diff --git a/src/css.rs b/src/css.rs
index 3357a56..1abe8cd 100644
--- a/src/css.rs
+++ b/src/css.rs
@@ -2,7 +2,8 @@ use cssparser::{ParseError, Parser, ParserInput, SourcePosition, Token};
use reqwest::blocking::Client;
use std::collections::HashMap;
-use crate::utils::{data_to_data_url, get_url_fragment, is_http_url, resolve_url, retrieve_asset};
+use crate::url::{data_to_data_url, get_url_fragment, is_http_url, resolve_url, url_with_fragment};
+use crate::utils::retrieve_asset;
const CSS_PROPS_WITH_IMAGE_URLS: &[&str] = &[
// Universal
@@ -173,32 +174,34 @@ pub fn process_css<'a>(
let import_url_fragment = get_url_fragment(import_full_url.clone());
match retrieve_asset(cache, client, &parent_url, &import_full_url, opt_silent) {
Ok((import_contents, import_final_url, _import_media_type)) => {
- result.push_str(
- enquote(
- data_to_data_url(
- "text/css",
- embed_css(
- cache,
- client,
- &import_final_url,
- &String::from_utf8_lossy(&import_contents),
- opt_no_fonts,
- opt_no_images,
- opt_silent,
- )
- .as_bytes(),
- &import_final_url,
- &import_url_fragment,
- ),
- false,
+ let import_data_url = data_to_data_url(
+ "text/css",
+ embed_css(
+ cache,
+ client,
+ &import_final_url,
+ &String::from_utf8_lossy(&import_contents),
+ opt_no_fonts,
+ opt_no_images,
+ opt_silent,
)
- .as_str(),
+ .as_bytes(),
+ &import_final_url,
+ );
+ let assembled_url: String = url_with_fragment(
+ import_data_url.as_str(),
+ import_url_fragment.as_str(),
);
+ result.push_str(enquote(assembled_url, false).as_str());
}
Err(_) => {
// Keep remote reference if unable to retrieve the asset
if is_http_url(import_full_url.clone()) {
- result.push_str(enquote(import_full_url, false).as_str());
+ let assembled_url: String = url_with_fragment(
+ import_full_url.as_str(),
+ import_url_fragment.as_str(),
+ );
+ result.push_str(enquote(assembled_url, false).as_str());
}
}
}
@@ -222,18 +225,19 @@ pub fn process_css<'a>(
opt_silent,
) {
Ok((data, final_url, media_type)) => {
- let data_url = data_to_data_url(
- &media_type,
- &data,
- &final_url,
- &url_fragment,
- );
- result.push_str(enquote(data_url, false).as_str());
+ let data_url = data_to_data_url(&media_type, &data, &final_url);
+ let assembled_url: String =
+ url_with_fragment(data_url.as_str(), url_fragment.as_str());
+ result.push_str(enquote(assembled_url, false).as_str());
}
Err(_) => {
// Keep remote reference if unable to retrieve the asset
if is_http_url(resolved_url.clone()) {
- result.push_str(enquote(resolved_url, false).as_str());
+ let assembled_url: String = url_with_fragment(
+ resolved_url.as_str(),
+ url_fragment.as_str(),
+ );
+ result.push_str(enquote(assembled_url, false).as_str());
}
}
}
@@ -320,14 +324,17 @@ pub fn process_css<'a>(
)
.as_bytes(),
&final_url,
- &url_fragment,
);
- result.push_str(enquote(data_url, false).as_str());
+ let assembled_url: String =
+ url_with_fragment(data_url.as_str(), url_fragment.as_str());
+ result.push_str(enquote(assembled_url, false).as_str());
}
Err(_) => {
// Keep remote reference if unable to retrieve the asset
if is_http_url(full_url.clone()) {
- result.push_str(enquote(full_url, false).as_str());
+ let assembled_url: String =
+ url_with_fragment(full_url.as_str(), url_fragment.as_str());
+ result.push_str(enquote(assembled_url, false).as_str());
}
}
}
@@ -339,14 +346,17 @@ pub fn process_css<'a>(
let url_fragment = get_url_fragment(full_url.clone());
match retrieve_asset(cache, client, &parent_url, &full_url, opt_silent) {
Ok((data, final_url, media_type)) => {
- let data_url =
- data_to_data_url(&media_type, &data, &final_url, &url_fragment);
- result.push_str(enquote(data_url, false).as_str());
+ let data_url = data_to_data_url(&media_type, &data, &final_url);
+ let assembled_url: String =
+ url_with_fragment(data_url.as_str(), url_fragment.as_str());
+ result.push_str(enquote(assembled_url, false).as_str());
}
Err(_) => {
// Keep remote reference if unable to retrieve the asset
if is_http_url(full_url.clone()) {
- result.push_str(enquote(full_url, false).as_str());
+ let assembled_url: String =
+ url_with_fragment(full_url.as_str(), url_fragment.as_str());
+ result.push_str(enquote(assembled_url, false).as_str());
}
}
}
diff --git a/src/html.rs b/src/html.rs
index 8590655..e2dead3 100644
--- a/src/html.rs
+++ b/src/html.rs
@@ -1,8 +1,3 @@
-use crate::css::embed_css;
-use crate::js::attr_is_event_handler;
-use crate::utils::{
- data_to_data_url, get_url_fragment, is_http_url, resolve_url, retrieve_asset, url_has_protocol,
-};
use base64;
use html5ever::interface::QualName;
use html5ever::parse_document;
@@ -16,6 +11,14 @@ use sha2::{Digest, Sha256, Sha384, Sha512};
use std::collections::HashMap;
use std::default::Default;
+use crate::css::embed_css;
+use crate::js::attr_is_event_handler;
+use crate::url::{
+ data_to_data_url, get_url_fragment, is_http_url, resolve_url, url_has_protocol,
+ url_with_fragment,
+};
+use crate::utils::retrieve_asset;
+
struct SrcSetItem<'a> {
path: &'a str,
descriptor: &'a str,
@@ -91,19 +94,19 @@ pub fn embed_srcset(
let image_url_fragment = get_url_fragment(image_full_url.clone());
match retrieve_asset(cache, client, &parent_url, &image_full_url, opt_silent) {
Ok((image_data, image_final_url, image_media_type)) => {
- let image_data_url = data_to_data_url(
- &image_media_type,
- &image_data,
- &image_final_url,
- &image_url_fragment,
- );
+ let image_data_url =
+ data_to_data_url(&image_media_type, &image_data, &image_final_url);
// Append retreved asset as a data URL
- result.push_str(image_data_url.as_ref());
+ let assembled_url: String =
+ url_with_fragment(image_data_url.as_str(), image_url_fragment.as_str());
+ result.push_str(assembled_url.as_ref());
}
Err(_) => {
// Keep remote reference if unable to retrieve the asset
if is_http_url(image_full_url.clone()) {
- result.push_str(image_full_url.as_ref());
+ let assembled_url: String =
+ url_with_fragment(image_full_url.as_str(), image_url_fragment.as_str());
+ result.push_str(assembled_url.as_ref());
} else {
// Avoid breaking the structure in case if not an HTTP(S) URL
