From 13429e32d3e011ea1b7220c7e52c9a6ace5e3a4a Mon Sep 17 00:00:00 2001
From: Vincent Flyson <vflyson@uberspace.net>
Date: Fri, 23 Aug 2019 16:00:05 -0400
Subject: [PATCH 1/6] Allow HTTP redirects and preserve email links

---
 Cargo.toml  | 2 +-
 src/html.rs | 4 ++--
 src/http.rs | 3 ++-
 src/main.rs | 2 +-
 4 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/Cargo.toml b/Cargo.toml
index ca1b409..c0ae12f 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "monolith"
-version = "2.0.5"
+version = "2.0.6"
 authors = ["Sunshine <sunshine@uberspace.net>"]
 description = "CLI tool to save webpages as a single HTML file"
 
diff --git a/src/html.rs b/src/html.rs
index 63c1d7d..0da1aaf 100644
--- a/src/html.rs
+++ b/src/html.rs
@@ -146,8 +146,8 @@ pub fn walk_and_embed_assets(
                 NodeMatch::Anchor => {
                     for attr in attrs_mut.iter_mut() {
                         if &attr.name.local == "href" {
-                            // Do not touch hrefs which begin with a hash sign
-                            if attr.value.to_string().chars().nth(0) == Some('#') {
+                            // Don't touch email links or hrefs which begin with a hash sign
+                            if attr.value.starts_with('#') || attr.value.starts_with("mailto:") {
                                 continue;
                             }
 
diff --git a/src/http.rs b/src/http.rs
index 19e064d..b18da0c 100644
--- a/src/http.rs
+++ b/src/http.rs
@@ -1,6 +1,6 @@
 use regex::Regex;
 use reqwest::header::{CONTENT_TYPE, USER_AGENT};
-use reqwest::Client;
+use reqwest::{Client, RedirectPolicy};
 use std::time::Duration;
 use url::{ParseError, Url};
 use utils::data_to_dataurl;
@@ -75,6 +75,7 @@ pub fn retrieve_asset(
         Ok(url.to_string())
     } else {
         let client = Client::builder()
+            .redirect(RedirectPolicy::limited(3))
             .timeout(Duration::from_secs(10))
             .build()
             .unwrap();
diff --git a/src/main.rs b/src/main.rs
index cfb4872..7988f2f 100644
--- a/src/main.rs
+++ b/src/main.rs
@@ -22,7 +22,7 @@ fn main() {
         )
         .args_from_usage("-j, --no-js 'Excludes JavaScript'")
         .args_from_usage("-i, --no-images 'Removes images'")
-        .args_from_usage("-u, --user-agent=<Iceweasel> 'Custom User-Agent string'")
+        .args_from_usage("-u, --user-agent=[Iceweasel] 'Custom User-Agent string'")
         .get_matches();
 
     // Process the command

From c0fffbb21235f11b1947e11e66cb69ca6c3c5421 Mon Sep 17 00:00:00 2001
From: Vincent Flyson <vflyson@uberspace.net>
Date: Fri, 23 Aug 2019 18:48:08 -0400
Subject: [PATCH 2/6] Get rid of mime-sniffer dependency

---
 Cargo.toml   |  5 ++--
 src/utils.rs | 64 +++++++++++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 63 insertions(+), 6 deletions(-)

diff --git a/Cargo.toml b/Cargo.toml
index c0ae12f..11b9328 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "monolith"
-version = "2.0.6"
+version = "2.0.7"
 authors = ["Sunshine <sunshine@uberspace.net>"]
 description = "CLI tool to save webpages as a single HTML file"
 
