anki/pylib/tests/test_importing.py

334 lines
9.9 KiB
Python
Raw Normal View History

2021-04-13 10:45:05 +02:00
# Copyright: Ankitects Pty Ltd and contributors
# License: GNU AGPL, version 3 or later; http://www.gnu.org/licenses/agpl.html
# coding: utf-8
2019-12-25 05:18:34 +01:00
import os
from tempfile import NamedTemporaryFile
import pytest
2020-07-19 05:27:31 +02:00
from anki.consts import *
2019-12-25 05:18:34 +01:00
from anki.importing import (
Anki2Importer,
AnkiPackageImporter,
MnemosyneImporter,
SupermemoXmlImporter,
TextImporter,
2019-12-25 05:18:34 +01:00
)
from tests.shared import getEmptyCol, getUpgradeDeckPath
testDir = os.path.dirname(__file__)
def clear_tempfile(tf):
2021-05-07 10:12:56 +02:00
"""https://stackoverflow.com/questions/23212435/permission-denied-to-write-to-my-temporary-file"""
try:
tf.close()
os.unlink(tf.name)
except:
pass
def test_anki2_mediadupes():
2020-07-17 17:37:17 +02:00
col = getEmptyCol()
# add a note that references a sound
2020-07-17 17:37:17 +02:00
n = col.newNote()
2019-12-25 05:18:34 +01:00
n["Front"] = "[sound:foo.mp3]"
2021-06-27 04:12:23 +02:00
mid = n.note_type()["id"]
2020-07-17 17:37:17 +02:00
col.addNote(n)
# add that sound to media folder
2020-07-17 17:37:17 +02:00
with open(os.path.join(col.media.dir(), "foo.mp3"), "w") as note:
note.write("foo")
2020-07-17 17:37:17 +02:00
col.close()
# it should be imported correctly into an empty deck
2014-06-03 10:38:47 +02:00
empty = getEmptyCol()
2020-07-17 17:37:17 +02:00
imp = Anki2Importer(empty, col.path)
imp.run()
assert os.listdir(empty.media.dir()) == ["foo.mp3"]
# and importing again will not duplicate, as the file content matches
2020-06-04 10:21:04 +02:00
empty.remove_cards_and_orphaned_notes(empty.db.list("select id from cards"))
2020-07-17 17:37:17 +02:00
imp = Anki2Importer(empty, col.path)
imp.run()
assert os.listdir(empty.media.dir()) == ["foo.mp3"]
n = empty.get_note(empty.db.scalar("select id from notes"))
assert "foo.mp3" in n.fields[0]
# if the local file content is different, and import should trigger a
# rename
2020-06-04 10:21:04 +02:00
empty.remove_cards_and_orphaned_notes(empty.db.list("select id from cards"))
with open(os.path.join(empty.media.dir(), "foo.mp3"), "w") as note:
note.write("bar")
2020-07-17 17:37:17 +02:00
imp = Anki2Importer(empty, col.path)
imp.run()
2021-10-02 15:51:42 +02:00
assert sorted(os.listdir(empty.media.dir())) == ["foo.mp3", f"foo_{mid}.mp3"]
n = empty.get_note(empty.db.scalar("select id from notes"))
assert "_" in n.fields[0]
# if the localized media file already exists, we rewrite the note and
# media
2020-06-04 10:21:04 +02:00
empty.remove_cards_and_orphaned_notes(empty.db.list("select id from cards"))
with open(os.path.join(empty.media.dir(), "foo.mp3"), "w") as note:
note.write("bar")
2020-07-17 17:37:17 +02:00
imp = Anki2Importer(empty, col.path)
imp.run()
2021-10-02 15:51:42 +02:00
assert sorted(os.listdir(empty.media.dir())) == ["foo.mp3", f"foo_{mid}.mp3"]
assert sorted(os.listdir(empty.media.dir())) == ["foo.mp3", f"foo_{mid}.mp3"]
n = empty.get_note(empty.db.scalar("select id from notes"))
assert "_" in n.fields[0]
2019-12-25 05:18:34 +01:00
def test_apkg():
2020-07-17 17:37:17 +02:00
col = getEmptyCol()
apkg = str(os.path.join(testDir, "support", "media.apkg"))
2020-07-17 17:37:17 +02:00
imp = AnkiPackageImporter(col, apkg)
assert os.listdir(col.media.dir()) == []
imp.run()
2020-07-17 17:37:17 +02:00
assert os.listdir(col.media.dir()) == ["foo.wav"]
# importing again should be idempotent in terms of media
2020-07-17 17:37:17 +02:00
col.remove_cards_and_orphaned_notes(col.db.list("select id from cards"))
imp = AnkiPackageImporter(col, apkg)
imp.run()
2020-07-17 17:37:17 +02:00
assert os.listdir(col.media.dir()) == ["foo.wav"]
# but if the local file has different data, it will rename
2020-07-17 17:37:17 +02:00
col.remove_cards_and_orphaned_notes(col.db.list("select id from cards"))
with open(os.path.join(col.media.dir(), "foo.wav"), "w") as note:
note.write("xyz")
2020-07-17 17:37:17 +02:00
imp = AnkiPackageImporter(col, apkg)
imp.run()
2020-07-17 17:37:17 +02:00
assert len(os.listdir(col.media.dir())) == 2
2019-12-25 05:18:34 +01:00
def test_anki2_diffmodel_templates():
# different from the above as this one tests only the template text being
# changed, not the number of cards/fields
dst = getEmptyCol()
# import the first version of the model
2020-07-17 17:37:17 +02:00