result.push_str(empty_image!());
@@ -246,33 +249,36 @@ pub fn walk_and_embed_assets(
&link_href_media_type,
&link_href_data,
&link_href_final_url,
- &link_href_url_fragment,
);
// Add new data URL href attribute
+ let assembled_url: String = url_with_fragment(
+ link_href_data_url.as_str(),
+ link_href_url_fragment.as_str(),
+ );
attrs_mut.push(Attribute {
name: QualName::new(
None,
ns!(),
local_name!("href"),
),
- value: Tendril::from_slice(
- link_href_data_url.as_ref(),
- ),
+ value: Tendril::from_slice(assembled_url.as_ref()),
});
}
}
Err(_) => {
// Keep remote reference if unable to retrieve the asset
if is_http_url(link_href_full_url.clone()) {
+ let assembled_url: String = url_with_fragment(
+ link_href_full_url.as_str(),
+ link_href_url_fragment.as_str(),
+ );
attrs_mut.push(Attribute {
name: QualName::new(
None,
ns!(),
local_name!("href"),
),
- value: Tendril::from_slice(
- link_href_full_url.as_ref(),
- ),
+ value: Tendril::from_slice(assembled_url.as_ref()),
});
}
}
@@ -324,7 +330,6 @@ pub fn walk_and_embed_assets(
"text/css",
css.as_bytes(),
&link_href_final_url,
- "",
);
// Add new data URL href attribute
attrs_mut.push(Attribute {
@@ -399,20 +404,27 @@ pub fn walk_and_embed_assets(
&background_media_type,
&background_data,
&background_final_url,
- &background_url_fragment,
);
// Add new data URL background attribute
+ let assembled_url: String = url_with_fragment(
+ background_data_url.as_str(),
+ background_url_fragment.as_str(),
+ );
attrs_mut.push(Attribute {
name: QualName::new(None, ns!(), local_name!("background")),
- value: Tendril::from_slice(background_data_url.as_ref()),
+ value: Tendril::from_slice(assembled_url.as_ref()),
});
}
Err(_) => {
// Keep remote reference if unable to retrieve the asset
if is_http_url(background_full_url.clone()) {
+ let assembled_url: String = url_with_fragment(
+ background_full_url.as_str(),
+ background_url_fragment.as_str(),
+ );
attrs_mut.push(Attribute {
name: QualName::new(None, ns!(), local_name!("background")),
- value: Tendril::from_slice(background_full_url.as_ref()),
+ value: Tendril::from_slice(assembled_url.as_ref()),
});
}
}
@@ -469,19 +481,26 @@ pub fn walk_and_embed_assets(
&img_media_type,
&img_data,
&img_final_url,
- &img_url_fragment,
+ );
+ let assembled_url: String = url_with_fragment(
+ img_data_url.as_str(),
+ img_url_fragment.as_str(),
);
attrs_mut.push(Attribute {
name: QualName::new(None, ns!(), local_name!("src")),
- value: Tendril::from_slice(img_data_url.as_ref()),
+ value: Tendril::from_slice(assembled_url.as_ref()),
});
}
Err(_) => {
// Keep remote reference if unable to retrieve the asset
if is_http_url(img_full_url.clone()) {
+ let assembled_url: String = url_with_fragment(
+ img_full_url.as_str(),
+ img_url_fragment.as_str(),
+ );
attrs_mut.push(Attribute {
name: QualName::new(None, ns!(), local_name!("src")),
- value: Tendril::from_slice(img_full_url.as_ref()),
+ value: Tendril::from_slice(assembled_url.as_ref()),
});
}
}
@@ -563,22 +582,27 @@ pub fn walk_and_embed_assets(
&input_image_media_type,
&input_image_data,
&input_image_final_url,
- &input_image_url_fragment,
);
// Add data URL src attribute
+ let assembled_url: String = url_with_fragment(
+ input_image_data_url.as_str(),
+ input_image_url_fragment.as_str(),
+ );
attrs_mut.push(Attribute {
name: QualName::new(None, ns!(), local_name!("src")),
- value: Tendril::from_slice(input_image_data_url.as_ref()),
+ value: Tendril::from_slice(assembled_url.as_ref()),
});
}
Err(_) => {
// Keep remote reference if unable to retrieve the asset
if is_http_url(input_image_full_url.clone()) {
+ let assembled_url: String = url_with_fragment(
+ input_image_full_url.as_str(),
+ input_image_url_fragment.as_str(),
+ );
attrs_mut.push(Attribute {
name: QualName::new(None, ns!(), local_name!("src")),
- value: Tendril::from_slice(
- input_image_full_url.as_ref(),
- ),
+ value: Tendril::from_slice(assembled_url.as_ref()),
});
}
}
@@ -610,20 +634,27 @@ pub fn walk_and_embed_assets(
&image_media_type,
&image_data,
&image_final_url,
- &image_url_fragment,
);
// Add new data URL href attribute
+ let assembled_url: String = url_with_fragment(
+ image_data_url.as_str(),
+ image_url_fragment.as_str(),
+ );
attrs_mut.push(Attribute {
name: QualName::new(None, ns!(), local_name!("href")),
- value: Tendril::from_slice(image_data_url.as_ref()),
+ value: Tendril::from_slice(assembled_url.as_ref()),
});
}
Err(_) => {
// Keep remote reference if unable to retrieve the asset
if is_http_url(image_full_url.clone()) {
+ let assembled_url: String = url_with_fragment(
+ image_full_url.as_str(),
+ image_url_fragment.as_str(),
+ );
attrs_mut.push(Attribute {
name: QualName::new(None, ns!(), local_name!("href")),
- value: Tendril::from_slice(image_full_url.as_ref()),
+ value: Tendril::from_slice(assembled_url.as_ref()),
});
}
}
@@ -661,21 +692,23 @@ pub fn walk_and_embed_assets(
&srcset_media_type,
&srcset_data,
&srcset_final_url,
- &srcset_url_fragment,
);
attr.value.clear();
- attr.value.push_slice(srcset_data_url.as_str());
+ let assembled_url: String = url_with_fragment(
+ srcset_data_url.as_str(),
+ srcset_url_fragment.as_str(),
+ );
+ attr.value.push_slice(assembled_url.as_str());
}
Err(_) => {
// Keep remote reference if unable to retrieve the asset
if is_http_url(srcset_full_url.clone()) {
attr.value.clear();
- attr.value.push_slice(srcset_full_url.as_str());
- if !srcset_url_fragment.is_empty() {
- attr.value.push_slice("#");
- attr.value
- .push_slice(srcset_url_fragment.as_str());
- }
+ let assembled_url: String = url_with_fragment(
+ srcset_full_url.as_str(),
+ srcset_url_fragment.as_str(),
+ );
+ attr.value.push_slice(assembled_url.as_str());
}
}
}
@@ -739,7 +772,6 @@ pub fn walk_and_embed_assets(
"application/javascript",
&script_data,
&script_final_url,
- "",
);
// Add new data URL src attribute
attrs_mut.push(Attribute {
@@ -844,16 +876,23 @@ pub fn walk_and_embed_assets(
&frame_media_type,
&frame_data,
&frame_final_url,
- &frame_url_fragment,
);
attr.value.clear();