@@ -9,8 +9,7 @@ base64 = "0.10.1"
 clap = "2.33.0"
 html5ever = "0.24.0"
 indicatif = "0.11.0"
-mime-sniffer = "0.1.2"
+lazy_static = "1.3.0"
 regex = "1.2.1"
 reqwest = "0.9.20"
 url = "2.1.0"
-lazy_static = "1.3.0"
diff --git a/src/utils.rs b/src/utils.rs
index f459a02..2f91337 100644
--- a/src/utils.rs
+++ b/src/utils.rs
@@ -1,8 +1,31 @@
 extern crate base64;
-extern crate mime_sniffer;
 
 use self::base64::encode;
-use self::mime_sniffer::MimeTypeSniffer;
+
+static MAGIC: [[&[u8]; 2]; 19]  = [
+    // Image
+    [b"GIF87a", b"image/gif"],
+    [b"GIF89a", b"image/gif"],
+    [b"\xFF\xD8\xFF", b"image/jpeg"],
+    [b"\x89PNG\x0D\x0A\x1A\x0A", b"image/png"],
+    [b"<?xml ", b"image/svg+xml"],
+    [b"<svg ", b"image/svg+xml"],
+    [b"RIFF....WEBPVP8 ", b"image/webp"],
+    [b"\x00\x00\x01\x00", b"image/x-icon"],
+    // Audio
+    [b"ID3", b"audio/mpeg"],
+    [b"\xFF\x0E", b"audio/mpeg"],
+    [b"\xFF\x0F", b"audio/mpeg"],
+    [b"OggS", b"audio/ogg"],
+    [b"RIFF....WAVEfmt ", b"audio/wav"],
+    [b"fLaC", b"audio/x-flac"],
+    // Video
+    [b"RIFF....AVI LIST", b"video/avi"],
+    [b"....ftyp", b"video/mp4"],
+    [b"\x00\x00\x01\x0B", b"video/mpeg"],
+    [b"....moov", b"video/quicktime"],
+    [b"\x1A\x45\xDF\xA3", b"video/webm"],
+];
 
 pub fn data_to_dataurl(mime: &str, data: &[u8]) -> String {
     let mimetype = if mime == "" {
@@ -14,7 +37,16 @@ pub fn data_to_dataurl(mime: &str, data: &[u8]) -> String {
 }
 
 fn detect_mimetype(data: &[u8]) -> String {
-    data.sniff_mime_type().unwrap_or("").to_string()
+    let mut re = String::new();
+
+    for item in MAGIC.iter()  {
+        if data.starts_with(item[0]) {
+            re = String::from_utf8(item[1].to_vec()).unwrap();
+            break;
+        }
+    }
+
+    re
 }
 
 #[cfg(test)]
@@ -31,4 +63,30 @@ mod tests {
             "data:application/javascript;base64,dmFyIHdvcmQgPSAnaGVsbG8nOwphbGVydCh3b3JkKTsK"
         );
     }
+
+    #[test]
+    fn test_detect_mimetype() {
+        // Image
+        assert_eq!(detect_mimetype(b"GIF87a"), "image/gif");
+        assert_eq!(detect_mimetype(b"GIF89a"), "image/gif");
+        assert_eq!(detect_mimetype(b"\xFF\xD8\xFF"), "image/jpeg");
+        assert_eq!(detect_mimetype(b"\x89PNG\x0D\x0A\x1A\x0A"), "image/png");
+        assert_eq!(detect_mimetype(b"<?xml "), "image/svg+xml");
+        assert_eq!(detect_mimetype(b"<svg "), "image/svg+xml");
+        assert_eq!(detect_mimetype(b"RIFF....WEBPVP8 "), "image/webp");
+        assert_eq!(detect_mimetype(b"\x00\x00\x01\x00"), "image/x-icon");
+        // Audio
+        assert_eq!(detect_mimetype(b"ID3"), "audio/mpeg");
+        assert_eq!(detect_mimetype(b"\xFF\x0E"), "audio/mpeg");
+        assert_eq!(detect_mimetype(b"\xFF\x0F"), "audio/mpeg");
+        assert_eq!(detect_mimetype(b"OggS"), "audio/ogg");
+        assert_eq!(detect_mimetype(b"RIFF....WAVEfmt "), "audio/wav");
+        assert_eq!(detect_mimetype(b"fLaC"), "audio/x-flac");
+        // Video
+        assert_eq!(detect_mimetype(b"RIFF....AVI LIST"), "video/avi");
+        assert_eq!(detect_mimetype(b"....ftyp"), "video/mp4");
+        assert_eq!(detect_mimetype(b"\x00\x00\x01\x0B"), "video/mpeg");
+        assert_eq!(detect_mimetype(b"....moov"), "video/quicktime");
+        assert_eq!(detect_mimetype(b"\x1A\x45\xDF\xA3"), "video/webm");
+    }
 }