col = getUpgradeDeckPath("diffmodeltemplates-1.apkg")
imp = AnkiPackageImporter(dst, col)
Move away from Bazel (#2202) (for upgrading users, please see the notes at the bottom) Bazel brought a lot of nice things to the table, such as rebuilds based on content changes instead of modification times, caching of build products, detection of incorrect build rules via a sandbox, and so on. Rewriting the build in Bazel was also an opportunity to improve on the Makefile-based build we had prior, which was pretty poor: most dependencies were external or not pinned, and the build graph was poorly defined and mostly serialized. It was not uncommon for fresh checkouts to fail due to floating dependencies, or for things to break when trying to switch to an older commit. For day-to-day development, I think Bazel served us reasonably well - we could generally switch between branches while being confident that builds would be correct and reasonably fast, and not require full rebuilds (except on Windows, where the lack of a sandbox and the TS rules would cause build breakages when TS files were renamed/removed). Bazel achieves that reliability by defining rules for each programming language that define how source files should be turned into outputs. For the rules to work with Bazel's sandboxing approach, they often have to reimplement or partially bypass the standard tools that each programming language provides. The Rust rules call Rust's compiler directly for example, instead of using Cargo, and the Python rules extract each PyPi package into a separate folder that gets added to sys.path. These separate language rules allow proper declaration of inputs and outputs, and offer some advantages such as caching of build products and fine-grained dependency installation. But they also bring some downsides: - The rules don't always support use-cases/platforms that the standard language tools do, meaning they need to be patched to be used. I've had to contribute a number of patches to the Rust, Python and JS rules to unblock various issues. - The dependencies we use with each language sometimes make assumptions that do not hold in Bazel, meaning they either need to be pinned or patched, or the language rules need to be adjusted to accommodate them. I was hopeful that after the initial setup work, things would be relatively smooth-sailing. Unfortunately, that has not proved to be the case. Things frequently broke when dependencies or the language rules were updated, and I began to get frustrated at the amount of Anki development time I was instead spending on build system upkeep. It's now about 2 years since switching to Bazel, and I think it's time to cut losses, and switch to something else that's a better fit. The new build system is based on a small build tool called Ninja, and some custom Rust code in build/. This means that to build Anki, Bazel is no longer required, but Ninja and Rust need to be installed on your system. Python and Node toolchains are automatically downloaded like in Bazel. This new build system should result in faster builds in some cases: - Because we're using cargo to build now, Rust builds are able to take advantage of pipelining and incremental debug builds, which we didn't have with Bazel. It's also easier to override the default linker on Linux/macOS, which can further improve speeds. - External Rust crates are now built with opt=1, which improves performance of debug builds. - Esbuild is now used to transpile TypeScript, instead of invoking the TypeScript compiler. This results in faster builds, by deferring typechecking to test/check time, and by allowing more work to happen in parallel. As an example of the differences, when testing with the mold linker on Linux, adding a new message to tags.proto (which triggers a recompile of the bulk of the Rust and TypeScript code) results in a compile that goes from about 22s on Bazel to about 7s in the new system. With the standard linker, it's about 9s. Some other changes of note: - Our Rust workspace now uses cargo-hakari to ensure all packages agree on available features, preventing unnecessary rebuilds. - pylib/anki is now a PEP420 implicit namespace, avoiding the need to merge source files and generated files into a single folder for running. By telling VSCode about the extra search path, code completion now works with generated files without