- attr.value.push_slice(frame_data_url.as_str());
+ let assembled_url: String = url_with_fragment(
+ frame_data_url.as_str(),
+ frame_url_fragment.as_str(),
+ );
+ attr.value.push_slice(assembled_url.as_str());
}
Err(_) => {
// Keep remote reference if unable to retrieve the asset
if is_http_url(frame_full_url.clone()) {
attr.value.clear();
- attr.value.push_slice(frame_full_url.as_str());
+ let assembled_url: String = url_with_fragment(
+ frame_full_url.as_str(),
+ frame_url_fragment.as_str(),
+ );
+ attr.value.push_slice(assembled_url.as_str());
}
}
}
@@ -896,16 +935,23 @@ pub fn walk_and_embed_assets(
&video_poster_media_type,
&video_poster_data,
&video_poster_final_url,
- &video_poster_url_fragment,
);
attr.value.clear();
- attr.value.push_slice(video_poster_data_url.as_str());
+ let assembled_url: String = url_with_fragment(
+ video_poster_data_url.as_str(),
+ video_poster_url_fragment.as_str(),
+ );
+ attr.value.push_slice(assembled_url.as_str());
}
Err(_) => {
// Keep remote reference if unable to retrieve the asset
if is_http_url(video_poster_full_url.clone()) {
attr.value.clear();
- attr.value.push_slice(video_poster_full_url.as_str());
+ let assembled_url: String = url_with_fragment(
+ video_poster_full_url.as_str(),
+ video_poster_url_fragment.as_str(),
+ );
+ attr.value.push_slice(assembled_url.as_str());
}
}
}
diff --git a/src/lib.rs b/src/lib.rs
index a9034d5..024a8c2 100644
--- a/src/lib.rs
+++ b/src/lib.rs
@@ -4,6 +4,7 @@ mod macros;
pub mod css;
pub mod html;
pub mod js;
+pub mod url;
pub mod utils;
#[cfg(test)]
diff --git a/src/main.rs b/src/main.rs
index 330f1cd..0a72c14 100644
--- a/src/main.rs
+++ b/src/main.rs
@@ -1,6 +1,4 @@
use chrono::prelude::*;
-use monolith::html::{html_to_dom, stringify_document, walk_and_embed_assets};
-use monolith::utils::{data_url_to_data, is_data_url, is_file_url, is_http_url, retrieve_asset};
use reqwest::blocking::Client;
use reqwest::header::{HeaderMap, HeaderValue, USER_AGENT};
use reqwest::Url;
@@ -12,6 +10,10 @@ use std::path::Path;
use std::process;
use std::time::Duration;
+use monolith::html::{html_to_dom, stringify_document, walk_and_embed_assets};
+use monolith::url::{data_url_to_data, is_data_url, is_file_url, is_http_url};
+use monolith::utils::retrieve_asset;
+
mod args;
mod macros;
diff --git a/src/tests/utils/clean_url.rs b/src/tests/url/clean_url.rs
similarity index 81%
rename from src/tests/utils/clean_url.rs
rename to src/tests/url/clean_url.rs
index 9e3b9f7..4c1de79 100644
--- a/src/tests/utils/clean_url.rs
+++ b/src/tests/url/clean_url.rs
@@ -7,12 +7,12 @@
#[cfg(test)]
mod passing {
- use crate::utils;
+ use crate::url;
#[test]
fn removes_fragment() {
assert_eq!(
- utils::clean_url("https://somewhere.com/font.eot#iefix"),
+ url::clean_url("https://somewhere.com/font.eot#iefix"),
"https://somewhere.com/font.eot"
);
}
@@ -20,7 +20,7 @@ mod passing {
#[test]
fn removes_empty_fragment() {
assert_eq!(
- utils::clean_url("https://somewhere.com/font.eot#"),
+ url::clean_url("https://somewhere.com/font.eot#"),
"https://somewhere.com/font.eot"
);
}
@@ -28,7 +28,7 @@ mod passing {
#[test]
fn removes_empty_query_and_empty_fragment() {
assert_eq!(
- utils::clean_url("https://somewhere.com/font.eot?#"),
+ url::clean_url("https://somewhere.com/font.eot?#"),
"https://somewhere.com/font.eot"
);
}
@@ -36,7 +36,7 @@ mod passing {
#[test]
fn removes_empty_query_amp_and_empty_fragment() {
assert_eq!(
- utils::clean_url("https://somewhere.com/font.eot?a=b&#"),
+ url::clean_url("https://somewhere.com/font.eot?a=b&#"),
"https://somewhere.com/font.eot?a=b"
);
}
@@ -44,7 +44,7 @@ mod passing {
#[test]
fn keeps_credentials() {
assert_eq!(
- utils::clean_url("https://cookie:monster@gibson.internet/"),
+ url::clean_url("https://cookie:monster@gibson.internet/"),
"https://cookie:monster@gibson.internet/"
);
}
diff --git a/src/tests/utils/data_to_data_url.rs b/src/tests/url/data_to_data_url.rs
similarity index 83%
rename from src/tests/utils/data_to_data_url.rs
rename to src/tests/url/data_to_data_url.rs
index 9b4b4f6..f10e4a8 100644
--- a/src/tests/utils/data_to_data_url.rs
+++ b/src/tests/url/data_to_data_url.rs
@@ -7,13 +7,13 @@
#[cfg(test)]
mod passing {
- use crate::utils;
+ use crate::url;
#[test]
fn encode_string_with_specific_media_type() {
let mime = "application/javascript";
let data = "var word = 'hello';\nalert(word);\n";
- let data_url = utils::data_to_data_url(mime, data.as_bytes(), "", "");
+ let data_url = url::data_to_data_url(mime, data.as_bytes(), "");
assert_eq!(
&data_url,
@@ -24,8 +24,8 @@ mod passing {
#[test]
fn encode_append_fragment() {
let data = "\n";
- let data_url = utils::data_to_data_url("text/css", data.as_bytes(), "", "fragment");
+ let data_url = url::data_to_data_url("image/svg+xml", data.as_bytes(), "");
- assert_eq!(&data_url, "data:text/css;base64,PHN2Zz48L3N2Zz4K#fragment");
+ assert_eq!(&data_url, "data:image/svg+xml;base64,PHN2Zz48L3N2Zz4K");
}
}
diff --git a/src/tests/utils/data_url_to_data.rs b/src/tests/url/data_url_to_data.rs
similarity index 82%
rename from src/tests/utils/data_url_to_data.rs
rename to src/tests/url/data_url_to_data.rs
index 7d8b766..2ad5437 100644
--- a/src/tests/utils/data_url_to_data.rs
+++ b/src/tests/url/data_url_to_data.rs
@@ -7,11 +7,11 @@
#[cfg(test)]
mod passing {
- use crate::utils;
+ use crate::url;
#[test]
fn parse_text_html_base64() {
- let (media_type, data) = utils::data_url_to_data("data:text/html;base64,V29yayBleHBhbmRzIHNvIGFzIHRvIGZpbGwgdGhlIHRpbWUgYXZhaWxhYmxlIGZvciBpdHMgY29tcGxldGlvbg==");
+ let (media_type, data) = url::data_url_to_data("data:text/html;base64,V29yayBleHBhbmRzIHNvIGFzIHRvIGZpbGwgdGhlIHRpbWUgYXZhaWxhYmxlIGZvciBpdHMgY29tcGxldGlvbg==");
assert_eq!(media_type, "text/html");
assert_eq!(
@@ -22,7 +22,7 @@ mod passing {
#[test]
fn parse_text_html_utf8() {
- let (media_type, data) = utils::data_url_to_data(
+ let (media_type, data) = url::data_url_to_data(
"data:text/html;utf8,Work expands so as to fill the time available for its completion",
);
@@ -35,7 +35,7 @@ mod passing {
#[test]
fn parse_text_html_plaintext() {
