refactor: fetch html as markdown (#723)

1 files changed, 176 insertions, 0 deletions

diff --git a/Cargo.lock b/Cargo.lock
index 1d68226..8597201 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -60,6 +60,7 @@ dependencies = [
  "futures-util",
  "hmac",
  "hnsw_rs",
+ "html2text",
  "http",
  "http-body-util",
  "hyper",
@@ -844,6 +845,16 @@ dependencies = [
 ]
 
 [[package]]
+name = "futf"
+version = "0.1.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "df420e2e84819663797d1ec6544b13c5be84629e7bb00dc960d6917db2987843"
+dependencies = [
+ "mac",
+ "new_debug_unreachable",
+]
+
+[[package]]
 name = "futures-channel"
 version = "0.3.30"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -1070,6 +1081,33 @@ dependencies = [
 ]
 
 [[package]]
+name = "html2text"
+version = "0.12.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8c66ee488a63a92237d5b48875b7e05bb293be8fb2894641c8118b60c08ab5ef"
+dependencies = [
+ "html5ever",
+ "markup5ever",
+ "tendril",
+ "thiserror",
+ "unicode-width",
+]
+
+[[package]]
+name = "html5ever"
+version = "0.27.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c13771afe0e6e846f1e67d038d4cb29998a6779f93c809212e4e9c32efd244d4"
+dependencies = [
+ "log",
+ "mac",
+ "markup5ever",
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
 name = "http"
 version = "1.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -1383,6 +1421,12 @@ dependencies = [
 ]
 
 [[package]]
+name = "mac"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c41e0c4fef86961ac6d6f8a82609f55f31b05e4fce149ac5710e439df7619ba4"
+
+[[package]]
 name = "mach2"
 version = "0.4.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -1392,6 +1436,20 @@ dependencies = [
 ]
 
 [[package]]
+name = "markup5ever"
+version = "0.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "16ce3abbeba692c8b8441d036ef91aea6df8da2c6b6e21c7e14d3c18e526be45"
+dependencies = [
+ "log",
+ "phf",
+ "phf_codegen",
+ "string_cache",
+ "string_cache_codegen",
+ "tendril",
+]
+
+[[package]]
 name = "matchers"
 version = "0.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -1476,6 +1534,12 @@ dependencies = [
 ]
 
 [[package]]
+name = "new_debug_unreachable"
+version = "1.0.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "650eef8c711430f1a879fdd01d4745a7deea475becfb90269c06775983bbf086"
+
+[[package]]
 name = "newline-converter"
 version = "0.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -1809,6 +1873,63 @@ dependencies = [
 ]
 
 [[package]]
+name = "phf"
+version = "0.11.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ade2d8b8f33c7333b51bcf0428d37e217e9f32192ae4772156f65063b8ce03dc"
+dependencies = [
+ "phf_shared 0.11.2",
+]
+
+[[package]]
+name = "phf_codegen"
+version = "0.11.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e8d39688d359e6b34654d328e262234662d16cc0f60ec8dcbe5e718709342a5a"
+dependencies = [
+ "phf_generator 0.11.2",
+ "phf_shared 0.11.2",
+]
+
+[[package]]
+name = "phf_generator"
+version = "0.10.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5d5285893bb5eb82e6aaf5d59ee909a06a16737a8970984dd7746ba9283498d6"
+dependencies = [
+ "phf_shared 0.10.0",
+ "rand",
+]
+
+[[package]]
+name = "phf_generator"
+version = "0.11.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "48e4cc64c2ad9ebe670cb8fd69dd50ae301650392e81c05f9bfcb2d5bdbc24b0"
+dependencies = [
+ "phf_shared 0.11.2",
+ "rand",
+]
+
+[[package]]
+name = "phf_shared"
+version = "0.10.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b6796ad771acdc0123d2a88dc428b5e38ef24456743ddb1744ed628f9815c096"
+dependencies = [
+ "siphasher",
+]
+
+[[package]]
+name = "phf_shared"
+version = "0.11.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "90fcb95eef784c2ac79119d1dd819e162b5da872ce6f3c3abe1e8ca1c082f72b"
+dependencies = [
+ "siphasher",
+]
+
+[[package]]
 name = "pin-project"
 version = "1.1.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -1872,6 +1993,12 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5b40af805b3121feab8a3c29f04d8ad262fa8e0561883e7653e024ae4479e6de"
 
 [[package]]
+name = "precomputed-hash"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "925383efa346730478fb4838dbe9137d2a47675ad789c546d150a6e1dd4ab31c"
+
+[[package]]
 name = "pretty_assertions"
 version = "1.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -2454,6 +2581,12 @@ dependencies = [
 ]
 
 [[package]]
+name = "siphasher"
+version = "0.3.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "38b58827f4464d87d377d175e90bf58eb00fd8716ff0a62f80356b5e61555d0d"
+
+[[package]]
 name = "slab"
 version = "0.4.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -2491,6 +2624,32 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6980e8d7511241f8acf4aebddbb1ff938df5eebe98691418c4468d0b72a96a67"
 
 [[package]]
+name = "string_cache"
+version = "0.8.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f91138e76242f575eb1d3b38b4f1362f10d3a43f47d182a5b359af488a02293b"
+dependencies = [
+ "new_debug_unreachable",
+ "once_cell",
+ "parking_lot",
+ "phf_shared 0.10.0",
+ "precomputed-hash",
+ "serde",
+]
+
+[[package]]
+name = "string_cache_codegen"
+version = "0.5.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6bb30289b722be4ff74a408c3cc27edeaad656e06cb1fe8fa9231fa59c728988"
+dependencies = [
+ "phf_generator 0.10.0",
+ "phf_shared 0.10.0",
+ "proc-macro2",
+ "quote",
+]
+
+[[package]]
 name = "strip-ansi-escapes"
 version = "0.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -2595,6 +2754,17 @@ dependencies = [
 ]
 
 [[package]]
+name = "tendril"
+version = "0.4.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d24a120c5fc464a3458240ee02c299ebcb9d67b5249c8848b09d639dca8d7bb0"
+dependencies = [
+ "futf",
+ "mac",
+ "utf-8",
+]
+
+[[package]]
 name = "termcolor"
 version = "1.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -2974,6 +3144,12 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "daf8dba3b7eb870caf1ddeed7bc9d2a049f3cfdfae7cb521b087cc33ae4c49da"
 
 [[package]]
+name = "utf-8"
+version = "0.7.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "09cc8ee72d2a9becf2f2febe0205bbed8fc6615b7cb429ad062dc7b7ddd036a9"
+
+[[package]]
 name = "utf8parse"
 version = "0.2.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"