needing to symlink them into the source folder. - qt/aqt can't use PEP420 as it's difficult to get rid of aqt/__init__.py. Instead, the generated files are now placed in a separate _aqt package that's added to the path. - ts/lib is now exposed as @tslib, so the source code and generated code can be provided under the same namespace without a merging step. - MyPy and PyLint are now invoked once for the entire codebase. - dprint will be used to format TypeScript/json files in the future instead of the slower prettier (currently turned off to avoid causing conflicts). It can automatically defer to prettier when formatting Svelte files. - svelte-check is now used for typechecking our Svelte code, which revealed a few typing issues that went undetected with the old system. - The Jest unit tests now work on Windows as well. If you're upgrading from Bazel, updated usage instructions are in docs/development.md and docs/build.md. A summary of the changes: - please remove node_modules and .bazel - install rustup (https://rustup.rs/) - install rsync if not already installed (on windows, use pacman - see docs/windows.md) - install Ninja (unzip from https://github.com/ninja-build/ninja/releases/tag/v1.11.1 and place on your path, or from your distro/homebrew if it's 1.10+) - update .vscode/settings.json from .vscode.dist
2022-11-27 06:24:20 +01:00
imp.dupeOnSchemaChange = True # type: ignore
imp.run()
# then the version with updated template
2020-07-17 17:37:17 +02:00
col = getUpgradeDeckPath("diffmodeltemplates-2.apkg")
imp = AnkiPackageImporter(dst, col)
Move away from Bazel (#2202) (for upgrading users, please see the notes at the bottom) Bazel brought a lot of nice things to the table, such as rebuilds based on content changes instead of modification times, caching of build products, detection of incorrect build rules via a sandbox, and so on. Rewriting the build in Bazel was also an opportunity to improve on the Makefile-based build we had prior, which was pretty poor: most dependencies were external or not pinned, and the build graph was poorly defined and mostly serialized. It was not uncommon for fresh checkouts to fail due to floating dependencies, or for things to break when trying to switch to an older commit. For day-to-day development, I think Bazel served us reasonably well - we could generally switch between branches while being confident that builds would be correct and reasonably fast, and not require full rebuilds (except on Windows, where the lack of a sandbox and the TS rules would cause build breakages when TS files were renamed/removed). Bazel achieves that reliability by defining rules for each programming language that define how source files should be turned into outputs. For the rules to work with Bazel's sandboxing approach, they often have to reimplement or partially bypass the standard tools that each programming language provides. The Rust rules call Rust's compiler directly for example, instead of using Cargo, and the Python rules extract each PyPi package into a separate folder that gets added to sys.path. These separate language rules allow proper declaration of inputs and outputs, and offer some advantages such as caching of build products and fine-grained dependency installation. But they also bring some downsides: - The rules don't always support use-cases/platforms that the standard language tools do, meaning they need to be patched to be used. I've had to contribute a number of patches to the Rust, Python and JS rules to unblock various issues. - The dependencies we use with each language sometimes make assumptions that do not hold in Bazel, meaning they either need to be pinned or patched, or the language rules need to be adjusted to accommodate them. I was hopeful that after the initial setup work, things would be relatively smooth-sailing. Unfortunately, that has not proved to be the case. Things frequently broke when dependencies or the language rules were updated, and I began to get frustrated at the amount of Anki development time I was instead spending on build system upkeep. It's now about 2 years since switching to Bazel, and I think it's time to cut losses, and switch to something else that's a better fit. The new build system is based on a small build tool called Ninja, and some custom Rust code in build/. This means that to build Anki, Bazel is no longer required, but Ninja and