- let (media_type, data) = utils::data_url_to_data(
+ let (media_type, data) = url::data_url_to_data(
"data:text/html,Work expands so as to fill the time available for its completion",
);
@@ -48,7 +48,7 @@ mod passing {
#[test]
fn parse_text_html_charset_utf_8_between_two_whitespaces() {
- let (media_type, data) = utils::data_url_to_data(" data:text/html;charset=utf-8,Work expands so as to fill the time available for its completion ");
+ let (media_type, data) = url::data_url_to_data(" data:text/html;charset=utf-8,Work expands so as to fill the time available for its completion ");
assert_eq!(media_type, "text/html");
assert_eq!(
@@ -60,7 +60,7 @@ mod passing {
#[test]
fn parse_text_css_url_encoded() {
let (media_type, data) =
- utils::data_url_to_data("data:text/css,div{background-color:%23000}");
+ url::data_url_to_data("data:text/css,div{background-color:%23000}");
assert_eq!(media_type, "text/css");
assert_eq!(String::from_utf8_lossy(&data), "div{background-color:#000}");
@@ -68,7 +68,7 @@ mod passing {
#[test]
fn parse_no_media_type_base64() {
- let (media_type, data) = utils::data_url_to_data("data:;base64,dGVzdA==");
+ let (media_type, data) = url::data_url_to_data("data:;base64,dGVzdA==");
assert_eq!(media_type, "");
assert_eq!(String::from_utf8_lossy(&data), "test");
@@ -76,7 +76,7 @@ mod passing {
#[test]
fn parse_no_media_type_no_encoding() {
- let (media_type, data) = utils::data_url_to_data("data:;,test%20test");
+ let (media_type, data) = url::data_url_to_data("data:;,test%20test");
assert_eq!(media_type, "");
assert_eq!(String::from_utf8_lossy(&data), "test test");
@@ -92,11 +92,11 @@ mod passing {
#[cfg(test)]
mod failing {
- use crate::utils;
+ use crate::url;
#[test]
fn just_word_data() {
- let (media_type, data) = utils::data_url_to_data("data");
+ let (media_type, data) = url::data_url_to_data("data");
assert_eq!(media_type, "");
assert_eq!(String::from_utf8_lossy(&data), "");
diff --git a/src/tests/utils/decode_url.rs b/src/tests/url/decode_url.rs
similarity index 90%
rename from src/tests/utils/decode_url.rs
rename to src/tests/url/decode_url.rs
index f436605..5cec664 100644
--- a/src/tests/utils/decode_url.rs
+++ b/src/tests/url/decode_url.rs
@@ -7,12 +7,12 @@
#[cfg(test)]
mod passing {
- use crate::utils;
+ use crate::url;
#[test]
fn decode_unicode_characters() {
assert_eq!(
- utils::decode_url(str!(
+ url::decode_url(str!(
"%E6%A4%9C%E3%83%92%E3%83%A0%E8%A7%A3%E5%A1%97%E3%82%83%E3%83%83%20%3D%20%E3%82%B5"
)),
"検ヒム解塗ゃッ = サ"
@@ -22,7 +22,7 @@ mod passing {
#[test]
fn decode_file_url() {
assert_eq!(
- utils::decode_url(str!("file:///tmp/space%20here/test%231.html")),
+ url::decode_url(str!("file:///tmp/space%20here/test%231.html")),
"file:///tmp/space here/test#1.html"
);
}
@@ -30,7 +30,7 @@ mod passing {
#[test]
fn plus_sign() {
assert_eq!(
- utils::decode_url(str!(
+ url::decode_url(str!(
"fonts.somewhere.com/css?family=Open+Sans:300,400,400italic,600,600italic"
)),
"fonts.somewhere.com/css?family=Open+Sans:300,400,400italic,600,600italic"
diff --git a/src/tests/utils/file_url_to_fs_path.rs b/src/tests/url/file_url_to_fs_path.rs
similarity index 79%
rename from src/tests/utils/file_url_to_fs_path.rs
rename to src/tests/url/file_url_to_fs_path.rs
index 437f6bd..6194e3f 100644
--- a/src/tests/utils/file_url_to_fs_path.rs
+++ b/src/tests/url/file_url_to_fs_path.rs
@@ -7,18 +7,18 @@
#[cfg(test)]
mod passing {
- use crate::utils;
+ use crate::url;
#[test]
fn remove_protocl_and_fragment() {
if cfg!(windows) {
assert_eq!(
- utils::file_url_to_fs_path("file:///C:/documents/some-path/some-file.svg#fragment"),
+ url::file_url_to_fs_path("file:///C:/documents/some-path/some-file.svg#fragment"),
"C:\\documents\\some-path\\some-file.svg"
);
} else {
assert_eq!(
- utils::file_url_to_fs_path("file:///tmp/some-path/some-file.svg#fragment"),
+ url::file_url_to_fs_path("file:///tmp/some-path/some-file.svg#fragment"),
"/tmp/some-path/some-file.svg"
);
}
@@ -28,12 +28,12 @@ mod passing {
fn decodes_urls() {
if cfg!(windows) {
assert_eq!(
- utils::file_url_to_fs_path("file:///C:/Documents%20and%20Settings/some-file.html"),
+ url::file_url_to_fs_path("file:///C:/Documents%20and%20Settings/some-file.html"),
"C:\\Documents and Settings\\some-file.html"
);
} else {
assert_eq!(
- utils::file_url_to_fs_path("file:///home/user/My%20Documents"),
+ url::file_url_to_fs_path("file:///home/user/My%20Documents"),
"/home/user/My Documents"
);
}
diff --git a/src/tests/utils/get_url_fragment.rs b/src/tests/url/get_url_fragment.rs
similarity index 90%
rename from src/tests/utils/get_url_fragment.rs
rename to src/tests/url/get_url_fragment.rs
index 94cb8a6..9d65a21 100644
--- a/src/tests/utils/get_url_fragment.rs
+++ b/src/tests/url/get_url_fragment.rs
@@ -7,12 +7,12 @@
#[cfg(test)]
mod passing {
- use crate::utils;
+ use crate::url;
#[test]
fn data_url() {
assert_eq!(
- utils::get_url_fragment(
+ url::get_url_fragment(
"data:image/svg+xml;base64,V2VsY29tZSBUbyBUaGUgUGFydHksIDxiPlBhbDwvYj4h#test"
),
"test"
@@ -21,6 +21,6 @@ mod passing {
#[test]
fn https_empty() {
- assert_eq!(utils::get_url_fragment("https://kernel.org#"), "");
+ assert_eq!(url::get_url_fragment("https://kernel.org#"), "");
}
}
diff --git a/src/tests/utils/is_data_url.rs b/src/tests/url/is_data_url.rs
similarity index 88%
rename from src/tests/utils/is_data_url.rs
rename to src/tests/url/is_data_url.rs
index 92c896d..efd059c 100644
--- a/src/tests/utils/is_data_url.rs
+++ b/src/tests/url/is_data_url.rs
@@ -7,18 +7,18 @@
#[cfg(test)]
mod passing {
- use crate::utils;
+ use crate::url;
#[test]
fn data_url_text_html() {
- assert!(utils::is_data_url(
+ assert!(url::is_data_url(
"data:text/html;base64,V2VsY29tZSBUbyBUaGUgUGFydHksIDxiPlBhbDwvYj4h"
));
}
#[test]
fn data_url_no_media_type() {
- assert!(utils::is_data_url(
+ assert!(url::is_data_url(
"data:;base64,V2VsY29tZSBUbyBUaGUgUGFydHksIDxiPlBhbDwvYj4h"
));
}
@@ -33,20 +33,20 @@ mod passing {
#[cfg(test)]
mod failing {
- use crate::utils;
+ use crate::url;
#[test]
fn https_url() {
- assert!(!utils::is_data_url("https://kernel.org"));
