Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add support for custom headers in input processing #1561

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Add support for custom headers in input processing #1561

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d4ede50
Add support for custom headers when checking the initial inputs
mre Nov 7, 2024
cd2833b
wip
mre Nov 8, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions examples/collect_links/collect_links.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
use http::HeaderMap;
use lychee_lib::{Collector, Input, InputSource, Result};
use reqwest::Url;
use std::path::PathBuf;
Expand All @@ -13,11 +14,13 @@ async fn main() -> Result<()> {
)),
file_type_hint: None,
excluded_paths: None,
headers: HeaderMap::new(),
},
Input {
source: InputSource::FsPath(PathBuf::from("fixtures/TEST.md")),
file_type_hint: None,
excluded_paths: None,
headers: HeaderMap::new(),
},
];

Expand Down
13 changes: 11 additions & 2 deletions lychee-bin/src/options.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
use crate::archive::Archive;
use crate::parse::parse_base;
use crate::parse::{parse_base, parse_headers};
use crate::verbosity::Verbosity;
use anyhow::{anyhow, Context, Error, Result};
use clap::builder::PossibleValuesParser;
Expand Down Expand Up @@ -195,9 +195,18 @@ impl LycheeOptions {
} else {
Some(self.config.exclude_path.clone())
};
let headers = parse_headers(&self.config.header)?;
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is not ideal because we parse the headers twice: here and in lychee-bin/src/client. We should probably move the parsing to the Clap config.

self.raw_inputs
.iter()
.map(|s| Input::new(s, None, self.config.glob_ignore_case, excluded.clone()))
.map(|s| {
Input::new(
s,
None,
self.config.glob_ignore_case,
excluded.clone(),
headers.clone(),
)
})
.collect::<Result<_, _>>()
.context("Cannot parse inputs from arguments")
}
Expand Down
28 changes: 24 additions & 4 deletions lychee-lib/src/collector.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -136,7 +136,7 @@ impl Collector {
mod tests {
use std::{collections::HashSet, convert::TryFrom, fs::File, io::Write};

use http::StatusCode;
use http::{HeaderMap, StatusCode};
use reqwest::Url;

use super::*;
Expand Down Expand Up @@ -173,7 +173,13 @@ mod tests {
// Treat as plaintext file (no extension)
let file_path = temp_dir.path().join("README");
let _file = File::create(&file_path).unwrap();
let input = Input::new(&file_path.as_path().display().to_string(), None, true, None)?;
let input = Input::new(
&file_path.as_path().display().to_string(),
None,
true,
None,
HeaderMap::new(),
)?;
let contents: Vec<_> = input
.get_contents(true, true, true)
.collect::<Vec<_>>()
Expand All @@ -186,7 +192,7 @@ mod tests {

#[tokio::test]
async fn test_url_without_extension_is_html() -> Result<()> {
let input = Input::new("https://example.com/", None, true, None)?;
let input = Input::new("https://example.com/", None, true, None, HeaderMap::new())?;
let contents: Vec<_> = input
.get_contents(true, true, true)
.collect::<Vec<_>>()
Expand Down Expand Up @@ -221,6 +227,7 @@ mod tests {
source: InputSource::String(TEST_STRING.to_owned()),
file_type_hint: None,
excluded_paths: None,
headers: HeaderMap::new(),
},
Input {
source: InputSource::RemoteUrl(Box::new(
Expand All @@ -230,11 +237,13 @@ mod tests {
)),
file_type_hint: None,
excluded_paths: None,
headers: HeaderMap::new(),
},
Input {
source: InputSource::FsPath(file_path),
file_type_hint: None,
excluded_paths: None,
headers: HeaderMap::new(),
},
Input {
source: InputSource::FsGlob {
Expand All @@ -243,6 +252,7 @@ mod tests {
},
file_type_hint: None,
excluded_paths: None,
headers: HeaderMap::new(),
},
];

Expand All @@ -267,7 +277,8 @@ mod tests {
let input = Input {
source: InputSource::String("This is [a test](https://endler.dev). This is a relative link test [Relative Link Test](relative_link)".to_string()),
file_type_hint: Some(FileType::Markdown),
excluded_paths: None,
excluded_paths: None,
headers: HeaderMap::new(),
};
let links = collect(vec![input], Some(base)).await;

