From a2404d294e5be34b3f0689e26178f545e9c2e497 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Madeleine=20Sydney=20=C5=9Alaga?= Date: Tue, 4 Aug 2026 09:31:17 -0600 Subject: [PATCH] make-db --- db/.gitignore | 1 + db/Cargo.lock | 948 ++++++++++++++++++ db/Cargo.toml | 14 + db/default.nix | 9 + db/diesel.toml | 9 + db/migrations/.diesel_lock | 0 db/migrations/.keep | 0 .../down.sql | 2 + .../up.sql | 6 + db/src/db.rs | 45 + db/src/main.rs | 52 + db/src/models.rs | 17 + db/src/schema.rs | 9 + db/words.db-journal | Bin 0 -> 12824 bytes deps-lock.json | 18 +- deps.edn | 2 - flake.nix | 8 +- main | 5 - 18 files changed, 1123 insertions(+), 22 deletions(-) create mode 100644 db/.gitignore create mode 100644 db/Cargo.lock create mode 100644 db/Cargo.toml create mode 100644 db/default.nix create mode 100644 db/diesel.toml create mode 100644 db/migrations/.diesel_lock create mode 100644 db/migrations/.keep create mode 100644 db/migrations/2026-08-04-180241-0000_create-words/down.sql create mode 100644 db/migrations/2026-08-04-180241-0000_create-words/up.sql create mode 100644 db/src/db.rs create mode 100644 db/src/main.rs create mode 100644 db/src/models.rs create mode 100644 db/src/schema.rs create mode 100644 db/words.db-journal delete mode 100755 main diff --git a/db/.gitignore b/db/.gitignore new file mode 100644 index 0000000..1de5659 --- /dev/null +++ b/db/.gitignore @@ -0,0 +1 @@ +target \ No newline at end of file diff --git a/db/Cargo.lock b/db/Cargo.lock new file mode 100644 index 0000000..8164f44 --- /dev/null +++ b/db/Cargo.lock @@ -0,0 +1,948 @@ +# This file is automatically @generated by Cargo. +# It is not intended for manual editing. +version = 4 + +[[package]] +name = "adler2" +version = "2.0.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "320119579fcad9c21884f5c4861d16174d0e06250625266f50fe6898340abefa" + +[[package]] +name = "anstream" +version = "1.0.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "824a212faf96e9acacdbd09febd34438f8f711fb84e09a8916013cd7815ca28d" +dependencies = [ + "anstyle", + "anstyle-parse", + "anstyle-query", + "anstyle-wincon", + "colorchoice", + "is_terminal_polyfill", + "utf8parse", +] + +[[package]] +name = "anstyle" +version = "1.0.14" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "940b3a0ca603d1eade50a4846a2afffd5ef57a9feac2c0e2ec2e14f9ead76000" + +[[package]] +name = "anstyle-parse" +version = "1.0.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "52ce7f38b242319f7cabaa6813055467063ecdc9d355bbb4ce0c68908cd8130e" +dependencies = [ + "utf8parse", +] + +[[package]] +name = "anstyle-query" +version = "1.1.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "40c48f72fd53cd289104fc64099abca73db4166ad86ea0b4341abe65af83dadc" +dependencies = [ + "windows-sys 0.61.2", +] + +[[package]] +name = "anstyle-wincon" +version = "3.0.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "291e6a250ff86cd4a820112fb8898808a366d8f9f58ce16d1f538353ad55747d" +dependencies = [ + "anstyle", + "once_cell_polyfill", + "windows-sys 0.61.2", +] + +[[package]] +name = "bitflags" +version = "2.13.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b588b76d00fde79687d7646a9b5bdf3cc0f655e0bbd080335a95d7e96f3587da" + +[[package]] +name = "bumpalo" +version = "3.20.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "72f5acc6cb2ba439de613abc23857ec3d78374d8ed5ac84e9d11336e87da8649" + +[[package]] +name = "cc" +version = "1.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5add81bb678e6cb321aff7fa0dc7689ad82b112dbc032cea19f91d6b8e3582b9" +dependencies = [ + "find-msvc-tools", + "shlex", +] + +[[package]] +name = "cfg-if" +version = "1.0.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801" + +[[package]] +name = "clap" +version = "4.6.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "301b56658598e48f3648647ac6fc887be7e7108eddfa4e9b63fcf3ec58c0cadf" +dependencies = [ + "clap_builder", + "clap_derive", +] + +[[package]] +name = "clap_builder" +version = "4.6.