+ assert!(!url::is_data_url("https://kernel.org"));
}
#[test]
fn no_protocol_url() {
- assert!(!utils::is_data_url("//kernel.org"));
+ assert!(!url::is_data_url("//kernel.org"));
}
#[test]
fn empty_string() {
- assert!(!utils::is_data_url(""));
+ assert!(!url::is_data_url(""));
}
}
diff --git a/src/tests/utils/is_file_url.rs b/src/tests/url/is_file_url.rs
similarity index 84%
rename from src/tests/utils/is_file_url.rs
rename to src/tests/url/is_file_url.rs
index 5e6e360..927b793 100644
--- a/src/tests/utils/is_file_url.rs
+++ b/src/tests/url/is_file_url.rs
@@ -7,32 +7,32 @@
#[cfg(test)]
mod passing {
- use crate::utils;
+ use crate::url;
#[test]
fn unix_file_url() {
- assert!(utils::is_file_url(
+ assert!(url::is_file_url(
"file:///home/user/Websites/my-website/index.html"
));
}
#[test]
fn windows_file_url() {
- assert!(utils::is_file_url(
+ assert!(url::is_file_url(
"file:///C:/Documents%20and%20Settings/user/Websites/my-website/assets/images/logo.png"
));
}
#[test]
fn unix_url_with_backslashes() {
- assert!(utils::is_file_url(
+ assert!(url::is_file_url(
"file:\\\\\\home\\user\\Websites\\my-website\\index.html"
));
}
#[test]
fn windows_file_url_with_backslashes() {
- assert!(utils::is_file_url(
+ assert!(url::is_file_url(
"file:\\\\\\C:\\Documents%20and%20Settings\\user\\Websites\\my-website\\assets\\images\\logo.png"
));
}
@@ -47,37 +47,37 @@ mod passing {
#[cfg(test)]
mod failing {
- use crate::utils;
+ use crate::url;
#[test]
fn url_with_no_protocl() {
- assert!(!utils::is_file_url("//kernel.org"));
+ assert!(!url::is_file_url("//kernel.org"));
}
#[test]
fn dot_slash_filename() {
- assert!(!utils::is_file_url("./index.html"));
+ assert!(!url::is_file_url("./index.html"));
}
#[test]
fn just_filename() {
- assert!(!utils::is_file_url("some-local-page.htm"));
+ assert!(!url::is_file_url("some-local-page.htm"));
}
#[test]
fn https_ip_port_url() {
- assert!(!utils::is_file_url("https://1.2.3.4:80/www/index.html"));
+ assert!(!url::is_file_url("https://1.2.3.4:80/www/index.html"));
}
#[test]
fn data_url() {
- assert!(!utils::is_file_url(
+ assert!(!url::is_file_url(
"data:text/html;base64,V2VsY29tZSBUbyBUaGUgUGFydHksIDxiPlBhbDwvYj4h"
));
}
#[test]
fn just_word_file() {
- assert!(!utils::is_file_url("file"));
+ assert!(!url::is_file_url("file"));
}
}
diff --git a/src/tests/utils/is_http_url.rs b/src/tests/url/is_http_url.rs
similarity index 81%
rename from src/tests/utils/is_http_url.rs
rename to src/tests/url/is_http_url.rs
index 981accc..622d340 100644
--- a/src/tests/utils/is_http_url.rs
+++ b/src/tests/url/is_http_url.rs
@@ -7,21 +7,21 @@
#[cfg(test)]
mod passing {
- use crate::utils;
+ use crate::url;
#[test]
fn http_url() {
- assert!(utils::is_http_url("http://kernel.org"));
+ assert!(url::is_http_url("http://kernel.org"));
}
#[test]
fn https_url() {
- assert!(utils::is_http_url("https://www.rust-lang.org/"));
+ assert!(url::is_http_url("https://www.rust-lang.org/"));
}
#[test]
fn http_url_with_backslashes() {
- assert!(utils::is_http_url("http:\\\\freebsd.org\\"));
+ assert!(url::is_http_url("http:\\\\freebsd.org\\"));
}
}
@@ -34,31 +34,31 @@ mod passing {
#[cfg(test)]
mod failing {
- use crate::utils;
+ use crate::url;
#[test]
fn url_with_no_protocol() {
- assert!(!utils::is_http_url("//kernel.org"));
+ assert!(!url::is_http_url("//kernel.org"));
}
#[test]
fn dot_slash_filename() {
- assert!(!utils::is_http_url("./index.html"));
+ assert!(!url::is_http_url("./index.html"));
}
#[test]
fn just_filename() {
- assert!(!utils::is_http_url("some-local-page.htm"));
+ assert!(!url::is_http_url("some-local-page.htm"));
}
#[test]
fn https_ip_port_url() {
- assert!(!utils::is_http_url("ftp://1.2.3.4/www/index.html"));
+ assert!(!url::is_http_url("ftp://1.2.3.4/www/index.html"));
}
#[test]
fn data_url() {
- assert!(!utils::is_http_url(
+ assert!(!url::is_http_url(
"data:text/html;base64,V2VsY29tZSBUbyBUaGUgUGFydHksIDxiPlBhbDwvYj4h"
));
}
diff --git a/src/tests/url/mod.rs b/src/tests/url/mod.rs
new file mode 100644
index 0000000..226c388
--- /dev/null
+++ b/src/tests/url/mod.rs
@@ -0,0 +1,12 @@
+mod clean_url;
+mod data_to_data_url;
+mod data_url_to_data;
+mod decode_url;
+mod file_url_to_fs_path;
+mod get_url_fragment;
+mod is_data_url;
+mod is_file_url;
+mod is_http_url;
+mod resolve_url;
+mod url_has_protocol;
+mod url_with_fragment;
diff --git a/src/tests/utils/resolve_url.rs b/src/tests/url/resolve_url.rs
similarity index 88%
rename from src/tests/utils/resolve_url.rs
rename to src/tests/url/resolve_url.rs
index c3b1797..d584a32 100644
--- a/src/tests/utils/resolve_url.rs
+++ b/src/tests/url/resolve_url.rs
@@ -7,13 +7,13 @@
#[cfg(test)]
mod passing {
- use crate::utils;
+ use crate::url;
use url::ParseError;
#[test]
fn from_https_to_level_up_relative() -> Result<(), ParseError> {
let resolved_url =
- utils::resolve_url("https://www.kernel.org", "../category/signatures.html")?;
+ url::resolve_url("https://www.kernel.org", "../category/signatures.html")?;
assert_eq!(
resolved_url.as_str(),
@@ -25,7 +25,7 @@ mod passing {
#[test]
fn from_just_filename_to_full_https_url() -> Result<(), ParseError> {
- let resolved_url = utils::resolve_url(
+ let resolved_url = url::resolve_url(
"saved_page.htm",
"https://www.kernel.org/category/signatures.html",
)?;
@@ -40,7 +40,7 @@ mod passing {
#[test]
fn from_https_url_to_url_with_no_protocol() -> Result<(), ParseError> {
- let resolved_url = utils::resolve_url(
+ let resolved_url = url::resolve_url(
"https://www.kernel.org",
"//www.kernel.org/theme/images/logos/tux.png",
)?;
@@ -56,7 +56,7 @@ mod passing {
#[test]
fn from_https_url_to_url_with_no_protocol_and_on_different_hostname() -> Result<(), ParseError>
{
- let resolved_url = utils::resolve_url(
+ let resolved_url = url::resolve_url(
"https://www.kernel.org",
"//another-host.org/theme/images/logos/tux.png",
)?;
@@ -71,7 +71,7 @@ mod passing {
#[test]
fn from_https_url_to_relative_root_path() -> Result<(), ParseError> {
- let resolved_url = utils::resolve_url(
+ let resolved_url = url::resolve_url(