From 2be5b1c2351b1ed1772177651f61b64995b6d208 Mon Sep 17 00:00:00 2001
From: Vincent Flyson <vflyson@uberspace.net>
Date: Fri, 23 Aug 2019 20:16:16 -0400
Subject: [PATCH 3/6] Add support for iframes

---
 Cargo.toml  |  2 +-
 src/html.rs | 56 +++++++++++++++++++++++++++++++++++++----------------
 src/http.rs | 30 ++++++++++++++++++++--------
 src/main.rs |  4 ++--
 4 files changed, 64 insertions(+), 28 deletions(-)

diff --git a/Cargo.toml b/Cargo.toml
index 11b9328..8335adf 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "monolith"
-version = "2.0.7"
+version = "2.0.8"
 authors = ["Sunshine <sunshine@uberspace.net>"]
 description = "CLI tool to save webpages as a single HTML file"
 
diff --git a/src/html.rs b/src/html.rs
index 0da1aaf..100cddd 100644
--- a/src/html.rs
+++ b/src/html.rs
@@ -1,6 +1,7 @@
 use http::{is_valid_url, resolve_url, retrieve_asset};
 use std::default::Default;
 use std::io;
+use utils::data_to_dataurl;
 
 use html5ever::parse_document;
 use html5ever::rcdom::{Handle, NodeData, RcDom};
@@ -14,6 +15,7 @@ enum NodeMatch {
     Anchor,
     Script,
     Form,
+    IFrame,
     Other,
 }
 
@@ -85,26 +87,26 @@ pub fn walk_and_embed_assets(
             let attrs_mut = &mut attrs.borrow_mut();
             let mut found = NodeMatch::Other;
 
-            if &name.local == "link" {
-                for attr in attrs_mut.iter_mut() {
-                    if &attr.name.local == "rel" {
-                        if is_icon(&attr.value.to_string()) {
-                            found = NodeMatch::Icon;
-                            break;
-                        } else if attr.value.to_string() == "stylesheet" {
-                            found = NodeMatch::StyleSheet;
-                            break;
+            match name.local.as_ref() {
+                "link" => {
+                    for attr in attrs_mut.iter_mut() {
+                        if &attr.name.local == "rel" {
+                            if is_icon(&attr.value.to_string()) {
+                                found = NodeMatch::Icon;
+                                break;
+                            } else if attr.value.to_string() == "stylesheet" {
+                                found = NodeMatch::StyleSheet;
+                                break;
+                            }
                         }
                     }
                 }
-            } else if &name.local == "img" {
-                found = NodeMatch::Image;
-            } else if &name.local == "a" {
-                found = NodeMatch::Anchor;
-            } else if &name.local == "script" {
-                found = NodeMatch::Script;
-            } else if &name.local == "form" {
-                found = NodeMatch::Form;
+                "img" => { found = NodeMatch::Image; }
+                "a" => { found = NodeMatch::Anchor; }
+                "script" => { found = NodeMatch::Script; }
+                "form" => { found = NodeMatch::Form; }
+                "iframe" => { found = NodeMatch::IFrame; }
+                _ => {}
             }
 