Expand All @@ -294,6 +305,7 @@ mod tests {
),
file_type_hint: Some(FileType::Html),
excluded_paths: None,
headers: HeaderMap::new(),
};
let links = collect(vec![input], Some(base)).await;

Expand Down Expand Up @@ -323,6 +335,7 @@ mod tests {
),
file_type_hint: Some(FileType::Html),
excluded_paths: None,
headers: HeaderMap::new(),
};
let links = collect(vec![input], Some(base)).await;

Expand All @@ -349,6 +362,7 @@ mod tests {
),
file_type_hint: Some(FileType::Markdown),
excluded_paths: None,
headers: HeaderMap::new(),
};

let links = collect(vec![input], Some(base)).await;
Expand All @@ -372,6 +386,7 @@ mod tests {
source: InputSource::String(input),
file_type_hint: Some(FileType::Html),
excluded_paths: None,
headers: HeaderMap::new(),
};
let links = collect(vec![input], Some(base)).await;

Expand Down Expand Up @@ -404,6 +419,7 @@ mod tests {
source: InputSource::RemoteUrl(Box::new(server_uri.clone())),
file_type_hint: None,
excluded_paths: None,
headers: HeaderMap::new(),
};

let links = collect(vec![input], None).await;
Expand All @@ -424,6 +440,7 @@ mod tests {
),
file_type_hint: None,
excluded_paths: None,
headers: HeaderMap::new(),
};
let links = collect(vec![input], None).await;

Expand Down Expand Up @@ -454,6 +471,7 @@ mod tests {
)),
file_type_hint: Some(FileType::Html),
excluded_paths: None,
headers: HeaderMap::new(),
},
Input {
source: InputSource::RemoteUrl(Box::new(
Expand All @@ -465,6 +483,7 @@ mod tests {
)),
file_type_hint: Some(FileType::Html),
excluded_paths: None,
headers: HeaderMap::new(),
},
];

Expand Down Expand Up @@ -500,6 +519,7 @@ mod tests {
),
file_type_hint: Some(FileType::Html),
excluded_paths: None,
headers: HeaderMap::new(),
};

let links = collect(vec![input], Some(base)).await;
Expand Down
59 changes: 36 additions & 23 deletions lychee-lib/src/types/input.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,7 @@ use crate::{utils, ErrorKind, Result};
use async_stream::try_stream;
use futures::stream::Stream;
use glob::glob_with;
use http::HeaderMap;
use ignore::WalkBuilder;
use reqwest::Url;
use serde::{Deserialize, Serialize};
Expand Down Expand Up @@ -105,14 +106,16 @@ impl Display for InputSource {
}

/// Lychee Input with optional file hint for parsing
#[derive(Clone, Debug, PartialEq, Eq, Hash)]
#[derive(Clone, Debug, PartialEq, Eq)]
pub struct Input {
/// Origin of input
pub source: InputSource,
/// Hint to indicate which extractor to use
pub file_type_hint: Option<FileType>,
/// Excluded paths that will be skipped when reading content
pub excluded_paths: Option<Vec<PathBuf>>,
/// Custom headers to be used when fetching remote URLs
pub headers: reqwest::header::HeaderMap,
}

impl Input {
Expand All @@ -129,6 +132,7 @@ impl Input {
file_type_hint: Option<FileType>,
glob_ignore_case: bool,
excluded_paths: Option<Vec<PathBuf>>,
headers: reqwest::header::HeaderMap,
) -> Result<Self> {
let source = if value == STDIN {
InputSource::Stdin
Expand Down Expand Up @@ -194,9 +198,20 @@ impl Input {
source,
file_type_hint,
excluded_paths,
headers,
})
}

/// Convenience constructor with sane defaults
///
/// # Errors
///
/// Returns an error if the input does not exist (i.e. invalid path)
/// and the input cannot be parsed as a URL.
pub fn from_value(value: &str) -> Result<Self> {
Self::new(value, None, false, None, HeaderMap::new())
}

/// Retrieve the contents from the input
///
/// # Errors
Expand Down Expand Up @@ -424,6 +439,8 @@ fn is_excluded_path(excluded_paths: &[PathBuf], path: &PathBuf) -> bool {

#[cfg(test)]
mod tests {
use http::HeaderMap;

use super::*;