"https://www.kernel.org/category/signatures.html",
"/theme/images/logos/tux.png",
)?;
@@ -86,7 +86,7 @@ mod passing {
#[test]
fn from_https_to_just_filename() -> Result<(), ParseError> {
- let resolved_url = utils::resolve_url(
+ let resolved_url = url::resolve_url(
"https://www.w3schools.com/html/html_iframe.asp",
"default.asp",
)?;
@@ -101,7 +101,7 @@ mod passing {
#[test]
fn from_data_url_to_https() -> Result<(), ParseError> {
- let resolved_url = utils::resolve_url(
+ let resolved_url = url::resolve_url(
"data:text/html;base64,V2VsY29tZSBUbyBUaGUgUGFydHksIDxiPlBhbDwvYj4h",
"https://www.kernel.org/category/signatures.html",
)?;
@@ -116,7 +116,7 @@ mod passing {
#[test]
fn from_data_url_to_data_url() -> Result<(), ParseError> {
- let resolved_url = utils::resolve_url(
+ let resolved_url = url::resolve_url(
"data:text/html;base64,V2VsY29tZSBUbyBUaGUgUGFydHksIDxiPlBhbDwvYj4h",
"data:text/html;base64,PGEgaHJlZj0iaW5kZXguaHRtbCI+SG9tZTwvYT4K",
)?;
@@ -131,7 +131,7 @@ mod passing {
#[test]
fn from_file_url_to_relative_path() -> Result<(), ParseError> {
- let resolved_url = utils::resolve_url(
+ let resolved_url = url::resolve_url(
"file:///home/user/Websites/my-website/index.html",
"assets/images/logo.png",
)
@@ -147,7 +147,7 @@ mod passing {
#[test]
fn from_file_url_to_relative_path_with_backslashes() -> Result<(), ParseError> {
- let resolved_url = utils::resolve_url(
+ let resolved_url = url::resolve_url(
"file:\\\\\\home\\user\\Websites\\my-website\\index.html",
"assets\\images\\logo.png",
)
@@ -163,7 +163,7 @@ mod passing {
#[test]
fn from_data_url_to_file_url() -> Result<(), ParseError> {
- let resolved_url = utils::resolve_url(
+ let resolved_url = url::resolve_url(
"data:text/html;base64,V2VsY29tZSBUbyBUaGUgUGFydHksIDxiPlBhbDwvYj4h",
"file:///etc/passwd",
)
@@ -176,7 +176,7 @@ mod passing {
#[test]
fn preserve_fragment() -> Result<(), ParseError> {
- let resolved_url = utils::resolve_url(
+ let resolved_url = url::resolve_url(
"http://doesnt-matter.local/",
"css/fonts/fontmarvelous.svg#fontmarvelous",
)
@@ -193,9 +193,9 @@ mod passing {
#[test]
fn resolve_from_file_url_to_file_url() -> Result<(), ParseError> {
let resolved_url = if cfg!(windows) {
- utils::resolve_url("file:///c:/index.html", "file:///c:/image.png").unwrap_or(str!())
+ url::resolve_url("file:///c:/index.html", "file:///c:/image.png").unwrap_or(str!())
} else {
- utils::resolve_url("file:///tmp/index.html", "file:///tmp/image.png").unwrap_or(str!())
+ url::resolve_url("file:///tmp/index.html", "file:///tmp/image.png").unwrap_or(str!())
};
assert_eq!(
@@ -220,12 +220,12 @@ mod passing {
#[cfg(test)]
mod failing {
- use crate::utils;
+ use crate::url;
use url::ParseError;
#[test]
fn from_data_url_to_url_with_no_protocol() -> Result<(), ParseError> {
- let resolved_url = utils::resolve_url(
+ let resolved_url = url::resolve_url(
"data:text/html;base64,V2VsY29tZSBUbyBUaGUgUGFydHksIDxiPlBhbDwvYj4h",
"//www.w3schools.com/html/html_iframe.asp",
)
diff --git a/src/tests/utils/url_has_protocol.rs b/src/tests/url/url_has_protocol.rs
similarity index 78%
rename from src/tests/utils/url_has_protocol.rs
rename to src/tests/url/url_has_protocol.rs
index 3c03619..1111b4a 100644
--- a/src/tests/utils/url_has_protocol.rs
+++ b/src/tests/url/url_has_protocol.rs
@@ -7,50 +7,50 @@
#[cfg(test)]
mod passing {
- use crate::utils;
+ use crate::url;
#[test]
fn mailto() {
- assert!(utils::url_has_protocol(
+ assert!(url::url_has_protocol(
"mailto:somebody@somewhere.com?subject=hello"
));
}
#[test]
fn tel() {
- assert!(utils::url_has_protocol("tel:5551234567"));
+ assert!(url::url_has_protocol("tel:5551234567"));
}
#[test]
fn ftp_no_slashes() {
- assert!(utils::url_has_protocol("ftp:some-ftp-server.com"));
+ assert!(url::url_has_protocol("ftp:some-ftp-server.com"));
}
#[test]
fn ftp_with_credentials() {
- assert!(utils::url_has_protocol(
+ assert!(url::url_has_protocol(
"ftp://user:password@some-ftp-server.com"
));
}
#[test]
fn javascript() {
- assert!(utils::url_has_protocol("javascript:void(0)"));
+ assert!(url::url_has_protocol("javascript:void(0)"));
}
#[test]
fn http() {
- assert!(utils::url_has_protocol("http://news.ycombinator.com"));
+ assert!(url::url_has_protocol("http://news.ycombinator.com"));
}
#[test]
fn https() {
- assert!(utils::url_has_protocol("https://github.com"));
+ assert!(url::url_has_protocol("https://github.com"));
}
#[test]
fn mailto_uppercase() {
- assert!(utils::url_has_protocol(
+ assert!(url::url_has_protocol(
"MAILTO:somebody@somewhere.com?subject=hello"
));
}
@@ -69,23 +69,23 @@ mod failing {
#[test]
fn url_with_no_protocol() {
- assert!(!utils::url_has_protocol(
+ assert!(!url::url_has_protocol(
"//some-hostname.com/some-file.html"
));
}
#[test]
fn relative_path() {
- assert!(!utils::url_has_protocol("some-hostname.com/some-file.html"));
+ assert!(!url::url_has_protocol("some-hostname.com/some-file.html"));
}
#[test]
fn relative_to_root_path() {
- assert!(!utils::url_has_protocol("/some-file.html"));
+ assert!(!url::url_has_protocol("/some-file.html"));
}
#[test]
fn empty_string() {
- assert!(!utils::url_has_protocol(""));
+ assert!(!url::url_has_protocol(""));
}
}
diff --git a/src/tests/url/url_with_fragment.rs b/src/tests/url/url_with_fragment.rs
new file mode 100644
index 0000000..955acf3
--- /dev/null
+++ b/src/tests/url/url_with_fragment.rs
@@ -0,0 +1,40 @@
+// ██████╗ █████╗ ███████╗███████╗██╗███╗ ██╗ ██████╗
+// ██╔══██╗██╔══██╗██╔════╝██╔════╝██║████╗ ██║██╔════╝
+// ██████╔╝███████║███████╗███████╗██║██╔██╗ ██║██║ ███╗
+// ██╔═══╝ ██╔══██║╚════██║╚════██║██║██║╚██╗██║██║ ██║
+// ██║ ██║ ██║███████║███████║██║██║ ╚████║╚██████╔╝
+// ╚═╝ ╚═╝ ╚═╝╚══════╝╚══════╝╚═╝╚═╝ ╚═══╝ ╚═════╝
+
+#[cfg(test)]
+mod passing {
+ use crate::url;
+
+ #[test]
+ fn url_with_fragment_url() {
+ let url = "https://localhost.localdomain/path/";
+ let fragment = "test";
+ let assembled_url = url::url_with_fragment(url, fragment);
+
+ assert_eq!(&assembled_url, "https://localhost.localdomain/path/#test");
+ }
+ #[test]
+ fn url_with_fragment_empty_url() {
+ let url = "https://localhost.localdomain/path/";
