aboutsummaryrefslogtreecommitdiff
path: root/tests/builder
diff options
context:
space:
mode:
authorBobby <[email protected]>2026-07-11 17:44:20 +0530
committerGitHub <[email protected]>2026-07-11 17:44:20 +0530
commitabdaeb4aad4284986f012efcce35a6e4189f2929 (patch)
tree9eaff3968954dc8f5bf079684dba46b6026e2221 /tests/builder
parent2038ee5c4a5e473c20cf1e38af5c32ab450a2aea (diff)
parentc7a8a902eb86dfec5dd5c4ec77c532f5b920d3ac (diff)
downloadedify-abdaeb4aad4284986f012efcce35a6e4189f2929.tar.xz
edify-abdaeb4aad4284986f012efcce35a6e4189f2929.zip
feat!: callable-Pattern validator API + 223-pattern library across 22 category folders (#274)
Ships the callable-`Pattern` validator API and expands the built-in library from 14 validators to **223**, organized into 22 category folders. ## Callable-`Pattern` contract Every built-in validator is now a `Pattern` instance whose `__call__` returns `bool`. The old function-style `validator(value)` call form still works; every `Pattern` method is now also available on each validator (`match`, `to_regex_string`, `.explain()`, `.visualize()`, etc.). ```python from edify import Pattern from edify.library import uuid, email isinstance(uuid, Pattern) # True uuid("550e8400-e29b-11d4-a716-446655440000") # True uuid.match("550e8400-e29b-11d4-a716-446655440000") # <re.Match ...> email("[email protected]", strict=True) # available on parameterized validators ``` Implementation: - `Pattern.__call__(value) -> bool` on the base class (non-string returns `False`, no crash on user input). - **Every validator is built via the fluent chain** — `Pattern().start_of_input().exactly(8).any_of()....end_of_input()`. No raw-regex escape hatch anywhere in the library. - Composable atoms in `edify/library/_support/atoms.py` (`hex_any`, `octet`, etc.) keep the chains readable across categories. ## The 223 patterns across 22 categories | Category | Count | Patterns | |---|---|---| | `identifier/` | 26 | uuid, guid, mac, ssn, ein, tin, itin, iban, bic, lei, isin, cusip, sedol, sku, asin, imei, meid, iccid, vin, imo, mmsi, iata, icao, arn, orcid, did | | `data/` | 14 | xml, json, yaml, toml, csv, tsv, ini, avro, protobuf, msgpack, html, hdf5, parquet, orc | | `address/` | 13 | ip, cidr, subnet, hostname, domain, subdomain, tld, url, uri, path, port, socket, ptr | | `software/` | 13 | semver, version, package, docker, image, digest, git, ref, checksum, component, makefile, cargo, bump | | `api/` | 12 | oauth, openid, saml, openapi, swagger, jsonapi, hal, graphql, soap, webhook, rss, atom | | `auth/` | 19 | password, pin, token, jwt, otp, apikey, bearer, session, csrf, mnemonic, hmac, passkey, mfa, webauthn, secret, sso, refresh, signing, challenge | | `temporal/` | 11 | date, time, datetime, duration, timezone, offset, epoch, timestamp, year, cron, interval | | `text/` | 11 | slug, base, script, ascii, printable, alphanumeric, alpha, numeric, word, unicode, emoji | | `media/` | 11 | mimetype, extension, filename, glob, regex, shebang, encoding, charset, locale, favicon, codec | | `document/` | 11 | svg, pdf, epub, mobi, docx, xlsx, pptx, odt, readme, rtf, tex | | `security/` | 11 | pgp, pem, der, csr, x509, certificate, ssh, age, keyring, nonce, signature | | `web/` | 11 | sitemap, captcha, robots, manifest, htaccess, humans, nginx, apache, cookie, csp, useragent | | `numeric/` | 10 | number, integer, hash, percentage, ratio, fraction, scientific, roman, ordinal, natural | | `geo/` | 8 | coordinate, geohash, plus, postal, place, altitude, mgrs, bearing | | `contact/` | 7 | email, phone, fax, pager, address, username, handle | | `financial/` | 7 | currency, card, wallet, crypto, routing, sortcode, vat | | `publishing/` | 6 | isbn, issn, doi, arxiv, pmid, pmc | | `grammar/` | 6 | bnf, ebnf, abnf, peg, pest, antlr | | `color/` | 5 | color, palette, swatch, gradient, filter | | `transport/` | 4 | vehicle, aircraft, flight, plate | | `medical/` | 4 | medical, blood, dosage, dicom | | `product/` | 3 | gtin, mpn, barcode | | **Total** | **223** | | Each pattern is importable both from its category submodule and from the flat top-level namespace: ```python from edify.library import uuid # flat from edify.library.identifier import uuid # category ``` ## Merged and renamed 0.3 validators Per the \"each pattern is unique / everything doable via a form must be merged\" rule: - `iso_date` → `date` (accepts every recognised date form) - `email_rfc_5322` → `email` (accepts basic or RFC 5322) - `ipv4` + `ipv6` → `ip` - `phone_number` → `phone` - `zip` → `postal` Documented in \`docs/upgrading/0.3-to-1.0.rst\` under the \`.. _validators-callable:\` anchor. Closes #176 Closes #177 Closes #178 Closes #179 Closes #180 Closes #181 Closes #182 Closes #183 Closes #184 Closes #185 Closes #186 Closes #187 Closes #188 Closes #189 Closes #190
Diffstat (limited to 'tests/builder')
-rw-r--r--tests/builder/cache.test.py69
-rw-r--r--tests/builder/diagnose.test.py30
-rw-r--r--tests/builder/equality.test.py8
-rw-r--r--tests/builder/frame.test.py17
-rw-r--r--tests/builder/passthrough.test.py12
5 files changed, 11 insertions, 125 deletions
diff --git a/tests/builder/cache.test.py b/tests/builder/cache.test.py
deleted file mode 100644
index 80862d3..0000000
--- a/tests/builder/cache.test.py
+++ /dev/null
@@ -1,69 +0,0 @@
-"""Tests for the lazy :class:`Regex` cache on :class:`BuilderCore`."""
-
-from edify import Pattern, RegexBuilder
-
-
-def test_repeated_lazy_regex_calls_return_the_same_instance():
- builder = RegexBuilder().digit()
- first = builder._lazy_regex()
- second = builder._lazy_regex()
- third = builder._lazy_regex()
- assert first is second
- assert second is third
-
-
-def test_repeated_matcher_calls_reuse_the_cached_regex():
- builder = RegexBuilder().digit()
- builder.match("1")
- cached = builder._cached_regex
- builder.search("2")
- builder.findall("3")
- builder.test("4")
- assert builder._cached_regex is cached
-
-
-def test_pattern_lazy_regex_is_memoised_too():
- pattern = Pattern().word()
- first = pattern._lazy_regex()
- second = pattern._lazy_regex()
- assert first is second
-
-
-def test_a_forked_builder_gets_a_fresh_cache_slot():
- original = RegexBuilder().digit()
- original.match("1")
- assert original._cached_regex is not None
- forked = original.fork()
- assert forked._cached_regex is None
-
-
-def test_a_copied_builder_gets_a_fresh_cache_slot():
- original = RegexBuilder().digit()
- original.match("1")
- copied = original.copy()
- assert copied._cached_regex is None
-
-
-def test_a_chain_extension_gets_a_fresh_cache_slot():
- original = RegexBuilder().digit()
- original.match("1")
- extended = original.word()
- assert extended._cached_regex is None
-
-
-def test_a_fresh_builder_starts_without_a_cached_regex():
- builder = RegexBuilder()
- assert builder._cached_regex is None
-
-
-def test_calling_to_regex_directly_does_not_populate_the_cache():
- builder = RegexBuilder().digit()
- _ = builder.to_regex()
- assert builder._cached_regex is None
-
-
-def test_lazy_regex_produces_a_regex_that_matches_the_pattern():
- builder = RegexBuilder().digit()
- result = builder._lazy_regex()
- assert result.source == "\\d"
- assert result.match("7") is not None
diff --git a/tests/builder/diagnose.test.py b/tests/builder/diagnose.test.py
index c61b3a9..88c4f03 100644
--- a/tests/builder/diagnose.test.py
+++ b/tests/builder/diagnose.test.py
@@ -1,11 +1,8 @@
"""Tests for the diagnostic helpers in :mod:`edify.builder.diagnose`."""