#[test]
Expand All @@ -434,14 +451,15 @@ mod tests {
assert!(path.exists());
assert!(path.is_relative());

let input = Input::new(test_file, None, false, None);
let input = Input::new(test_file, None, false, None, HeaderMap::new());
assert!(input.is_ok());
assert!(matches!(
input,
Ok(Input {
source: InputSource::FsPath(PathBuf { .. }),
file_type_hint: None,
excluded_paths: None
excluded_paths: None,
headers: _,
})
));
}
Expand All @@ -454,7 +472,7 @@ mod tests {
assert!(!path.exists());
assert!(path.is_relative());

let input = Input::new(test_file, None, false, None);
let input = Input::from_value(test_file);
assert!(input.is_err());
assert!(matches!(input, Err(ErrorKind::InvalidFile(PathBuf { .. }))));
}
Expand Down Expand Up @@ -497,7 +515,7 @@ mod tests {

#[test]
fn test_url_without_scheme() {
let input = Input::new("example.com", None, false, None);
let input = Input::from_value("example.com");
assert_eq!(
input.unwrap().source.to_string(),
String::from("http://example.com/")
Expand All @@ -508,7 +526,7 @@ mod tests {
#[cfg(windows)]
#[test]
fn test_windows_style_filepath_not_existing() {
let input = Input::new("C:\\example\\project\\here", None, false, None);
let input = Input::from_value("C:\\example\\project\\here");
assert!(input.is_err());
let input = input.unwrap_err();

Expand All @@ -528,7 +546,7 @@ mod tests {
let dir = temp_dir();
let file = NamedTempFile::new_in(dir).unwrap();
let path = file.path();
let input = Input::new(path.to_str().unwrap(), None, false, None).unwrap();
let input = Input::from_value(path.to_str().unwrap()).unwrap();

match input.source {
InputSource::FsPath(_) => (),
Expand All @@ -540,33 +558,28 @@ mod tests {
fn test_url_scheme_check_succeeding() {
// Valid http and https URLs
assert!(matches!(
Input::new("http://example.com", None, false, None),
Input::from_value("http://example.com"),
Ok(Input {
source: InputSource::RemoteUrl(_),
..
})
));
assert!(matches!(
Input::new("https://example.com", None, false, None),
Input::from_value("https://example.com"),
Ok(Input {
source: InputSource::RemoteUrl(_),
..
})
));
assert!(matches!(
Input::new(
"http://subdomain.example.com/path?query=value",
None,
false,
None
),
Input::from_value("http://subdomain.example.com/path?query=value",),
Ok(Input {
source: InputSource::RemoteUrl(_),
..
})
));
assert!(matches!(
Input::new("https://example.com:8080", None, false, None),
Input::from_value("https://example.com:8080"),
Ok(Input {
source: InputSource::RemoteUrl(_),
..
Expand All @@ -578,19 +591,19 @@ mod tests {
fn test_url_scheme_check_failing() {
// Invalid schemes
assert!(matches!(
Input::new("ftp://example.com", None, false, None),
Input::from_value("ftp://example.com"),
Err(ErrorKind::InvalidFile(_))
));
assert!(matches!(
Input::new("httpx://example.com", None, false, None),
Input::from_value("httpx://example.com"),
Err(ErrorKind::InvalidFile(_))
));
assert!(matches!(
Input::new("file:///path/to/file", None, false, None),
Input::from_value("file:///path/to/file"),
Err(ErrorKind::InvalidFile(_))
));
assert!(matches!(
Input::new("mailto:[email protected]", None, false, None),
Input::from_value("mailto:[email protected]"),
Err(ErrorKind::InvalidFile(_))
));
}
Expand All @@ -599,19 +612,19 @@ mod tests {
fn test_non_url_inputs() {
// Non-URL inputs
assert!(matches!(
Input::new("./local/path", None, false, None),
Input::from_value("./local/path"),
Err(ErrorKind::InvalidFile(_))
));
assert!(matches!(
Input::new("*.md", None, false, None),
Input::from_value("*.md"),
Ok(Input {
source: InputSource::FsGlob { .. },
..
})
));
// Assuming the current directory exists
assert!(matches!(
Input::new(".", None, false, None),
Input::from_value("."),
Ok(Input {
source: InputSource::FsPath(_),
..
Expand Down
Loading