+ let fragment = "";
+ let assembled_url = url::url_with_fragment(url, fragment);
+
+ assert_eq!(&assembled_url, "https://localhost.localdomain/path/");
+ }
+
+ #[test]
+ fn url_with_fragment_data_url() {
+ let url = "data:image/svg+xml;base64,PHN2Zz48L3N2Zz4K";
+ let fragment = "fragment";
+ let assembled_url = url::url_with_fragment(url, fragment);
+
+ assert_eq!(
+ &assembled_url,
+ "data:image/svg+xml;base64,PHN2Zz48L3N2Zz4K#fragment"
+ );
+ }
+}
diff --git a/src/tests/utils/mod.rs b/src/tests/utils/mod.rs
index 8fc7e47..8d13447 100644
--- a/src/tests/utils/mod.rs
+++ b/src/tests/utils/mod.rs
@@ -1,13 +1,2 @@
-mod clean_url;
-mod data_to_data_url;
-mod data_url_to_data;
-mod decode_url;
mod detect_media_type;
-mod file_url_to_fs_path;
-mod get_url_fragment;
-mod is_data_url;
-mod is_file_url;
-mod is_http_url;
-mod resolve_url;
mod retrieve_asset;
-mod url_has_protocol;
diff --git a/src/tests/utils/retrieve_asset.rs b/src/tests/utils/retrieve_asset.rs
index 4aeeb5b..3c3d1e0 100644
--- a/src/tests/utils/retrieve_asset.rs
+++ b/src/tests/utils/retrieve_asset.rs
@@ -7,11 +7,13 @@
#[cfg(test)]
mod passing {
- use crate::utils;
use reqwest::blocking::Client;
use std::collections::HashMap;
use std::env;
+ use crate::url;
+ use crate::utils;
+
#[test]
fn read_data_url() {
let cache = &mut HashMap::new();
@@ -28,12 +30,12 @@ mod passing {
)
.unwrap();
assert_eq!(
- utils::data_to_data_url(&media_type, &data, &final_url, ""),
- utils::data_to_data_url("text/html", "target".as_bytes(), "", "")
+ url::data_to_data_url(&media_type, &data, &final_url),
+ url::data_to_data_url("text/html", "target".as_bytes(), "")
);
assert_eq!(
final_url,
- utils::data_to_data_url("text/html", "target".as_bytes(), "", "")
+ url::data_to_data_url("text/html", "target".as_bytes(), "")
);
assert_eq!(&media_type, "text/html");
}
@@ -63,7 +65,7 @@ mod passing {
false,
)
.unwrap();
- assert_eq!(utils::data_to_data_url("application/javascript", &data, &final_url, ""), "data:application/javascript;base64,ZG9jdW1lbnQuYm9keS5zdHlsZS5iYWNrZ3JvdW5kQ29sb3IgPSAiZ3JlZW4iOwpkb2N1bWVudC5ib2R5LnN0eWxlLmNvbG9yID0gInJlZCI7Cg==");
+ assert_eq!(url::data_to_data_url("application/javascript", &data, &final_url), "data:application/javascript;base64,ZG9jdW1lbnQuYm9keS5zdHlsZS5iYWNrZ3JvdW5kQ29sb3IgPSAiZ3JlZW4iOwpkb2N1bWVudC5ib2R5LnN0eWxlLmNvbG9yID0gInJlZCI7Cg==");
assert_eq!(
&final_url,
&format!(
diff --git a/src/url.rs b/src/url.rs
new file mode 100644
index 0000000..e493ce1
--- /dev/null
+++ b/src/url.rs
@@ -0,0 +1,168 @@
+use base64;
+use url::{form_urlencoded, ParseError, Url};
+
+use crate::utils::detect_media_type;
+
+pub fn clean_url>(input: T) -> String {
+ let mut url = Url::parse(input.as_ref()).unwrap();
+
+ // Clear fragment
+ url.set_fragment(None);
+
+ // Get rid of stray question mark
+ if url.query() == Some("") {
+ url.set_query(None);
+ }
+
+ // Remove empty trailing ampersand(s)
+ let mut result: String = url.to_string();
+ while result.ends_with("&") {
+ result.pop();
+ }
+
+ result
+}
+
+pub fn data_to_data_url(media_type: &str, data: &[u8], url: &str) -> String {
+ let media_type: String = if media_type.is_empty() {
+ detect_media_type(data, &url)
+ } else {
+ media_type.to_string()
+ };
+
+ format!("data:{};base64,{}", media_type, base64::encode(data))
+}
+
+pub fn data_url_to_data>(url: T) -> (String, Vec) {
+ let parsed_url: Url = Url::parse(url.as_ref()).unwrap_or(Url::parse("data:,").unwrap());
+ let path: String = parsed_url.path().to_string();
+ let comma_loc: usize = path.find(',').unwrap_or(path.len());
+
+ let meta_data: String = path.chars().take(comma_loc).collect();
+ let raw_data: String = path.chars().skip(comma_loc + 1).collect();
+
+ let text: String = decode_url(raw_data);
+
+ let meta_data_items: Vec<&str> = meta_data.split(';').collect();
+ let mut media_type: String = str!();
+ let mut encoding: &str = "";
+
+ let mut i: i8 = 0;
+ for item in &meta_data_items {
+ if i == 0 {
+ media_type = str!(item);
+ } else {
+ if item.eq_ignore_ascii_case("base64")
+ || item.eq_ignore_ascii_case("utf8")
+ || item.eq_ignore_ascii_case("charset=UTF-8")
+ {
+ encoding = item;
+ }
+ }
+
+ i = i + 1;
+ }
+
+ let data: Vec = if encoding.eq_ignore_ascii_case("base64") {
+ base64::decode(&text).unwrap_or(vec![])
+ } else {
+ text.as_bytes().to_vec()
+ };
+
+ (media_type, data)
+}
+
+pub fn decode_url(input: String) -> String {
+ let input: String = input.replace("+", "%2B");
+
+ form_urlencoded::parse(input.as_bytes())
+ .map(|(key, val)| {
+ [
+ key.to_string(),
+ if val.to_string().len() == 0 {
+ str!()
+ } else {
+ str!('=')
+ },
+ val.to_string(),
+ ]
+ .concat()
+ })
+ .collect()
+}
+
+pub fn file_url_to_fs_path(url: &str) -> String {
+ if !is_file_url(url) {
+ return str!();
+ }
+
+ let cutoff_l = if cfg!(windows) { 8 } else { 7 };
+ let mut fs_file_path: String = decode_url(url.to_string()[cutoff_l..].to_string());
+ let url_fragment = get_url_fragment(url);
+ if url_fragment != "" {
+ let max_len = fs_file_path.len() - 1 - url_fragment.len();
+ fs_file_path = fs_file_path[0..max_len].to_string();
+ }
+
+ if cfg!(windows) {
+ fs_file_path = fs_file_path.replace("/", "\\");
+ }
+
+ // File paths should not be %-encoded
+ decode_url(fs_file_path)
+}
+
+pub fn get_url_fragment>(url: T) -> String {
+ if Url::parse(url.as_ref()).unwrap().fragment() == None {
+ str!()
+ } else {
+ str!(Url::parse(url.as_ref()).unwrap().fragment().unwrap())
+ }
+}
+
+pub fn is_data_url>(url: T) -> bool {
+ Url::parse(url.as_ref())
+ .and_then(|u| Ok(u.scheme() == "data"))
+ .unwrap_or(false)
+}
+
+pub fn is_file_url>(url: T) -> bool {
+ Url::parse(url.as_ref())
+ .and_then(|u| Ok(u.scheme() == "file"))
+ .unwrap_or(false)
+}
+
+pub fn is_http_url>(url: T) -> bool {
+ Url::parse(url.as_ref())
+ .and_then(|u| Ok(u.scheme() == "http" || u.scheme() == "https"))
+ .unwrap_or(false)
+}
+
+pub fn resolve_url, U: AsRef>(from: T, to: U) -> Result {
+ let result = if is_http_url(to.as_ref()) {
+ to.as_ref().to_string()
+ } else {
+ Url::parse(from.as_ref())?