Rust need to be installed on your system. Python and Node toolchains are automatically downloaded like in Bazel. This new build system should result in faster builds in some cases: - Because we're using cargo to build now, Rust builds are able to take advantage of pipelining and incremental debug builds, which we didn't have with Bazel. It's also easier to override the default linker on Linux/macOS, which can further improve speeds. - External Rust crates are now built with opt=1, which improves performance of debug builds. - Esbuild is now used to transpile TypeScript, instead of invoking the TypeScript compiler. This results in faster builds, by deferring typechecking to test/check time, and by allowing more work to happen in parallel. As an example of the differences, when testing with the mold linker on Linux, adding a new message to tags.proto (which triggers a recompile of the bulk of the Rust and TypeScript code) results in a compile that goes from about 22s on Bazel to about 7s in the new system. With the standard linker, it's about 9s. Some other changes of note: - Our Rust workspace now uses cargo-hakari to ensure all packages agree on available features, preventing unnecessary rebuilds. - pylib/anki is now a PEP420 implicit namespace, avoiding the need to merge source files and generated files into a single folder for running. By telling VSCode about the extra search path, code completion now works with generated files without needing to symlink them into the source folder. - qt/aqt can't use PEP420 as it's difficult to get rid of aqt/__init__.py. Instead, the generated files are now placed in a separate _aqt package that's added to the path. - ts/lib is now exposed as @tslib, so the source code and generated code can be provided under the same namespace without a merging step. - MyPy and PyLint are now invoked once for the entire codebase. - dprint will be used to format TypeScript/json files in the future instead of the slower prettier (currently turned off to avoid causing conflicts). It can automatically defer to prettier when formatting Svelte files. - svelte-check is now used for typechecking our Svelte code, which revealed a few typing issues that went undetected with the old system. - The Jest unit tests now work on Windows as well. If you're upgrading from Bazel, updated usage instructions are in docs/development.md and docs/build.md. A summary of the changes: - please remove node_modules and .bazel - install rustup (https://rustup.rs/) - install rsync if not already installed (on windows, use pacman - see docs/windows.md) - install Ninja (unzip from https://github.com/ninja-build/ninja/releases/tag/v1.11.1 and place on your path, or from your distro/homebrew if it's 1.10+) - update .vscode/settings.json from .vscode.dist
2022-11-27 06:24:20 +01:00
imp.dupeOnSchemaChange = True # type: ignore
imp.run()
# collection should contain the note we imported
2021-06-27 07:12:22 +02:00
assert dst.note_count() == 1
# the front template should contain the text added in the 2nd package
2021-06-27 07:12:22 +02:00
tcid = dst.find_cards("")[0] # only 1 note in collection
tnote = dst.getCard(tcid).note()
assert "Changed Front Template" in tnote.cards()[0].template()["qfmt"]
2019-12-25 05:18:34 +01:00
def test_anki2_updates():
# create a new empty deck
2014-06-03 10:38:47 +02:00
dst = getEmptyCol()
2020-07-17 17:37:17 +02:00
col = getUpgradeDeckPath("update1.apkg")
imp = AnkiPackageImporter(dst, col)
imp.run()
assert imp.dupes == 0
assert imp.added == 1
assert imp.updated == 0
# importing again should be idempotent
2020-07-17 17:37:17 +02:00
imp = AnkiPackageImporter(dst, col)
imp.run()
assert imp.dupes == 1
assert imp.added == 0
assert imp.updated == 0
# importing a newer note should update
2021-06-27 07:12:22 +02:00
assert dst.note_count() == 1
assert dst.db.scalar("select flds from notes").startswith("hello")
2020-07-17 17:37:17 +02:00
col = getUpgradeDeckPath("update2.apkg")
imp = AnkiPackageImporter(dst, col)
imp.run()
assert imp.dupes == 0
assert imp.added == 0
assert imp.updated == 1
2021-06-27 07:12:22 +02:00
assert dst.note_count() == 1
assert dst.db.scalar("select flds from notes").startswith("goodbye")
2019-12-25 05:18:34 +01:00
def test_csv():
col = getEmptyCol()
file = str(os.path.join(testDir, "support", "text-2fields.txt"))
i = TextImporter(col, file)
i.initMapping()
i.run()
