polar: minor improvements, konsume: more type annotations
This commit is contained in:
parent
f3d5064ff2
commit
0f27071dcc
4 changed files with 50 additions and 40 deletions
|
@ -134,7 +134,8 @@ def get_files(pp: Paths, glob: str=DEFAULT_GLOB, sort: bool=True) -> Tuple[Path,
|
||||||
warnings.warn(f"Treating {ss} as glob path. Explicit glob={glob} argument is ignored!")
|
warnings.warn(f"Treating {ss} as glob path. Explicit glob={glob} argument is ignored!")
|
||||||
paths.extend(map(Path, do_glob(ss)))
|
paths.extend(map(Path, do_glob(ss)))
|
||||||
else:
|
else:
|
||||||
assert src.is_file(), src
|
if not src.is_file():
|
||||||
|
raise RuntimeError(f"Expected '{src}' to exist")
|
||||||
# todo assert matches glob??
|
# todo assert matches glob??
|
||||||
paths.append(src)
|
paths.append(src)
|
||||||
|
|
||||||
|
|
|
@ -11,7 +11,7 @@ def zoom(w, *keys):
|
||||||
|
|
||||||
# TODO need to support lists
|
# TODO need to support lists
|
||||||
class Zoomable:
|
class Zoomable:
|
||||||
def __init__(self, parent, *args, **kwargs):
|
def __init__(self, parent, *args, **kwargs) -> None:
|
||||||
super().__init__(*args, **kwargs) # type: ignore
|
super().__init__(*args, **kwargs) # type: ignore
|
||||||
self.parent = parent
|
self.parent = parent
|
||||||
|
|
||||||
|
@ -21,19 +21,19 @@ class Zoomable:
|
||||||
def dependants(self):
|
def dependants(self):
|
||||||
raise NotImplementedError
|
raise NotImplementedError
|
||||||
|
|
||||||
def ignore(self):
|
def ignore(self) -> None:
|
||||||
self.consume_all()
|
self.consume_all()
|
||||||
|
|
||||||
def consume_all(self):
|
def consume_all(self) -> None:
|
||||||
for d in self.dependants:
|
for d in self.dependants:
|
||||||
d.consume_all()
|
d.consume_all()
|
||||||
self.consume()
|
self.consume()
|
||||||
|
|
||||||
def consume(self):
|
def consume(self) -> None:
|
||||||
assert self.parent is not None
|
assert self.parent is not None
|
||||||
self.parent._remove(self)
|
self.parent._remove(self)
|
||||||
|
|
||||||
def zoom(self):
|
def zoom(self) -> 'Zoomable':
|
||||||
self.consume()
|
self.consume()
|
||||||
return self
|
return self
|
||||||
|
|
||||||
|
@ -56,6 +56,8 @@ class Wdict(Zoomable, OrderedDict):
|
||||||
|
|
||||||
def this_consumed(self):
|
def this_consumed(self):
|
||||||
return len(self) == 0
|
return len(self) == 0
|
||||||
|
# TODO specify mypy type for the index special method?
|
||||||
|
|
||||||
|
|
||||||
class Wlist(Zoomable, list):
|
class Wlist(Zoomable, list):
|
||||||
def _remove(self, xx):
|
def _remove(self, xx):
|
||||||
|
@ -83,7 +85,8 @@ class Wvalue(Zoomable):
|
||||||
def __repr__(self):
|
def __repr__(self):
|
||||||
return 'WValue{' + repr(self.value) + '}'
|
return 'WValue{' + repr(self.value) + '}'
|
||||||
|
|
||||||
def _wrap(j, parent=None):
|
from typing import Tuple
|
||||||
|
def _wrap(j, parent=None) -> Tuple[Zoomable, List[Zoomable]]:
|
||||||
res: Zoomable
|
res: Zoomable
|
||||||
cc: List[Zoomable]
|
cc: List[Zoomable]
|
||||||
if isinstance(j, dict):
|
if isinstance(j, dict):
|
||||||
|
@ -109,13 +112,14 @@ def _wrap(j, parent=None):
|
||||||
raise RuntimeError(f'Unexpected type: {type(j)} {j}')
|
raise RuntimeError(f'Unexpected type: {type(j)} {j}')
|
||||||
|
|
||||||
from contextlib import contextmanager
|
from contextlib import contextmanager
|
||||||
|
from typing import Iterator
|
||||||
|
|
||||||
class UnconsumedError(Exception):
|
class UnconsumedError(Exception):