             match found {
@@ -211,6 +213,26 @@ pub fn walk_and_embed_assets(
                         }
                     }
                 }
+                NodeMatch::IFrame => {
+                    for attr in attrs_mut.iter_mut() {
+                        if &attr.name.local == "src" {
+                            let src_full_url = resolve_url(&url, &attr.value.to_string()).unwrap();
+                            let iframe_data = retrieve_asset(
+                                &src_full_url,
+                                false,
+                                "text/html",
+                                opt_user_agent,
+                            );
+                            let dom = html_to_dom(&iframe_data.unwrap());
+                            walk_and_embed_assets(&src_full_url, &dom.document, opt_no_js, opt_no_images, opt_user_agent);
+                            let mut buf: Vec<u8> = Vec::new();
+                            serialize(&mut buf, &dom.document, SerializeOpts::default()).unwrap();
+                            let iframe_datauri = data_to_dataurl("text/html", &buf);
+                            attr.value.clear();
+                            attr.value.push_slice(iframe_datauri.as_str());
+                        }
+                    }
+                }
                 NodeMatch::Other => {}
             }
 
diff --git a/src/http.rs b/src/http.rs
index b18da0c..1765f14 100644
--- a/src/http.rs
+++ b/src/http.rs
@@ -21,11 +21,11 @@ pub fn resolve_url(from: &str, to: &str) -> Result<String, ParseError> {
         let mut re = String::new();
         if is_valid_url(from) {
             // It's a remote resource (HTTP)
-            if to.chars().nth(0) == Some('/') {
+            if to.starts_with('/') {
                 // (http://site.com/article/1, /...?)
                 let from_url = Url::parse(from)?;
 
-                if to.chars().nth(1) == Some('/') {
+                if to.starts_with("//") {
                     // (http://site.com/article/1, //images/1.png)
                     re.push_str(from_url.scheme());
                     re.push_str(":");
@@ -40,9 +40,8 @@ pub fn resolve_url(from: &str, to: &str) -> Result<String, ParseError> {
             } else {
                 // (http://site.com, css/main.css)
                 // TODO improve to ensure no // or /// ever happen
-                re.push_str(from);
-                re.push_str("/");
-                re.push_str(to);
+                let base = Url::parse(from)?;
+                re = base.join(to)?.to_string();
             }
         } else {
             // It's a local resource (fs)
@@ -126,13 +125,19 @@ mod tests {
 
     #[test]
     fn test_resolve_url() -> Result<(), ParseError> {
-        let resolved_url = resolve_url("https://www.kernel.org", "../category/signatures.html")?;
+        let resolved_url = resolve_url(
+            "https://www.kernel.org",
+            "../category/signatures.html",
+        )?;
         assert_eq!(
             resolved_url.as_str(),
-            "https://www.kernel.org/../category/signatures.html"
+            "https://www.kernel.org/category/signatures.html"
         );
 
-        let resolved_url = resolve_url("https://www.kernel.org", "category/signatures.html")?;
+        let resolved_url = resolve_url(
+            "https://www.kernel.org",
+            "category/signatures.html",
+        )?;
         assert_eq!(
             resolved_url.as_str(),
             "https://www.kernel.org/category/signatures.html"
@@ -165,6 +170,15 @@ mod tests {
             "https://www.kernel.org/theme/images/logos/tux.png"
         );
 
+        let resolved_url = resolve_url(
+            "https://www.w3schools.com/html/html_iframe.asp",
+            "default.asp",
+        )?;
+        assert_eq!(
+            resolved_url.as_str(),
+            "https://www.w3schools.com/html/default.asp"
+        );
+
         Ok(())
     }
 
diff --git a/src/main.rs b/src/main.rs
index 7988f2f..3e45f97 100644
--- a/src/main.rs
+++ b/src/main.rs
@@ -28,14 +28,14 @@ fn main() {
     // Process the command
     let arg_target = command.value_of("url").unwrap();
     let opt_no_js = command.is_present("no-js");
-    let opt_no_img = command.is_present("no-images");
+    let opt_no_images = command.is_present("no-images");
     let opt_user_agent = command.value_of("user-agent").unwrap_or(DEFAULT_USER_AGENT);
 
     if is_valid_url(arg_target) {
         let data = retrieve_asset(&arg_target, false, "", opt_user_agent);
         let dom = html_to_dom(&data.unwrap());
 