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "94a65403d1a1bd28f7dc68eb8506e8874808ee5eecb59298de588e2e1407a078" +dependencies = [ + "anstream", + "anstyle", + "clap_lex", + "strsim", +] + +[[package]] +name = "clap_derive" +version = "4.6.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d012d2b9d65aca7f18f4d9878a045bc17899bba951561ba5ec3c2ba1eed9a061" +dependencies = [ + "heck", + "proc-macro2", + "quote", + "syn 3.0.3", +] + +[[package]] +name = "clap_lex" +version = "1.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c8d4a3bb8b1e0c1050499d1815f5ab16d04f0959b233085fb31653fbfc9d98f9" + +[[package]] +name = "clio" +version = "0.3.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b7fc6734af48458f72f5a3fa7b840903606427d98a710256e808f76a965047d9" +dependencies = [ + "cfg-if", + "clap", + "is-terminal", + "libc", + "tempfile", + "walkdir", + "windows-sys 0.42.0", +] + +[[package]] +name = "colorchoice" +version = "1.0.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1d07550c9036bf2ae0c684c4297d503f838287c83c53686d05370d0e139ae570" + +[[package]] +name = "console" +version = "0.16.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4fe5f465a4f6fee88fad41b85d990f84c835335e85b5d9e6e63e0d06d28cba7c" +dependencies = [ + "encode_unicode", + "libc", + "unicode-width", + "windows-sys 0.61.2", +] + +[[package]] +name = "crc32fast" +version = "1.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9481c1c90cbf2ac953f07c8d4a58aa3945c425b7185c9154d67a65e4230da511" +dependencies = [ + "cfg-if", +] + +[[package]] +name = "darling" +version = "0.21.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9cdf337090841a411e2a7f3deb9187445851f91b309c0c0a29e05f74a00a48c0" +dependencies = [ + "darling_core", + "darling_macro", +] + +[[package]] +name = "darling_core" +version = "0.21.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1247195ecd7e3c85f83c8d2a366e4210d588e802133e1e355180a9870b517ea4" +dependencies = [ + "fnv", + "ident_case", + "proc-macro2", + "quote", + "strsim", + "syn 2.0.119", +] + +[[package]] +name = "darling_macro" +version = "0.21.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d38308df82d1080de0afee5d069fa14b0326a88c14f15c5ccda35b4a6c414c81" +dependencies = [ + "darling_core", + "quote", + "syn 2.0.119", +] + +[[package]] +name = "db" +version = "0.1.0" +dependencies = [ + "clap", + "clio", + "diesel", + "flate2", + "indicatif", + "serde", + "serde_json", + "wiktionary-schema", +] + +[[package]] +name = "deranged" +version = "0.5.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7cd812cc2bc1d69d4764bd80df88b4317eaef9e773c75226407d9bc0876b211c" + +[[package]] +name = "diesel" +version = "2.3.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e54d1f576cd3a3460f212a4615fd12ce1b6303c095b79a44449ffbe627753dc1" +dependencies = [ + "diesel_derives", + "downcast-rs", + "libsqlite3-sys", + "sqlite-wasm-rs", + "time", +] + +[[package]] +name = "diesel_derives" +version = "2.3.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d1817b7f4279b947fc4cafddec12b0e5f8727141706561ce3ac94a60bddd1cf5" +dependencies = [ + "diesel_table_macro_syntax", + "dsl_auto_type", + "proc-macro2", + "quote", + "syn 2.0.119", +] + +[[package]] +name = "diesel_table_macro_syntax" +version = "0.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fe2444076b48641147115697648dc743c2c00b61adade0f01ce67133c7babe8c" +dependencies = [ + "syn 2.0.119", +] + +[[package]] +name = "downcast-rs" +version = "2.0.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "117240f60069e65410b3ae1bb213295bd828f707b5bec6596a1afc8793ce0cbc" + +[[package]] +name = "dsl_auto_type" +version = "0.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "dd122633e4bef06db27737f21d3738fb89c8f6d5360d6d9d7635dda142a7757e" +dependencies = [ + "darling", + "either", + "heck", + "proc-macro2", + "quote", + "syn 2.0.119", +] + +[[package]] +name = "either" +version = "1.17.