|
||||||
pass
|
pass
|
||||||
|
|
||||||
# TODO think about error policy later...
|
# TODO think about error policy later...
|
||||||
@contextmanager
|
@contextmanager
|
||||||
def wrap(j, throw=True):
|
def wrap(j, throw=True) -> Iterator[Zoomable]:
|
||||||
w, children = _wrap(j)
|
w, children = _wrap(j)
|
||||||
|
|
||||||
yield w
|
yield w
|
||||||
|
@ -128,28 +132,33 @@ def wrap(j, throw=True):
|
||||||
# TODO log?
|
# TODO log?
|
||||||
pass
|
pass
|
||||||
|
|
||||||
|
from typing import cast
|
||||||
def test_unconsumed():
|
def test_unconsumed():
|
||||||
import pytest # type: ignore
|
import pytest # type: ignore
|
||||||
with pytest.raises(UnconsumedError):
|
with pytest.raises(UnconsumedError):
|
||||||
with wrap({'a': 1234}) as w:
|
with wrap({'a': 1234}) as w:
|
||||||
|
w = cast(Wdict, w)
|
||||||
pass
|
pass
|
||||||
|
|
||||||
with pytest.raises(UnconsumedError):
|
with pytest.raises(UnconsumedError):
|
||||||
with wrap({'c': {'d': 2222}}) as w:
|
with wrap({'c': {'d': 2222}}) as w:
|
||||||
|
w = cast(Wdict, w)
|
||||||
d = w['c']['d'].zoom()
|
d = w['c']['d'].zoom()
|
||||||
|
|
||||||
def test_consumed():
|
def test_consumed():
|
||||||
with wrap({'a': 1234}) as w:
|
with wrap({'a': 1234}) as w:
|
||||||
|
w = cast(Wdict, w)
|
||||||
a = w['a'].zoom()
|
a = w['a'].zoom()
|
||||||
|
|
||||||
with wrap({'c': {'d': 2222}}) as w:
|
with wrap({'c': {'d': 2222}}) as w:
|
||||||
|
w = cast(Wdict, w)
|
||||||
c = w['c'].zoom()
|
c = w['c'].zoom()
|
||||||
d = c['d'].zoom()
|
d = c['d'].zoom()
|
||||||
|
|
||||||
def test_types():
|
def test_types():
|
||||||
# (string, number, object, array, boolean or nul
|
# (string, number, object, array, boolean or nul
|
||||||
with wrap({'string': 'string', 'number': 3.14, 'boolean': True, 'null': None, 'list': [1, 2, 3]}) as w:
|
with wrap({'string': 'string', 'number': 3.14, 'boolean': True, 'null': None, 'list': [1, 2, 3]}) as w:
|
||||||
|
w = cast(Wdict, w)
|
||||||
w['string'].zoom()
|
w['string'].zoom()
|
||||||
w['number'].consume()
|
w['number'].consume()
|
||||||
w['boolean'].zoom()
|
w['boolean'].zoom()
|
||||||
|
@ -159,5 +168,8 @@ def test_types():
|
||||||
|
|
||||||
def test_consume_all():
|
def test_consume_all():
|
||||||
with wrap({'aaa': {'bbb': {'hi': 123}}}) as w:
|
with wrap({'aaa': {'bbb': {'hi': 123}}}) as w:
|
||||||
|
w = cast(Wdict, w)
|
||||||
aaa = w['aaa'].zoom()
|
aaa = w['aaa'].zoom()
|
||||||
aaa['bbb'].consume_all()
|
aaa['bbb'].consume_all()