-        walk_and_embed_assets(&arg_target, &dom.document, opt_no_js, opt_no_img, opt_user_agent);
+        walk_and_embed_assets(&arg_target, &dom.document, opt_no_js, opt_no_images, opt_user_agent);
 
         print_dom(&dom.document);
         println!(); // Ensure newline at end of output

From 9138485c6100f2bdb5c6665b7127493483e1fca2 Mon Sep 17 00:00:00 2001
From: Vincent Flyson <vflyson@uberspace.net>
Date: Fri, 23 Aug 2019 20:19:49 -0400
Subject: [PATCH 4/6] Update Cargo.toml

---
 Cargo.toml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Cargo.toml b/Cargo.toml
index 8335adf..14a9cb3 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -2,7 +2,7 @@
 name = "monolith"
 version = "2.0.8"
 authors = ["Sunshine <sunshine@uberspace.net>"]
-description = "CLI tool to save webpages as a single HTML file"
+description = "CLI tool for saving web pages as a single HTML file"
 
 [dependencies]
 base64 = "0.10.1"

From 27f1411decdbadb8a483905b64839f9d153e1e49 Mon Sep 17 00:00:00 2001
From: Alan Pope <alan.pope@canonical.com>
Date: Fri, 23 Aug 2019 17:41:55 -0700
Subject: [PATCH 5/6] Add snapcraft yaml

Adds support for building snap of monolith
---
 snap/snapcraft.yaml | 34 ++++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)
 create mode 100644 snap/snapcraft.yaml

diff --git a/snap/snapcraft.yaml b/snap/snapcraft.yaml
new file mode 100644
index 0000000..8daf922
--- /dev/null
+++ b/snap/snapcraft.yaml
@@ -0,0 +1,34 @@
+name: monolith
+base: core18 
+version: git
+summary: Monolith - Save HTML pages with ease 
+description: |
+  A data hoarder's dream come true: bundle any web page into a single
+  HTML file. You can finally replace that gazillion of open tabs with
+  a gazillion of .html files stored somewhere on your precious little
+  drive.
+  Unlike conventional "Save page as…", monolith not only saves the
+  target document, it embeds CSS, image, and JavaScript assets all
+  at once, producing a single HTML5 document that is a joy to store
+  and share.
+  If compared to saving websites with wget -mpk, monolith embeds
+  all assets as data URLs and therefore displays the saved page
+  exactly the same, being completely separated from the Internet.
+
+confinement: strict
+
+parts:
+  monolith:
+    plugin: rust
+    source: .
+    build-packages:
+      - libssl-dev
+      - pkg-config
+
+apps:
+  monolith:
+    command: monolith
+    plugs:
+      - home
+      - network
+      - removable-media

From c34d77d5d84dc190e0673779a7cbe3b261c422d4 Mon Sep 17 00:00:00 2001
From: Vincent Flyson <vflyson@uberspace.net>
Date: Fri, 23 Aug 2019 23:06:06 -0400
Subject: [PATCH 6/6] Revamp resolve_url() and improve code format

---
 Cargo.toml  |  2 +-
 src/html.rs | 16 +++++++++----
 src/http.rs | 68 +++++++++++++++++------------------------------------
 src/main.rs | 15 ++++++++----
 4 files changed, 46 insertions(+), 55 deletions(-)

diff --git a/Cargo.toml b/Cargo.toml
index 14a9cb3..4694a41 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "monolith"
-version = "2.0.8"
+version = "2.0.9"
 authors = ["Sunshine <sunshine@uberspace.net>"]
 description = "CLI tool for saving web pages as a single HTML file"
 
diff --git a/src/html.rs b/src/html.rs
index 100cddd..22052e3 100644
--- a/src/html.rs
+++ b/src/html.rs
@@ -19,7 +19,8 @@ enum NodeMatch {
     Other,
 }
 