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9e5e8f6c15a24b9a3ee5efec809ccd006d3b30e8b3bb63c39af737c7f87daa1d" + +[[package]] +name = "encode_unicode" +version = "1.0.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "34aa73646ffb006b8f5147f3dc182bd4bcb190227ce861fc4a4844bf8e3cb2c0" + +[[package]] +name = "errno" +version = "0.3.14" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "39cab71617ae0d63f51a36d69f866391735b51691dbda63cf6f96d042b63efeb" +dependencies = [ + "libc", + "windows-sys 0.61.2", +] + +[[package]] +name = "fastrand" +version = "2.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "da7c62ceae207dd37ea5b845da6a0696c799f85e97da1ab5b7910be3c1c80223" + +[[package]] +name = "find-msvc-tools" +version = "0.1.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5baebc0774151f905a1a2cc41989300b1e6fbb29aff0ceffa1064fdd3088d582" + +[[package]] +name = "flate2" +version = "1.1.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "843fba2746e448b37e26a819579957415c8cef339bf08564fe8b7ddbd959573c" +dependencies = [ + "crc32fast", + "miniz_oxide", + "zlib-rs", +] + +[[package]] +name = "fnv" +version = "1.0.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1" + +[[package]] +name = "foldhash" +version = "0.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "77ce24cb58228fbb8aa041425bb1050850ac19177686ea6e0f41a70416f56fdb" + +[[package]] +name = "futures-core" +version = "0.3.33" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2cd50c473c80f6d7c3670a752354b8e569b1a7cbfdc0419ec88e5edad85e0dc7" + +[[package]] +name = "futures-task" +version = "0.3.33" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b231ed28831efb4a61a08580c4bc233ec56bc009f4cd8f52da2c3cb97df0c109" + +[[package]] +name = "futures-util" +version = "0.3.33" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a77a90a256fce34da66415271e30f94ee91c57b04b8a2c042d9cf3220179deaa" +dependencies = [ + "futures-core", + "futures-task", + "pin-project-lite", + "slab", +] + +[[package]] +name = "getrandom" +version = "0.4.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "300e883d756b2e4ec94e02791f39b04b522276138852cfc41d9fb7e904106099" +dependencies = [ + "cfg-if", + "libc", + "r-efi", +] + +[[package]] +name = "hashbrown" +version = "0.16.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "841d1cc9bed7f9236f321df977030373f4a4163ae1a7dbfe1a51a2c1a51d9100" +dependencies = [ + "foldhash", +] + +[[package]] +name = "heck" +version = "0.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea" + +[[package]] +name = "hermit-abi" +version = "0.5.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fc0fef456e4baa96da950455cd02c081ca953b141298e41db3fc7e36b1da849c" + +[[package]] +name = "ident_case" +version = "1.0.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b9e0384b61958566e926dc50660321d12159025e767c18e043daf26b70104c39" + +[[package]] +name = "indicatif" +version = "0.18.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9433806cd6b4ec1aba79c021c7e4c58fb4c3b9977c085062e611ac929998fb0c" +dependencies = [ + "console", + "portable-atomic", + "unicode-width", + "unit-prefix", + "web-time", +] + +[[package]] +name = "is-terminal" +version = "0.4.17" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3640c1c38b8e4e43584d8df18be5fc6b0aa314ce6ebf51b53313d4306cca8e46" +dependencies = [ + "hermit-abi", + "libc", + "windows-sys 0.61.2", +] + +[[package]] +name = "is_terminal_polyfill" +version = "1.70.