feat(corp/data-import): add import of OpenRussian 'words' table r/5729

This is actually the lemmata table of this corpus, not the forms of
all words (they're in a separate table).

Change-Id: I89a2c2817ccce840f47406fa2a636f4ed3f49154
Reviewed-on: https://cl.tvl.fyi/c/depot/+/7893
Reviewed-by: tazjin <tazjin@tvl.su>
Tested-by: BuildkiteCI

1 files changed, 115 insertions, 0 deletions

diff --git a/corp/russian/data-import/Cargo.lock b/corp/russian/data-import/Cargo.lock
index 125b62d43e90..cd85e058108f 100644
--- a/corp/russian/data-import/Cargo.lock
+++ b/corp/russian/data-import/Cargo.lock
@@ -29,6 +29,18 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
 
 [[package]]
+name = "bstr"
+version = "0.2.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ba3569f383e8f1598449f1a423e72e99569137b47740b1da11ef19af3d5c3223"
+dependencies = [
+ "lazy_static",
+ "memchr",
+ "regex-automata",
+ "serde",
+]
+
+[[package]]
 name = "cc"
 version = "1.0.78"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -41,12 +53,36 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
 
 [[package]]
+name = "csv"
+version = "1.1.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "22813a6dc45b335f9bade10bf7271dc477e81113e89eb251a0bc2a8a81c536e1"
+dependencies = [
+ "bstr",
+ "csv-core",
+ "itoa",
+ "ryu",
+ "serde",
+]
+
+[[package]]
+name = "csv-core"
+version = "0.1.10"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2b2466559f260f48ad25fe6317b3c8dac77b5bdb5763ac7d9d6103530663bc90"
+dependencies = [
+ "memchr",
+]
+
+[[package]]
 name = "data-import"
 version = "0.1.0"
 dependencies = [
+ "csv",
  "env_logger",
  "log",
  "rusqlite",
+ "serde",
  "xml-rs",
 ]
 
@@ -163,6 +199,18 @@ dependencies = [
 ]
 
 [[package]]
+name = "itoa"
+version = "0.4.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b71991ff56294aa922b450139ee08b3bfc70982c6b2c7562771375cf73542dd4"
+
+[[package]]
+name = "lazy_static"
+version = "1.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e2abad23fbc42b3700f2f279844dc832adb2b2eb069b2df918f455c4e18cc646"
+
+[[package]]
 name = "libc"
 version = "0.2.139"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -212,6 +260,24 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6ac9a59f73473f1b8d852421e59e64809f025994837ef743615c6d0c5b305160"
 
 [[package]]
+name = "proc-macro2"
+version = "1.0.50"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6ef7d57beacfaf2d8aee5937dab7b7f28de3cb8b1828479bb5de2a7106f2bae2"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "quote"
+version = "1.0.23"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8856d8364d252a14d474036ea1358d63c9e6965c8e5c1885c18f73d70bff9c7b"
+dependencies = [
+ "proc-macro2",
+]
+
+[[package]]
 name = "regex"
 version = "1.7.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -223,6 +289,12 @@ dependencies = [
 ]
 
 [[package]]
+name = "regex-automata"
+version = "0.1.10"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6c230d73fb8d8c1b9c0b3135c5142a8acee3a0558fb8db5cf1cb65f8d7862132"
+
+[[package]]
 name = "regex-syntax"
 version = "0.6.28"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -257,12 +329,49 @@ dependencies = [
 ]
 
 [[package]]
+name = "ryu"
+version = "1.0.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7b4b9743ed687d4b4bcedf9ff5eaa7398495ae14e61cba0a295704edbc7decde"
+
+[[package]]
+name = "serde"
+version = "1.0.152"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bb7d1f0d3021d347a83e556fc4683dea2ea09d87bccdf88ff5c12545d89d5efb"
+dependencies = [
+ "serde_derive",
+]
+
+[[package]]
+name = "serde_derive"
+version = "1.0.152"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "af487d118eecd09402d70a5d72551860e788df87b464af30e5ea6a38c75c541e"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
 name = "smallvec"
 version = "1.10.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a507befe795404456341dfab10cef66ead4c041f62b8b11bbb92bffe5d0953e0"
 
 [[package]]
+name = "syn"
+version = "1.0.107"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1f4064b5b16e03ae50984a5a8ed5d4f8803e6bc1fd170a3cda91a1be4b18e3f5"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
 name = "termcolor"
 version = "1.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -272,6 +381,12 @@ dependencies = [
 ]
 
 [[package]]
+name = "unicode-ident"
+version = "1.0.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "84a22b9f218b40614adcb3f4ff08b703773ad44fa9423e4e0d346d5db86e4ebc"
+
+[[package]]
 name = "vcpkg"
 version = "0.2.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"