-const PNG_PIXEL: &str = "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mNkYAAAAAYAAjCB0C8AAAAASUVORK5CYII=";
+const TRANSPARENT_PIXEL: &str = "data:image/png;base64,\
+iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mNkYAAAAAYAAjCB0C8AAAAASUVORK5CYII=";
 
 const JS_DOM_EVENT_ATTRS: [&str; 21] = [
     // Input
@@ -76,7 +77,8 @@ pub fn walk_and_embed_assets(
         NodeData::Comment { .. } => {
             // Note: in case of opt_no_js being set to true, there's no need to worry about
             //       getting rid of comments that may contain scripts, e.g. <!--[if IE]><script>...
-            //       since that's not part of W3C standard and gets ignored by browsers other than IE [5, 9]
+            //       since that's not part of W3C standard and therefore gets ignored
+            //       by browsers other than IE [5, 9]
         }
 
         NodeData::Element {
@@ -130,7 +132,7 @@ pub fn walk_and_embed_assets(
                         if &attr.name.local == "src" {
                             if opt_no_images {
                                 attr.value.clear();
-                                attr.value.push_slice(PNG_PIXEL);
+                                attr.value.push_slice(TRANSPARENT_PIXEL);
                             } else {
                                 let src_full_url = resolve_url(&url, &attr.value.to_string());
                                 let img_datauri = retrieve_asset(
@@ -224,7 +226,13 @@ pub fn walk_and_embed_assets(
                                 opt_user_agent,
                             );
                             let dom = html_to_dom(&iframe_data.unwrap());
-                            walk_and_embed_assets(&src_full_url, &dom.document, opt_no_js, opt_no_images, opt_user_agent);
+                            walk_and_embed_assets(
+                                &src_full_url,
+                                &dom.document,
+                                opt_no_js,
+                                opt_no_images,
+                                opt_user_agent,
+                            );
                             let mut buf: Vec<u8> = Vec::new();
                             serialize(&mut buf, &dom.document, SerializeOpts::default()).unwrap();
                             let iframe_datauri = data_to_dataurl("text/html", &buf);
diff --git a/src/http.rs b/src/http.rs
index 1765f14..f13baf4 100644
--- a/src/http.rs
+++ b/src/http.rs
@@ -9,6 +9,13 @@ lazy_static! {
     static ref REGEX_URL: Regex = Regex::new(r"^https?://").unwrap();
 }
 
+pub fn is_data_url(url: &str) -> Result<bool, String> {
+    match Url::parse(url) {
+        Ok(parsed_url) => Ok(parsed_url.scheme() == "data"),
+        Err(err) => Err(format!("{}", err)),
+    }
+}
+
 pub fn is_valid_url(path: &str) -> bool {
     REGEX_URL.is_match(path)
 }
@@ -18,59 +25,19 @@ pub fn resolve_url(from: &str, to: &str) -> Result<String, ParseError> {
         // (anything, http://site.com/css/main.css)
         to.to_string()
     } else {
-        let mut re = String::new();
-        if is_valid_url(from) {
-            // It's a remote resource (HTTP)
-            if to.starts_with('/') {
-                // (http://site.com/article/1, /...?)
-                let from_url = Url::parse(from)?;
-
-                if to.starts_with("//") {
-                    // (http://site.com/article/1, //images/1.png)
-                    re.push_str(from_url.scheme());
-                    re.push_str(":");
-                    re.push_str(to);
-                } else {
-                    // (http://site.com/article/1, /css/main.css)
-                    re.push_str(from_url.scheme());
-                    re.push_str("://");
-                    re.push_str(from_url.host_str().unwrap());
-                    re.push_str(to);
-                }
-            } else {
-                // (http://site.com, css/main.css)
-                // TODO improve to ensure no // or /// ever happen
-                let base = Url::parse(from)?;
-                re = base.join(to)?.to_string();
-            }
-        } else {
-            // It's a local resource (fs)
-            // TODO improve to ensure no // or /// ever happen
-            // TODO for fs use basepath instead of $from
-            re.push_str(from);
-            re.push_str("/");
-            re.push_str(to);
-        }
-        re
+        Url::parse(from)?.join(to)?.to_string()
     };
 