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a6cb138bb79a146c1bd460005623e142ef0181e3d0219cb493e02f7d08a35695" + +[[package]] +name = "itoa" +version = "1.0.18" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8f42a60cbdf9a97f5d2305f08a87dc4e09308d1276d28c869c684d7777685682" + +[[package]] +name = "js-sys" +version = "0.3.103" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "53b44bfcdb3f8d5837a46dae1ca9660a837176eee74a28b229bc626816589102" +dependencies = [ + "cfg-if", + "futures-util", + "wasm-bindgen", +] + +[[package]] +name = "libc" +version = "0.2.189" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3eaf3ede3fee6db1a4c2ee091bf8a8b4dccdc6d17f656fb07896ee72867612f2" + +[[package]] +name = "libsqlite3-sys" +version = "0.37.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b1f111c8c41e7c61a49cd34e44c7619462967221a6443b0ec299e0ac30cfb9b1" +dependencies = [ + "pkg-config", + "vcpkg", +] + +[[package]] +name = "linux-raw-sys" +version = "0.12.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "32a66949e030da00e8c7d4434b251670a91556f4144941d37452769c25d58a53" + +[[package]] +name = "memchr" +version = "2.8.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "cf8baf1c55e62ffcace7a9f06f4bd9cd3f0c4beb022d3b367256b91b87513d98" + +[[package]] +name = "miniz_oxide" +version = "0.8.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1fa76a2c86f704bdb222d66965fb3d63269ce38518b83cb0575fca855ebb6316" +dependencies = [ + "adler2", + "simd-adler32", +] + +[[package]] +name = "num-conv" +version = "0.2.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "521739c6d2bac4aa25192232afe6841231376b2b26d4d9fae5ecf8ca5772e441" + +[[package]] +name = "once_cell" +version = "1.21.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9f7c3e4beb33f85d45ae3e3a1792185706c8e16d043238c593331cc7cd313b50" + +[[package]] +name = "once_cell_polyfill" +version = "1.70.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "384b8ab6d37215f3c5301a95a4accb5d64aa607f1fcb26a11b5303878451b4fe" + +[[package]] +name = "pin-project-lite" +version = "0.2.17" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a89322df9ebe1c1578d689c92318e070967d1042b512afbe49518723f4e6d5cd" + +[[package]] +name = "pkg-config" +version = "0.3.33" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "19f132c84eca552bf34cab8ec81f1c1dcc229b811638f9d283dceabe58c5569e" + +[[package]] +name = "portable-atomic" +version = "1.14.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3d20d5497ef88037a52ff98267d066e7f11fcc5e99bbfbd58a42336193aacec3" + +[[package]] +name = "powerfmt" +version = "0.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "439ee305def115ba05938db6eb1644ff94165c5ab5e9420d1c1bcedbba909391" + +[[package]] +name = "proc-macro2" +version = "1.0.107" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "985e7ec9bb745e6ce6535b544d84d6cd6f7ad8bd711c398938ae983b91a766d9" +dependencies = [ + "unicode-ident", +] + +[[package]] +name = "quote" +version = "1.0.47" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1fbf4db142a473a8d80c26bbf18454ed458bf8d26c8219c331daecfdbd079001" +dependencies = [ + "proc-macro2", +] + +[[package]] +name = "r-efi" +version = "6.0.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f8dcc9c7d52a811697d2151c701e0d08956f92b0e24136cf4cf27b57a6a0d9bf" + +[[package]] +name = "rsqlite-vfs" +version = "0.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c51c9ae4df8a7fba42103df5c621fa3c37eccf3a3c650879e90fc48b11cc192c" +dependencies = [ + "hashbrown", + "thiserror", +] + +[[package]] +name = "rustix" +version = "1.1.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b6fe4565b9518b83ef4f91bb47ce29620ca828bd32cb7e408f0062e9930ba190" +dependencies = [ + "bitflags", + "errno", + "libc", + "linux-raw-sys", + "windows-sys 0.61.2", +] + +[[package]] +name = "rustversion" +version = "1.0.23" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "cf54715a573b99ac80df0bc206da022bcd442c974952c7b9720069370852e21f" + +[[package]] +name = "same-file" +version = "1.0.