+ .join(to.as_ref())?
+ .as_ref()
+ .to_string()
+ };
+ Ok(result)
+}
+
+pub fn url_has_protocol>(url: T) -> bool {
+ Url::parse(url.as_ref())
+ .and_then(|u| Ok(u.scheme().len() > 0))
+ .unwrap_or(false)
+}
+
+pub fn url_with_fragment(url: &str, fragment: &str) -> String {
+ let mut result = str!(&url);
+
+ if !fragment.is_empty() {
+ result += "#";
+ result += fragment;
+ }
+
+ result
+}
diff --git a/src/utils.rs b/src/utils.rs
index 11aecb2..de0ca45 100644
--- a/src/utils.rs
+++ b/src/utils.rs
@@ -1,10 +1,10 @@
-use base64;
use reqwest::blocking::Client;
use reqwest::header::CONTENT_TYPE;
use std::collections::HashMap;
use std::fs;
use std::path::Path;
-use url::{form_urlencoded, ParseError, Url};
+
+use crate::url::{clean_url, data_url_to_data, file_url_to_fs_path, is_data_url, is_file_url};
const MAGIC: [[&[u8]; 2]; 18] = [
// Image
@@ -38,26 +38,6 @@ const PLAINTEXT_MEDIA_TYPES: &[&str] = &[
"text/plain",
];
-pub fn data_to_data_url(media_type: &str, data: &[u8], url: &str, fragment: &str) -> String {
- let media_type: String = if media_type.is_empty() {
- detect_media_type(data, &url)
- } else {
- media_type.to_string()
- };
- let hash: String = if fragment != "" {
- format!("#{}", fragment)
- } else {
- str!()
- };
-
- format!(
- "data:{};base64,{}{}",
- media_type,
- base64::encode(data),
- hash
- )
-}
-
pub fn detect_media_type(data: &[u8], url: &str) -> String {
for item in MAGIC.iter() {
if data.starts_with(item[0]) {
@@ -72,153 +52,10 @@ pub fn detect_media_type(data: &[u8], url: &str) -> String {
str!()
}
-pub fn url_has_protocol>(url: T) -> bool {
- Url::parse(url.as_ref())
- .and_then(|u| Ok(u.scheme().len() > 0))
- .unwrap_or(false)
-}
-
-pub fn is_data_url>(url: T) -> bool {
- Url::parse(url.as_ref())
- .and_then(|u| Ok(u.scheme() == "data"))
- .unwrap_or(false)
-}
-
-pub fn is_file_url>(url: T) -> bool {
- Url::parse(url.as_ref())
- .and_then(|u| Ok(u.scheme() == "file"))
- .unwrap_or(false)
-}
-
-pub fn is_http_url>(url: T) -> bool {
- Url::parse(url.as_ref())
- .and_then(|u| Ok(u.scheme() == "http" || u.scheme() == "https"))
- .unwrap_or(false)
-}
-
pub fn is_plaintext_media_type(media_type: &str) -> bool {
PLAINTEXT_MEDIA_TYPES.contains(&media_type.to_lowercase().as_str())
}
-pub fn resolve_url, U: AsRef>(from: T, to: U) -> Result {
- let result = if is_http_url(to.as_ref()) {
- to.as_ref().to_string()
- } else {
- Url::parse(from.as_ref())?
- .join(to.as_ref())?
- .as_ref()
- .to_string()
- };
- Ok(result)
-}
-
-pub fn get_url_fragment>(url: T) -> String {
- if Url::parse(url.as_ref()).unwrap().fragment() == None {
- str!()
- } else {
- str!(Url::parse(url.as_ref()).unwrap().fragment().unwrap())
- }
-}
-
-pub fn clean_url>(input: T) -> String {
- let mut url = Url::parse(input.as_ref()).unwrap();
-
- // Clear fragment
- url.set_fragment(None);
-
- // Get rid of stray question mark
- if url.query() == Some("") {
- url.set_query(None);
- }
-
- // Remove empty trailing ampersand(s)
- let mut result: String = url.to_string();
- while result.ends_with("&") {
- result.pop();
- }
-
- result
-}
-
-pub fn data_url_to_data>(url: T) -> (String, Vec) {
- let parsed_url: Url = Url::parse(url.as_ref()).unwrap_or(Url::parse("data:,").unwrap());
- let path: String = parsed_url.path().to_string();
- let comma_loc: usize = path.find(',').unwrap_or(path.len());
-
- let meta_data: String = path.chars().take(comma_loc).collect();
- let raw_data: String = path.chars().skip(comma_loc + 1).collect();
-
- let text: String = decode_url(raw_data);
-
- let meta_data_items: Vec<&str> = meta_data.split(';').collect();
- let mut media_type: String = str!();
- let mut encoding: &str = "";
-
- let mut i: i8 = 0;
- for item in &meta_data_items {
- if i == 0 {
- media_type = str!(item);
- } else {
- if item.eq_ignore_ascii_case("base64")
- || item.eq_ignore_ascii_case("utf8")
- || item.eq_ignore_ascii_case("charset=UTF-8")
- {
- encoding = item;
- }
- }
-
- i = i + 1;
- }
-
- let data: Vec = if encoding.eq_ignore_ascii_case("base64") {
- base64::decode(&text).unwrap_or(vec![])
- } else {
- text.as_bytes().to_vec()
- };
-
- (media_type, data)
-}
-
-pub fn decode_url(input: String) -> String {
- let input: String = input.replace("+", "%2B");
-
- form_urlencoded::parse(input.as_bytes())
- .map(|(key, val)| {
- [
- key.to_string(),
- if val.to_string().len() == 0 {
- str!()
- } else {
- str!('=')
- },
- val.to_string(),
- ]
- .concat()
- })
- .collect()
-}
-
-pub fn file_url_to_fs_path(url: &str) -> String {
- if !is_file_url(url) {
- return str!();
- }
-
- let cutoff_l = if cfg!(windows) { 8 } else { 7 };
- let mut fs_file_path: String = decode_url(url.to_string()[cutoff_l..].to_string());
- let url_fragment = get_url_fragment(url);
- if url_fragment != "" {
- let max_len = fs_file_path.len() - 1 - url_fragment.len();
- fs_file_path = fs_file_path[0..max_len].to_string();
- }
-
- if cfg!(windows) {
- fs_file_path = fs_file_path.replace("/", "\\");
- }
-
- // File paths should not be %-encoded
- decode_url(fs_file_path)
-}
-
pub fn retrieve_asset(
cache: &mut HashMap>,
client: &Client,