     Ok(result)
 }
 
-pub fn url_is_data(url: &str) -> Result<bool, String> {
-    match Url::parse(url) {
-        Ok(parsed_url) => Ok(parsed_url.scheme() == "data"),
-        Err(err) => Err(format!("{}", err)),
-    }
-}
-
 pub fn retrieve_asset(
     url: &str,
     as_dataurl: bool,
     as_mime: &str,
     opt_user_agent: &str,
 ) -> Result<String, reqwest::Error> {
-    if url_is_data(&url).unwrap() {
+    if is_data_url(&url).unwrap() {
         Ok(url.to_string())
     } else {
         let client = Client::builder()
@@ -161,6 +128,15 @@ mod tests {
             "https://www.kernel.org/theme/images/logos/tux.png"
         );
 
+        let resolved_url = resolve_url(
+            "https://www.kernel.org",
+            "//another-host.org/theme/images/logos/tux.png",
+        )?;
+        assert_eq!(
+            resolved_url.as_str(),
+            "https://another-host.org/theme/images/logos/tux.png"
+        );
+
         let resolved_url = resolve_url(
             "https://www.kernel.org/category/signatures.html",
             "/theme/images/logos/tux.png",
@@ -183,12 +159,12 @@ mod tests {
     }
 
     #[test]
-    fn test_url_is_data() {
+    fn test_is_data_url() {
         assert!(
-            url_is_data("data:text/html;base64,V2VsY29tZSBUbyBUaGUgUGFydHksIDxiPlBhbDwvYj4h")
+            is_data_url("data:text/html;base64,V2VsY29tZSBUbyBUaGUgUGFydHksIDxiPlBhbDwvYj4h")
                 .unwrap_or(false)
         );
-        assert!(!url_is_data("https://kernel.org").unwrap_or(false));
-        assert!(!url_is_data("//kernel.org").unwrap_or(false));
+        assert!(!is_data_url("https://kernel.org").unwrap_or(false));
+        assert!(!is_data_url("//kernel.org").unwrap_or(false));
     }
 }
diff --git a/src/main.rs b/src/main.rs
index 3e45f97..80b2666 100644
--- a/src/main.rs
+++ b/src/main.rs
@@ -6,7 +6,8 @@ use clap::{App, Arg};
 use monolith::html::{html_to_dom, print_dom, walk_and_embed_assets};
 use monolith::http::{is_valid_url, retrieve_asset};
 
-static DEFAULT_USER_AGENT: &str = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.14; rv:66.0) Gecko/20100101 Firefox/66.0";
+static DEFAULT_USER_AGENT: &str =
+    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.14; rv:66.0) Gecko/20100101 Firefox/66.0";
 
 fn main() {
     let command = App::new("monolith")
@@ -32,10 +33,16 @@ fn main() {
     let opt_user_agent = command.value_of("user-agent").unwrap_or(DEFAULT_USER_AGENT);
 
     if is_valid_url(arg_target) {
-        let data = retrieve_asset(&arg_target, false, "", opt_user_agent);
-        let dom = html_to_dom(&data.unwrap());
+        let data = retrieve_asset(&arg_target, false, "", opt_user_agent).unwrap();
+        let dom = html_to_dom(&data);
 
-        walk_and_embed_assets(&arg_target, &dom.document, opt_no_js, opt_no_images, opt_user_agent);
+        walk_and_embed_assets(
+            &arg_target,
+            &dom.document,
+            opt_no_js,
+            opt_no_images,
+            opt_user_agent,
+        );
 
         print_dom(&dom.document);
         println!(); // Ensure newline at end of output