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "93fc1dc3aaa9bfed95e02e6eadabb4baf7e3078b0bd1b4d7b6b0b68378900502" +dependencies = [ + "winapi-util", +] + +[[package]] +name = "serde" +version = "1.0.229" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4148590afebada386688f18773da617792bf2ef03ffc1e4cbd2b1d45b023e0ba" +dependencies = [ + "serde_core", + "serde_derive", +] + +[[package]] +name = "serde_core" +version = "1.0.229" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "67dca2c9c51e58a4791a4b1ed58308b39c64224d349a935ab5039aa360942a48" +dependencies = [ + "serde_derive", +] + +[[package]] +name = "serde_derive" +version = "1.0.229" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e7a5d71263a5a7d47b41f6b3f06ba276f10cc18b0931f1799f710578e2309348" +dependencies = [ + "proc-macro2", + "quote", + "syn 3.0.3", +] + +[[package]] +name = "serde_json" +version = "1.0.151" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c841b55ecdae098c80dcae9cf767f6f8a0c2cdb3416bbef72181df4d0fe73f14" +dependencies = [ + "itoa", + "memchr", + "serde", + "serde_core", + "zmij", +] + +[[package]] +name = "shlex" +version = "2.0.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f8fadd59c855ef2080decdef8ff161eb6661b86933c9d82e5ba29dc602a55aba" + +[[package]] +name = "simd-adler32" +version = "0.3.10" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3a219298ac11a56ea9a6d2120044824d6f01aeb034955e7af7bc16858527deea" + +[[package]] +name = "slab" +version = "0.4.12" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0c790de23124f9ab44544d7ac05d60440adc586479ce501c1d6d7da3cd8c9cf5" + +[[package]] +name = "sqlite-wasm-rs" +version = "0.5.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "dc3efc0da82635d7e1ced0053bbbfa8c7ab9645d0bf36ceb4f7127bb85315d75" +dependencies = [ + "cc", + "js-sys", + "rsqlite-vfs", + "wasm-bindgen", +] + +[[package]] +name = "strsim" +version = "0.11.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7da8b5736845d9f2fcb837ea5d9e2628564b3b043a70948a3f0b778838c5fb4f" + +[[package]] +name = "syn" +version = "2.0.119" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "872831b642d1a07999a962a351ed35b955ea2cfc8f3862091e2a240a84f17297" +dependencies = [ + "proc-macro2", + "quote", + "unicode-ident", +] + +[[package]] +name = "syn" +version = "3.0.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "53e9bae58849f64dfa4f5d5ae372c8341f7305f82a3868709269343628b659a3" +dependencies = [ + "proc-macro2", + "quote", + "unicode-ident", +] + +[[package]] +name = "tempfile" +version = "3.27.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "32497e9a4c7b38532efcdebeef879707aa9f794296a4f0244f6f69e9bc8574bd" +dependencies = [ + "fastrand", + "getrandom", + "once_cell", + "rustix", + "windows-sys 0.61.2", +] + +[[package]] +name = "thiserror" +version = "2.0.19" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "09a43598840e33d5b0331f38c5e30d13bb11c11210a4b58f0d9b18a5a5eefcd9" +dependencies = [ + "thiserror-impl", +] + +[[package]] +name = "thiserror-impl" +version = "2.0.19" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "43cbfe0cf76104d42a574802844187e84a305e531ed54455f11fbde0f10541cd" +dependencies = [ + "proc-macro2", + "quote", + "syn 3.0.3", +] + +[[package]] +name = "time" +version = "0.3.55" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "cdb87b95ec50ddfa440816d227a17b2ccbdda963a316a727fda0fc4334f7d134" +dependencies = [ + "deranged", + "num-conv", + "powerfmt", + "serde_core", + "time-core", + "time-macros", +] + +[[package]] +name = "time-core" +version = "0.1.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9e1c906769ad99c88eaa54e728060edef082f8e358ff32030cb7c7d315e81109" + +[[package]] +name = "time-macros" +version = "0.2.32" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7e689342a48d2ea927c87ea50cabf8594854bf940e9310208848d680d668ed85" +dependencies = [ + "num-conv", + "time-core", +] + +[[package]] +name = "unicode-ident" +version = "1.0.24" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75" + +[[package]] +name = "unicode-width" +version = "0.2.