|
||||||
|
|
||||||
|
# TODO type check this...
|
||||||
|
|
|
@ -35,27 +35,20 @@ config = make_config(polar)
|
||||||
# https://github.com/burtonator/polar-bookshelf/issues/296
|
# https://github.com/burtonator/polar-bookshelf/issues/296
|
||||||
|
|
||||||
from datetime import datetime
|
from datetime import datetime
|
||||||
from typing import List, Dict, Iterator, NamedTuple, Sequence, Optional
|
from typing import List, Dict, Iterable, NamedTuple, Sequence, Optional
|
||||||
import json
|
import json
|
||||||
|
|
||||||
import pytz
|
import pytz
|
||||||
|
|
||||||
from ..core import get_files, LazyLogger
|
from ..core import LazyLogger, Json
|
||||||
|
from ..core.common import isoparse
|
||||||
from ..error import Res, echain, unwrap, sort_res_by
|
from ..error import Res, echain, sort_res_by
|
||||||
from ..kython.konsume import wrap, zoom, ignore
|
from ..kython.konsume import wrap, zoom, ignore, Zoomable, Wdict
|
||||||
|
|
||||||
|
|
||||||
logger = LazyLogger(__name__)
|
logger = LazyLogger(__name__)
|
||||||
|
|
||||||
|
|
||||||
# TODO use core.isoparse
|
|
||||||
def parse_dt(s: str) -> datetime:
|
|
||||||
return pytz.utc.localize(datetime.strptime(s, '%Y-%m-%dT%H:%M:%S.%fZ'))
|
|
||||||
|
|
||||||
Uid = str
|
|
||||||
|
|
||||||
|
|
||||||
# Ok I guess handling comment-level errors is a bit too much..
|
# Ok I guess handling comment-level errors is a bit too much..
|
||||||
Cid = str
|
Cid = str
|
||||||
class Comment(NamedTuple):
|
class Comment(NamedTuple):
|
||||||
|
@ -71,6 +64,8 @@ class Highlight(NamedTuple):
|
||||||
comments: Sequence[Comment]
|
comments: Sequence[Comment]
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
Uid = str
|
||||||
class Book(NamedTuple):
|
class Book(NamedTuple):
|
||||||
uid: Uid
|
uid: Uid
|
||||||
created: datetime
|
created: datetime
|
||||||
|
@ -80,8 +75,6 @@ class Book(NamedTuple):
|
||||||
# think about it later.
|
# think about it later.
|
||||||
items: Sequence[Highlight]
|
items: Sequence[Highlight]
|
||||||
|
|
||||||
Error = Exception # for backwards compat with Orger; can remove later
|
|
||||||
|
|
||||||
Result = Res[Book]
|
Result = Res[Book]
|
||||||
|
|
||||||
class Loader:
|
class Loader:
|
||||||
|
@ -89,12 +82,13 @@ class Loader:
|
||||||
self.path = p
|
self.path = p
|
||||||
self.uid = self.path.parent.name
|
self.uid = self.path.parent.name
|
||||||
|
|
||||||
def error(self, cause, extra='') -> Exception:
|
def error(self, cause: Exception, extra: str ='') -> Exception:
|
||||||
if len(extra) > 0:
|
if len(extra) > 0:
|
||||||
extra = '\n' + extra
|
extra = '\n' + extra
|
||||||
return echain(Exception(f'while processing {self.path}{extra}'), cause)
|
return echain(Exception(f'while processing {self.path}{extra}'), cause)
|
||||||
|
|
||||||
def load_item(self, meta) -> Iterator[Highlight]:
|
def load_item(self, meta: Zoomable) -> Iterable[Highlight]:
|
||||||
|
meta = cast(Wdict, meta)
|
||||||
# TODO this should be destructive zoom?
|
# TODO this should be destructive zoom?
|
||||||
meta['notes'].zoom()
|
meta['notes'].zoom()
|
||||||
meta['pagemarks'].zoom()
|
meta['pagemarks'].zoom()
|
||||||
|
@ -134,7 +128,7 @@ class Loader:
|
||||||
cmap[hlid] = ccs
|
cmap[hlid] = ccs
|
||||||
ccs.append(Comment(
|
ccs.append(Comment(
|
||||||
cid=cid.value,
|
cid=cid.value,
|
||||||
created=parse_dt(crt.value),
|
created=isoparse(crt.value),
|
||||||
text=html.value, # TODO perhaps coonvert from html to text or org?
|
text=html.value, # TODO perhaps coonvert from html to text or org?
|
||||||
))
|
))
|
||||||
v.consume()
|
v.consume()
|
||||||
|
@ -162,7 +156,7 @@ class Loader:
|
||||||
|
|
||||||
yield Highlight(
|
yield Highlight(
|
||||||
hid=hid,
|
hid=hid,
|
||||||
created=parse_dt(crt),
|
created=isoparse(crt),
|
||||||
selection=text,
|
selection=text,
|
||||||
comments=tuple(comments),
|
comments=tuple(comments),
|
||||||
)
|
)
|
||||||
|
@ -174,12 +168,12 @@ class Loader:
|
||||||
# TODO sort by date?
|
# TODO sort by date?
|
||||||
|
|
||||||
|
|
||||||
def load_items(self, metas) -> Iterator[Highlight]:
|
def load_items(self, metas: Json) -> Iterable[Highlight]:
|
||||||
for p, meta in metas.items():
|
for p, meta in metas.items():
|
||||||
with wrap(meta, throw=False) as meta:
|
with wrap(meta, throw=False) as meta:
|
||||||
yield from self.load_item(meta)
|
yield from self.load_item(meta)
|
||||||
|
|
||||||
def load(self) -> Iterator[Result]:
|
def load(self) -> Iterable[Result]:
|
||||||
logger.info('processing %s', self.path)
|
logger.info('processing %s', self.path)
|
||||||
j = json.loads(self.path.read_text())
|
j = json.loads(self.path.read_text())
|
||||||
|
|
||||||
|
@ -193,14 +187,15 @@ class Loader:
|
||||||
|
|
||||||
yield Book(
|
yield Book(
|
||||||
uid=self.uid,
|
uid=self.uid,
|
||||||
created=parse_dt(added),
|
created=isoparse(added),
|
||||||
filename=filename,
|
filename=filename,
|
||||||
title=title,
|
title=title,
|
||||||
items=list(self.load_items(pm)),
|
items=list(self.load_items(pm)),
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
def iter_entries() -> Iterator[Result]:
|
def iter_entries() -> Iterable[Result]:
|
||||||
|
from ..core import get_files
|
||||||
for d in get_files(config.polar_dir, glob='*/state.json'):
|
for d in get_files(config.polar_dir, glob='*/state.json'):
|
||||||
loader = Loader(d)
|
loader = Loader(d)
|
||||||
try:
|
try:
|
||||||
|
@ -213,16 +208,18 @@ def iter_entries() -> Iterator[Result]:
|
||||||
|
|
||||||
def get_entries() -> List[Result]:
|
def get_entries() -> List[Result]:
|
||||||
# sorting by first annotation is reasonable I guess???
|
# sorting by first annotation is reasonable I guess???
|
||||||
|
# todo perhaps worth making it a pattern? X() returns iterable, get_X returns reasonably sorted list?
|
||||||
return list(sort_res_by(iter_entries(), key=lambda e: e.created))
|
return list(sort_res_by(iter_entries(), key=lambda e: e.created))
|
||||||
|
|
||||||
|
|
||||||
def main():
|
def main():
|
||||||
for entry in iter_entries():
|
for e in iter_entries():
|
||||||
try:
|
if isinstance(e, Exception):
|
||||||
ee = unwrap(entry)
|
|
||||||
except Error as e:
|
|
||||||
logger.exception(e)
|
logger.exception(e)
|
||||||
else:
|
else:
|
||||||
logger.info('processed %s', ee.uid)
|
logger.info('processed %s', e.uid)
|
||||||
for i in ee.items:
|
for i in e.items:
|
||||||
logger.info(i)
|
logger.info(i)
|
||||||
|
|
||||||
|
|
||||||
|
Error = Exception # for backwards compat with Orger; can remove later
|
||||||
|
|
|
@ -1,6 +1,6 @@
|
||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
|
|
||||||
ROOT = Path(__file__).parent.parent.absolute()
|
ROOT = Path(__file__).parent.absolute()
|
||||||
|
|
||||||
|
|
||||||
import pytest # type: ignore
|
import pytest # type: ignore
|
||||||
|
@ -17,7 +17,7 @@ def test_hpi(dotpolar: str):
|
||||||
if dotpolar != '':
|
if dotpolar != '':
|
||||||
pdir = Path(ROOT / dotpolar)
|
pdir = Path(ROOT / dotpolar)
|
||||||
class user_config:
|
class user_config:
|
||||||
export_dir = pdir
|
polar_dir = pdir
|
||||||
|
|
||||||
import my.config
|
import my.config
|
||||||
setattr(my.config, 'polar', user_config)
|
setattr(my.config, 'polar', user_config)
|
||||||
|
@ -30,4 +30,4 @@ def test_hpi(dotpolar: str):
|
||||||
|
|
||||||
import my.reading.polar as polar
|
import my.reading.polar as polar
|
||||||
from my.reading.polar import get_entries
|
from my.reading.polar import get_entries
|
||||||
assert len(list(get_entries())) > 10
|
assert len(list(get_entries())) > 1
|
||||||
|
|
Loading…
Add table
Reference in a new issue