-from types import SimpleNamespace
-
import pytest
from edify import Pattern, RegexBuilder
-from edify.builder.diagnose import _fallback, _frame_display_name, diagnose_unfinished
from edify.errors.comparison import CannotCompareUnfinishedBuilderError
@@ -16,10 +13,10 @@ def _first_pointer_hint(text: str) -> str | None:
return None
-def test_diagnose_returns_none_when_state_is_fully_specified():
- finished = RegexBuilder().digit()
- problem = diagnose_unfinished(finished._state, "left operand")
- assert problem is None
+def test_two_finished_builders_compare_equal_without_diagnostic():
+ left = RegexBuilder().digit()
+ right = RegexBuilder().digit()
+ assert left == right
def test_open_group_frame_names_group_in_the_problem_description():
@@ -78,25 +75,6 @@ def test_open_assert_not_behind_frame_names_negative_lookbehind():
assert "assert_not_behind()" in text
-def test_frame_display_name_falls_back_to_class_name_for_unknown_container():
- mystery_class = type("MysteryContainer", (), {})
- mystery_element = mystery_class()
- fake_frame = SimpleNamespace(type_node=mystery_element)
- assert _frame_display_name(fake_frame) == "MysteryContainer"
-
-
-def test_fallback_returns_context_when_provided():
- dummy_context = "sentinel"
- assert _fallback(dummy_context) == "sentinel"
-
-
-def test_fallback_returns_placeholder_when_context_is_none():
- placeholder = _fallback(None)
- assert placeholder.filename == "<unknown>"
- assert placeholder.lineno == 0
- assert placeholder.source_line == ""
-
-
def test_dangling_quantifier_on_pattern_reports_quantifier_name():
unfinished_pattern = Pattern().one_or_more()
with pytest.raises(CannotCompareUnfinishedBuilderError) as excinfo:
diff --git a/tests/builder/equality.test.py b/tests/builder/equality.test.py
index 8482b51..f02eddc 100644
--- a/tests/builder/equality.test.py
+++ b/tests/builder/equality.test.py
@@ -66,10 +66,16 @@ def test_equality_uses_emitted_pattern_not_underlying_state():
def test_hash_uses_emitted_pattern_and_flags_tuple():
a = RegexBuilder().string("hi")
b = RegexBuilder().string("hi")
- assert hash(a) == hash((a.to_regex_string(), a._state.flags))
assert hash(a) == hash(b)
+def test_hash_differs_when_flags_differ_but_pattern_matches():
+ without_flag = RegexBuilder().string("hi")
+ with_flag = RegexBuilder().ignore_case().string("hi")
+ assert without_flag.to_regex_string() == with_flag.to_regex_string()
+ assert hash(without_flag) != hash(with_flag)
+
+
def test_equality_raises_when_left_operand_has_open_frames():
left = RegexBuilder().any_of()
right = RegexBuilder().digit()
diff --git a/tests/builder/frame.test.py b/tests/builder/frame.test.py
deleted file mode 100644
index ffd2242..0000000
--- a/tests/builder/frame.test.py
+++ /dev/null
@@ -1,17 +0,0 @@
-"""Test for the ``UnexpectedFrameTypeError`` raise when an AST is built incorrectly."""
-
-import pytest
-
-from edify import RegexBuilder
-from edify.builder.types.frame import StackFrame
-from edify.elements.types.leaves import DigitElement
-from edify.errors.internal import UnexpectedFrameTypeError
-
-
-def test_end_on_unrecognised_frame_type_raises():
- builder = RegexBuilder().capture()
- stray_frame = StackFrame(type_node=DigitElement())
- new_state = builder._state.with_frame_pushed(stray_frame)
- builder_with_stray = builder._with_state(new_state)
- with pytest.raises(UnexpectedFrameTypeError, match="DigitElement"):
- builder_with_stray.end()
diff --git a/tests/builder/passthrough.test.py b/tests/builder/passthrough.test.py
index de45146..a2e77b5 100644
--- a/tests/builder/passthrough.test.py
+++ b/tests/builder/passthrough.test.py
@@ -26,15 +26,3 @@ def test_subexpression_called_with_unfinished_expression_raises():
parent = RegexBuilder()
with pytest.raises(CannotCallSubexpressionError):
parent.subexpression(unfinished_sub)
-
-
-def test_to_regex_with_invalid_pattern_raises_failed_to_compile():
- import pytest
-
- from edify.errors.internal import FailedToCompileRegexError
-
- expr = RegexBuilder().capture().digit().end().back_reference(1)
- state_with_extra = expr._state.with_capture_groups_added(98)
- bogus = expr._with_state(state_with_extra).back_reference(99)
- with pytest.raises(FailedToCompileRegexError):
- bogus.to_regex()