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b4ac048d71ede7ee76d585517add45da530660ef4390e49b098733c6e897f254" + +[[package]] +name = "unit-prefix" +version = "0.5.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "81e544489bf3d8ef66c953931f56617f423cd4b5494be343d9b9d3dda037b9a3" + +[[package]] +name = "utf8parse" +version = "0.2.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821" + +[[package]] +name = "vcpkg" +version = "0.2.15" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "accd4ea62f7bb7a82fe23066fb0957d48ef677f6eeb8215f372f52e48bb32426" + +[[package]] +name = "walkdir" +version = "2.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "29790946404f91d9c5d06f9874efddea1dc06c5efe94541a7d6863108e3a5e4b" +dependencies = [ + "same-file", + "winapi-util", +] + +[[package]] +name = "wasm-bindgen" +version = "0.2.126" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4b067c0c11094aef6b7a801c1e34a26affafdf3d051dba08456b868789aaf9a4" +dependencies = [ + "cfg-if", + "once_cell", + "rustversion", + "wasm-bindgen-macro", + "wasm-bindgen-shared", +] + +[[package]] +name = "wasm-bindgen-macro" +version = "0.2.126" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "167ce5e579f6bcf889c4f7175a8a5a585de84e8ff93976ce393efa5f2837aab1" +dependencies = [ + "quote", + "wasm-bindgen-macro-support", +] + +[[package]] +name = "wasm-bindgen-macro-support" +version = "0.2.126" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f3997c7839262f4ef12cf90b818d6340c18e80f263f1a94bf157d0ec4420380e" +dependencies = [ + "bumpalo", + "proc-macro2", + "quote", + "syn 2.0.119", + "wasm-bindgen-shared", +] + +[[package]] +name = "wasm-bindgen-shared" +version = "0.2.126" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "dc1b4cb0cc549fcf58d7dfc081778139b3d283a081644e833e84682ad71cea24" +dependencies = [ + "unicode-ident", +] + +[[package]] +name = "web-time" +version = "1.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5a6580f308b1fad9207618087a65c04e7a10bc77e02c8e84e9b00dd4b12fa0bb" +dependencies = [ + "js-sys", + "wasm-bindgen", +] + +[[package]] +name = "wiktionary-schema" +version = "0.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "36c5f990e2a439ac0e03e23a5089dd0458072a0b1f5752a8f620c5501422adf4" +dependencies = [ + "serde", +] + +[[package]] +name = "winapi-util" +version = "0.1.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c2a7b1c03c876122aa43f3020e6c3c3ee5c05081c9a00739faf7503aeba10d22" +dependencies = [ + "windows-sys 0.61.2", +] + +[[package]] +name = "windows-link" +version = "0.2.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f0805222e57f7521d6a62e36fa9163bc891acd422f971defe97d64e70d0a4fe5" + +[[package]] +name = "windows-sys" +version = "0.42.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5a3e1820f08b8513f676f7ab6c1f99ff312fb97b553d30ff4dd86f9f15728aa7" +dependencies = [ + "windows_aarch64_gnullvm", + "windows_aarch64_msvc", + "windows_i686_gnu", + "windows_i686_msvc", + "windows_x86_64_gnu", + "windows_x86_64_gnullvm", + "windows_x86_64_msvc", +] + +[[package]] +name = "windows-sys" +version = "0.61.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ae137229bcbd6cdf0f7b80a31df61766145077ddf49416a728b02cb3921ff3fc" +dependencies = [ + "windows-link", +] + +[[package]] +name = "windows_aarch64_gnullvm" +version = "0.42.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "597a5118570b68bc08d8d59125332c54f1ba9d9adeedeef5b99b02ba2b0698f8" + +[[package]] +name = "windows_aarch64_msvc" +version = "0.42.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e08e8864a60f06ef0d0ff4ba04124db8b0fb3be5776a5cd47641e942e58c4d43" + +[[package]] +name = "windows_i686_gnu" +version = "0.42.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c61d927d8da41da96a81f029489353e68739737d3beca43145c8afec9a31a84f" + +[[package]] +name = "windows_i686_msvc" +version = "0.42.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "44d840b6ec649f480a41c8d80f9c65108b92d89345dd94027bfe06ac444d1060" + +[[package]] +name = "windows_x86_64_gnu" +version = "0.42.