# four problems - too many & too few fields, a missing front, and a
# duplicate entry
assert len(i.log) == 5
assert i.total == 5
# if we run the import again, it should update instead
i.run()
2013-05-16 10:19:11 +02:00
assert len(i.log) == 10
assert i.total == 5
# but importing should not clobber tags if they're unmapped
n = col.get_note(col.db.scalar("select id from notes"))
n.add_tag("test")
n.flush()
i.run()
n.load()
2019-12-25 05:18:34 +01:00
assert n.tags == ["test"]
# if add-only mode, count will be 0
i.importMode = 1
i.run()
assert i.total == 0
# and if dupes mode, will reimport everything
2021-06-27 07:12:22 +02:00
assert col.card_count() == 5
i.importMode = 2
i.run()
# includes repeated field
assert i.total == 6
2021-06-27 07:12:22 +02:00
assert col.card_count() == 11
col.close()
2019-12-25 05:18:34 +01:00
def test_csv2():
col = getEmptyCol()
mm = col.models
m = mm.current()
2021-06-27 05:49:58 +02:00
note = mm.new_field("Three")
mm.addField(m, note)
mm.save(m)
n = col.newNote()
2019-12-25 05:18:34 +01:00
n["Front"] = "1"
n["Back"] = "2"
n["Three"] = "3"
col.addNote(n)
# an update with unmapped fields should not clobber those fields
file = str(os.path.join(testDir, "support", "text-update.txt"))
i = TextImporter(col, file)
i.initMapping()
i.run()
n.load()
2019-12-25 05:18:34 +01:00
assert n["Front"] == "1"
assert n["Back"] == "x"
assert n["Three"] == "3"
col.close()
2019-12-25 05:18:34 +01:00
def test_tsv_tag_modified():
col = getEmptyCol()
mm = col.models
m = mm.current()
2021-06-27 05:49:58 +02:00
note = mm.new_field("Top")
mm.addField(m, note)
mm.save(m)
n = col.newNote()
n["Front"] = "1"
n["Back"] = "2"
n["Top"] = "3"
n.add_tag("four")
col.addNote(n)
# https://stackoverflow.com/questions/23212435/permission-denied-to-write-to-my-temporary-file
with NamedTemporaryFile(mode="w", delete=False) as tf:
tf.write("1\tb\tc\n")
tf.flush()
i = TextImporter(col, tf.name)
i.initMapping()
i.tagModified = "boom"
i.run()
clear_tempfile(tf)
n.load()
assert n["Front"] == "1"
assert n["Back"] == "b"
assert n["Top"] == "c"
assert "four" in n.tags
assert "boom" in n.tags
assert len(n.tags) == 2
assert i.updateCount == 1
col.close()
def test_tsv_tag_multiple_tags():
col = getEmptyCol()
mm = col.models
m = mm.current()
2021-06-27 05:49:58 +02:00
note = mm.new_field("Top")
mm.addField(m, note)
mm.save(m)
n = col.newNote()
n["Front"] = "1"
n["Back"] = "2"
n["Top"] = "3"
n.add_tag("four")
n.add_tag("five")
col.addNote(n)
# https://stackoverflow.com/questions/23212435/permission-denied-to-write-to-my-temporary-file
with NamedTemporaryFile(mode="w", delete=False) as tf:
tf.write("1\tb\tc\n")
tf.flush()
i = TextImporter(col, tf.name)
i.initMapping()
2020-01-02 20:05:56 +01:00
i.tagModified = "five six"
i.run()
clear_tempfile(tf)
n.load()
assert n["Front"] == "1"
assert n["Back"] == "b"
assert n["Top"] == "c"
assert list(sorted(n.tags)) == list(sorted(["four", "five", "six"]))
col.close()
def test_csv_tag_only_if_modified():
col = getEmptyCol()
mm = col.models
m = mm.current()
2021-06-27 05:49:58 +02:00
note = mm.new_field("Left")
mm.addField(m, note)
mm.save(m)
n = col.newNote()
n["Front"] = "1"
n["Back"] = "2"
n["Left"] = "3"
col.addNote(n)
# https://stackoverflow.com/questions/23212435/permission-denied-to-write-to-my-temporary-file
with NamedTemporaryFile(mode="w", delete=False) as tf:
tf.write("1,2,3\n")
tf.flush()
i = TextImporter(col, tf.name)
i.initMapping()
i.tagModified = "right"
i.run()
clear_tempfile(tf)
n.load()
assert n.tags == []
assert i.updateCount == 0
col.close()
@pytest.mark.filterwarnings("ignore:Using or importing the ABCs")
def test_supermemo_xml_01_unicode():
col = getEmptyCol()
file = str(os.path.join(testDir, "support", "supermemo1.xml"))
i = SupermemoXmlImporter(col, file)
2019-12-25 05:18:34 +01:00
# i.META.logToStdOutput = True
i.run()
assert i.total == 1
cid = col.db.scalar("select id from cards")
c = col.get_card(cid)
2014-02-13 08:46:38 +01:00
# Applies A Factor-to-E Factor conversion
assert c.factor == 2879
assert c.reps == 7
col.close()
2019-12-25 05:18:34 +01:00
def test_mnemo():
col = getEmptyCol()
file = str(os.path.join(testDir, "support", "mnemo.db"))
i = MnemosyneImporter(col, file)
i.run()
2021-06-27 07:12:22 +02:00
assert col.card_count() == 7
assert "a_longer_tag" in col.tags.all()
2020-07-19 05:27:31 +02:00
assert col.db.scalar(f"select count() from cards where type = {CARD_TYPE_NEW}") == 1
col.close()