diff --git a/.gititnore b/.gititnore
new file mode 100644
index 0000000..b539013
--- /dev/null
+++ b/.gititnore
@@ -0,0 +1,172 @@
+
+# Created by https://www.gitignore.io/api/python,emacs
+
+### Emacs ###
+# -*- mode: gitignore; -*-
+*~
+\#*\#
+/.emacs.desktop
+/.emacs.desktop.lock
+*.elc
+auto-save-list
+tramp
+.\#*
+
+# Org-mode
+.org-id-locations
+*_archive
+
+# flymake-mode
+*_flymake.*
+
+# eshell files
+/eshell/history
+/eshell/lastdir
+
+# elpa packages
+/elpa/
+
+# reftex files
+*.rel
+
+# AUCTeX auto folder
+/auto/
+
+# cask packages
+.cask/
+dist/
+
+# Flycheck
+flycheck_*.el
+
+# server auth directory
+/server/
+
+# projectiles files
+.projectile
+
+# directory configuration
+.dir-locals.el
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+
+### Python Patch ###
+.venv/
+
+### Python.VirtualEnv Stack ###
+# Virtualenv
+# http://iamzed.com/2009/05/07/a-primer-on-virtualenv/
+[Bb]in
+[Ii]nclude
+[Ll]ib
+[Ll]ib64
+[Ll]ocal
+[Ss]cripts
+pyvenv.cfg
+pip-selfcheck.json
+
+
+# End of https://www.gitignore.io/api/python,emacs
diff --git a/hypothesis/__init__.py b/hypothesis/__init__.py
new file mode 100644
index 0000000..a30fa29
--- /dev/null
+++ b/hypothesis/__init__.py
@@ -0,0 +1,121 @@
+from functools import lru_cache
+from kython import listdir_abs
+from typing import Dict, List, NamedTuple, Optional, Sequence
+from pathlib import Path
+import json
+from pytz import UTC
+from datetime import datetime
+import os
+
+from kython import group_by_key, the, cproperty
+
+
+_PATH = '/L/backups/hypothesis/'
+
+Url = str
+
+class Entry(NamedTuple):
+    dt: datetime
+    summary: str
+    content: Optional[str] # might be none if for instance we just marked page with tags. not sure if we want to handle it somehow separately
+    link: Url
+    eid: str
+    annotation: Optional[str]
+    context: Url
+    tags: Sequence[str]
+    hyp_link: Url
+
+    @property
+    def title(self):
+        return self.summary # TODO eh, remove one of them?...
+
+
+class Page(NamedTuple):
+    highlights: Sequence[Entry]
+
+    @cproperty
+    def link(self):
+        return the(h.link for h in self.highlights)
+
+    @cproperty
+    def title(self):
+        return the(h.summary for h in self.highlights)
+
+    @cproperty
+    def dt(self):
+        return min(h.dt for h in self.highlights)
+
+
+# TODO guarantee order?
+def _iter():
+    last = max(listdir_abs(_PATH))
+    with Path(last).open() as fo:
+        j = json.load(fo)
+    for i in j:
+        dts = i['created']
+        title = ' '.join(i['document']['title'])
+        selectors = i['target'][0].get('selector', None)
+        if selectors is None:
+            # TODO warn?...
+            selectors = []
+        content: Optional[str] = None
+        for s in selectors:
+            if 'exact' in s:
+                content = s['exact']
+                break
+        eid = i['id']
+        link = i['uri']
+        dt = datetime.strptime(dts[:-3] + dts[-2:], '%Y-%m-%dT%H:%M:%S.%f%z')
+        txt = i['text']
+        annotation = None if len(txt.strip()) == 0 else txt
+        context = i['links']['incontext']
+        yield Entry(
+            dt=dt,
+            summary=title,
+            content=content,
+            link=link,
+            eid=eid,
+            annotation=annotation,
+            context=context, # TODO FIXME is context used anywhere?
+            tags=tuple(i['tags']),
+            hyp_link=context,
+        )
+
+
+def get_pages() -> List[Page]:
+    grouped = group_by_key(_iter(), key=lambda e: e.link)
+    pages = []
+    for link, group in grouped.items():
+        sgroup = tuple(sorted(group, key=lambda e: e.dt))
+        pages.append(Page(highlights=sgroup))
+    pages = list(sorted(pages, key=lambda p: p.dt))
+    # TODO fixme page tag??
+    return pages
+
+
+def get_entries():
+    return list(_iter())
+
+
+def get_todos():
+    def is_todo(e: Entry) -> bool:
+        if any(t.lower() == 'todo' for t in  e.tags):
+            return True
+        if e.annotation is None:
+            return False
+        return e.annotation.lstrip().lower().startswith('todo')
+    return list(filter(is_todo, get_entries()))
+
+
+def test():
+    get_pages()
+    get_todos()
+    get_entries()
+
+
+def _main():
+    for page in get_pages():
+        print(page)
+
+if __name__ == '__main__':
+    _main()