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8de912b8b8feb55c064867cf047dda097f92d51efad5b491dfb98f6bbb70cb36" + +[[package]] +name = "windows_x86_64_gnullvm" +version = "0.42.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "26d41b46a36d453748aedef1486d5c7a85db22e56aff34643984ea85514e94a3" + +[[package]] +name = "windows_x86_64_msvc" +version = "0.42.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9aec5da331524158c6d1a4ac0ab1541149c0b9505fde06423b02f5ef0106b9f0" + +[[package]] +name = "zlib-rs" +version = "0.6.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "34b31d188d9d685a4f9c7b46d6e36631b07058d2cfe190267adce54dc230bf12" + +[[package]] +name = "zmij" +version = "1.0.23" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "29666d0abbfad1e3dc4dcf6144730dd3a3ab225bbbdac83319345b1b44ccfc1b" diff --git a/db/Cargo.toml b/db/Cargo.toml new file mode 100644 index 0000000..442e935 --- /dev/null +++ b/db/Cargo.toml @@ -0,0 +1,14 @@ +[package] +name = "db" +version = "0.1.0" +edition = "2024" + +[dependencies] +clap = { version = "4.6.5", features = ["derive"] } +clio = { version = "0.3.5", features = ["clap-parse"] } +diesel = { version = "2.3.11", features = ["sqlite"] } +flate2 = { version = "1.1.9", features = ["zlib-rs"] } +indicatif = "0.18.6" +serde = "1.0.229" +serde_json = "1.0.151" +wiktionary-schema = "0.3.0" diff --git a/db/default.nix b/db/default.nix new file mode 100644 index 0000000..3c3009f --- /dev/null +++ b/db/default.nix @@ -0,0 +1,9 @@ +{ rustPlatform +}: + +rustPlatform.buildRustPackage (finalAttrs: { + pname = "make-db"; + version = "0.1.0"; + src = ./.; + cargoLock.lockFile = ./Cargo.lock; +}) diff --git a/db/diesel.toml b/db/diesel.toml new file mode 100644 index 0000000..a0d61bf --- /dev/null +++ b/db/diesel.toml @@ -0,0 +1,9 @@ +# For documentation on how to configure this file, +# see https://diesel.rs/guides/configuring-diesel-cli + +[print_schema] +file = "src/schema.rs" +custom_type_derives = ["diesel::query_builder::QueryId", "Clone"] + +[migrations_directory] +dir = "migrations" diff --git a/db/migrations/.diesel_lock b/db/migrations/.diesel_lock new file mode 100644 index 0000000..e69de29 diff --git a/db/migrations/.keep b/db/migrations/.keep new file mode 100644 index 0000000..e69de29 diff --git a/db/migrations/2026-08-04-180241-0000_create-words/down.sql b/db/migrations/2026-08-04-180241-0000_create-words/down.sql new file mode 100644 index 0000000..4330df3 --- /dev/null +++ b/db/migrations/2026-08-04-180241-0000_create-words/down.sql @@ -0,0 +1,2 @@ +-- This file should undo anything in `up.sql` +drop table words diff --git a/db/migrations/2026-08-04-180241-0000_create-words/up.sql b/db/migrations/2026-08-04-180241-0000_create-words/up.sql new file mode 100644 index 0000000..182f008 --- /dev/null +++ b/db/migrations/2026-08-04-180241-0000_create-words/up.sql @@ -0,0 +1,6 @@ +-- Your SQL goes here +create table words ( + id integer not null primary key autoincrement, + word varchar not null, + info text not null +) diff --git a/db/src/db.rs b/db/src/db.rs new file mode 100644 index 0000000..d59372f --- /dev/null +++ b/db/src/db.rs @@ -0,0 +1,45 @@ +use diesel::prelude::*; +use std::env; +use crate::models::*; + +pub fn connect () -> SqliteConnection { + let database_url = env::var ("DATABASE_URL") + .expect ("DATABASE_URL must be set"); + SqliteConnection::establish (&database_url) + .unwrap_or_else (|_| panic! ("Error connecting to {}", database_url)) +} + +pub fn get_word (w : &str) -> Vec { + let conn = &mut connect (); + use crate::schema::words::dsl::*; + let results = words + .filter (word.eq (w)) + .limit (5) + .select (Word::as_select ()) + .load (conn) + .expect ("error loading words"); + for wd in results { + println! ("{}", wd.word); + } + todo! () +} + +pub fn entry_as_word (entry : &serde_json::Value) -> Option<&str> { + entry.get ("word")?.as_str () +} + +pub fn insert_word ( + conn : &mut SqliteConnection, + entry : serde_json::Value, +) -> Option<()> { + use crate::schema::words; + let new_word = NewWord { + word: entry_as_word (&entry)?, + info: &entry.to_string (), + }; + diesel::insert_into (words::table) + .values (new_word) + .execute (conn) + .expect ("error saving new word"); + Some (()) +} diff --git a/db/src/main.rs b/db/src/main.rs new file mode 100644 index 0000000..5ead5bb --- /dev/null +++ b/db/src/main.rs @@ -0,0 +1,52 @@ +pub mod models; +pub mod schema; +pub mod db; + +use flate2::read::GzDecoder; +use indicatif::ProgressBar; +use serde_json::Value; +use wiktionary_schema::en::WordData; +use std::{fs::File, io::{self, BufRead, BufReader}, path::PathBuf}; +use clap::Parser; + +/// Build an SQLite database from a Wiktextract JSONLines dump. +#[derive(Parser, Debug)] +#[command(name = "make-db", version, about, long_about = None)] +struct Args { + /// Input file + #[clap(long, value_parser)] + wiktextract_dump : PathBuf, + + /// Output file + #[clap(long, value_parser)] + database : Option, +} + +fn open_wiktextract_dump (path : PathBuf) -> Result< + BufReader>, io::Error +> { + Ok (BufReader::new (GzDecoder::new (File::open (path)?))) +} + +#[allow(nonstandard_style)] +const wiktextract_dump_lines : u64 = 10736399; + +fn main() -> Result<(), String> { + let args = Args::parse (); + let d = open_wiktextract_dump (args.wiktextract_dump).unwrap (); + let bar = ProgressBar::new (wiktextract_dump_lines); + let conn = &mut db::connect (); + + for i in d.lines () { + if let Ok (word) = serde_json::from_str:: ( + &i.expect ("entry") + ) { + bar.println (db::entry_as_word (&word).map_or ("", |x| x)); + db::insert_word (conn, word); + bar.inc (1); + } + } + + bar.finish (); + Ok (()) +} diff --git a/db/src/models.rs b/db/src/models.rs new file mode 100644 index 0000000..2d96726 --- /dev/null +++ b/db/src/models.rs @@ -0,0 +1,17 @@ +use diesel::prelude::*; + +#[derive(Queryable, Selectable)] +#[diesel(table_name = crate::schema::words)] +#[diesel(check_for_backend(diesel::sqlite::Sqlite))] +pub struct Word { + pub id : i32, + pub word : String, + pub info : String, +} + +#[derive(Insertable)] +#[diesel(table_name = crate::schema::words)] +pub struct NewWord<'a> { + pub word : &'a str, + pub info : &'a str, +} diff --git a/db/src/schema.rs b/db/src/schema.rs new file mode 100644 index 0000000..ec448ae --- /dev/null +++ b/db/src/schema.rs @@ -0,0 +1,9 @@ +// @generated automatically by Diesel CLI. + +diesel::table! { + words (id) { + id -> Integer, + word -> Text, + info -> Text, + } +} diff --git a/db/words.db-journal b/db/words.db-journal new file mode 100644 index 0000000000000000000000000000000000000000..16ebe0ddf56d5a1f28a40d4b10b09b14c926c834 GIT binary patch literal 12824 zcmZQT0yaNOWEmL#7BVm}F)%O)Ajym}hi?e{E#zfjU|{6nW8mN$zP=pw*=PuihQMeD zjE2By2#kgRz7XioZCcOI${;#FG&`rXtXe6xq%t=@CqKP1z9cobASbaTwOGk2x>_l* zD7{$8s#?iV$x5j#Ur9&FNXbemB~?jB$ymus$vY>pG*ziqM=7=T2X$k0J|TN(pX> z8B_w~uH?iLP=O07stgm8lT&jbL2U&pm})=@(u`1q^YU|R3X~vDQ?gP5hfooyR75XS zLE)#M0do#GI1_agAZ`HjiZzwsWi7~~$b~mrflrcIW%;_`@TiT|QOZfoOINZ|3d_$) zEI7O;TL~f(pPZipDk{O%O+kLKl9duzhmKNlYF;t4UP?|ZNlni$$^>(j0us|xixtW< zOEMG;6;ks`iYk?KkOe_PAf-BRyTGb4VVW}YlJkp-Qj<#*Ku#)6Oixt+`8l;n2}wsz zYHlvL;DNbU0pu)DB)|nqQj2nn6;e`*GRsm^AXN~w%0V^=iz-M(r4*~9l%A7c4DqBA zxWWSkQ)XT^sFsR`i0DA5*jOE<;>x`Iyh>;lR-Rv!0!lidx~Mi56uvN#oYFF-TAQEc z*$fN}tl)6~{?82jpYgR1M&(9BU^E0qLtr!nMnhmU1V%$(Gz3ONU^E0qLtr!nMnhmU z1cq1$a5FNCGlK>LiW#Q&L)L#VFa`(uWR|2VfQIf8OB9S51Q-|@85|T87#P+*gRBpM z`;vo!fq@0iV_;xJV&h=0ea4{I`-_*)n1O}YnSt*F|6<;Uyv{fjj|z{5z-S1JhQMeD zjE2By2#kinXb6mkz-S1JhQMGCfktUoc5!iW#wJnl3LbC|3rw&$2e~?ixGID=I{CON zfQ1w^xD+5DGesdYuOu}+wMZc^zeFLgG$%))peQppv8YlZJGD|Fv9u&VGcUO)H8(Y{ zLd_>|1l;?$h@;^d6f z+{F0Y%=Dr}&;qGq+%ilk-p8#D5r<`|MWEGg3So{x&K{0I8m0!C3IRc$zK%hW3f``f z3V!|}3VxwJKJW-CD$R?}&r=BT^mPpmar6y