(1)] += amount
+
+        sharedf = re.search(r" - DIV(\d+)", details)
+        if sharedf:
+            divisor = int(sharedf.group(1))
+            amount /= divisor
+            shared_expenses_per_head += amount
+
+        expenses_by_category[category] += amount
+        my_expenses += amount
+
+    click.echo("# Unaccounted text under expenses (look through)")
+    click.echo()
+    click.echo("\n".join(unaccounted_content))
+    click.echo("# Expenses by payer")
+    click.echo()
+    for payer in paid_by:
+        click.echo(f" * {base_currency} {paid_by[payer]:5.2f} - {payer}")
+    click.echo()
+    click.echo("# Expenses by category")
+    click.echo()
+    categories = list(expenses_by_category.keys())
+    categories.sort(key=lambda x: expenses_by_category[x])
+    for cat in categories:
+        click.echo(f" * {base_currency} {expenses_by_category[cat]:5.2f} - {cat}")
+    click.echo()
+
+    if conversion_warnings:
+        click.echo("# Currency conversion warnings")
+        click.echo()
+        for warning in conversion_warnings:
+            click.echo(f" * {warning}")
+        click.echo()
+
+    click.echo("# Totals")
+    click.echo()
+    click.echo(f"Total expenses: {base_currency} {total_expenses:5.2f}")
+    click.echo(f"Shared expenses per head: {base_currency} {shared_expenses_per_head:5.2f}")
+    click.echo(f"My expenses: {base_currency} {my_expenses:5.2f}")
+
+
+def main():
+    """Entry point for diary-digest command."""
+    digest()
+
+
+if __name__ == '__main__':
+    main()