Rewrite it in Rust (RIIR) (WIP)

.gitignore

@@ -0,0 +1,20 @@
+# Created by https://www.toptal.com/developers/gitignore/api/rust
+# Edit at https://www.toptal.com/developers/gitignore?templates=rust
+
+### Rust ###
+# Generated by Cargo
+# will have compiled files and executables
+debug/
+target/
+
+# Remove Cargo.lock from gitignore if creating an executable, leave it for libraries
+# More information here https://doc.rust-lang.org/cargo/guide/cargo-toml-vs-cargo-lock.html
+Cargo.lock
+
+# These are backup files generated by rustfmt
+**/*.rs.bk
+
+# MSVC Windows builds of rustc generate these, which store debugging information
+*.pdb
+
+# End of https://www.toptal.com/developers/gitignore/api/rust

Cargo.toml

@@ -0,0 +1,18 @@
+[package]
+name = "doi"
+version = "0.1.0"
+edition = "2021"
+rust-version = "1.65.0"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[dependencies]
+clap = { version = "4.2.5", features = ["derive"] }
+either = "1.8.1"
+itertools = "0.10.5"
+nom-bibtex = "0.4.0"
+nutype = { version = "0.2.0", features = ["regex"] }
+once_cell = "1.17.1"
+regex = "1.8.1"
+reqwest = { version = "0.11", features = ["blocking"] }
+url = "2.3.1"

README.md

@@ -1,49 +1,53 @@
 [![DOI](https://zenodo.org/badge/67431697.svg)](https://zenodo.org/badge/latestdoi/67431697)
 
-# doi2bib and friends
-
-This repository provides scripts for converting from either [Digital Object Identifier (DOI)](https://www.doi.org) or [Uniform Resource Locator (URL)](https://en.wikipedia.org/wiki/URL) to [BibTeX](http://www.bibtex.org), or from DOI to plain text.
-
 <p align="center">
   <img alt="ASCII video" src="cast.svg">
 </p>
 
-## doi2bib
+TODO: support storing to the clipboard automatically.
+TODO: add the surname of the first author automatically if not given (if only the year is shown as id when retrieved)
 
-Convert [Digital Object Identifier (DOI)](https://www.doi.org) to
-[BibTeX](http://www.bibtex.org) using
-[crosscite.org](https://citation.crosscite.org/).
-DOIs are received and the corresponding BibTeX entries are output.
+# Bibliography in your command-line
 
-Inspired by <https://gist.github.com/mlund/4609288> and
-<http://www.doi2bib.org/>.
+This repository provides scripts for converting from either [Digital Object Identifier (DOI)](https://www.doi.org) or [Uniform Resource Locator (URL)](https://en.wikipedia.org/wiki/URL) to [BibTeX](http://www.bibtex.org), or from DOI to plain text.
+
+## `doi2bib`
 
-**October 16, 2017**: <http://www.doi2bib.org/> seems not to be working
-any more.
+Convert [Digital Object Identifier (DOI)](https://www.doi.org) to [BibTeX](http://www.bibtex.org) using [crosscite.org](https://citation.crosscite.org/).
+DOIs are received and the corresponding BibTeX entries are output.
+(Inspired by <https://gist.github.com/mlund/4609288> and <http://www.doi2bib.org/>.)
 
-## doi2text
+## `doi2text`
 
-Convert [Digital Object Identifier (DOI)](https://www.doi.org) to plain text
-using [crosscite.org](https://citation.crosscite.org/). DOIs are received and
-the corresponding text entries are output. In theory, all the styles
-available at <https://github.com/citation-style-language/styles> can be used.
+Convert [Digital Object Identifier (DOI)](https://www.doi.org) to plain text using [crosscite.org](https://citation.crosscite.org/).
+DOIs are received and the corresponding text entries are output. In theory, all the styles available at <https://github.com/citation-style-language/styles> can be used.
 
-## url2bib
+## `url2bib`
 
-Convert [Uniform Resource Locator (URL)](https://en.wikipedia.org/wiki/URL) to
-[BibTeX](http://www.bibtex.org) using pure
-[Bash](https://en.wikipedia.org/wiki/Bash_(Unix_shell)).
+Convert [Uniform Resource Locator (URL)](https://en.wikipedia.org/wiki/URL) to [BibTeX](http://www.bibtex.org) using pure [Bash](<https://en.wikipedia.org/wiki/Bash_(Unix_shell)>).
 URLs are received and the corresponding BibTeX entries are output.
+(This is made to be used exactly as one would use `doi2bib`.)
 
-(This is made to be used exactly as one would use doi2bib.)
+This requires `gawk` (`sudo apt install gawk`).
+
+## Dependencies
+
+`doi2bib` requires [curl](https://curl.haxx.se/):
+
+    $ sudo apt install curl
+
+You will also need `make` to install:
+
+    $ sudo apt install make
 
 ## Installation
 
 After downloading the tarball and using `cd` to go where the files are, simply do a `sudo make install` and everything will be installed.
+By default, it will install in `/usr/local/bin/`.
 
 ## Usage
 
-    $ doi2bib 10.1021/acs.jpcc.8b06244 10.1021/acscatal.9b00210                                
+    $ doi2bib 10.1021/acs.jpcc.8b06244 10.1021/acscatal.9b00210
     @article{Schneider_2018,
       title={How Do Secondary Phosphine Oxides Interact with Silver Nanoclusters? Insights from Computation},
       volume={122},
@@ -74,7 +78,7 @@ After downloading the tarball and using `cd` to go where the files are, simply d
       pages={3792–3799}
     }
 
-    $ url2bib google.com http://schneiderfelipe.xyz/ https://github.com/schneiderfelipe/doi2bib
+    $ url2bib google.com https://schneiderfelipe.github.io/ https://github.com/schneiderfelipe/doi
     @misc{google,
       title = {Google},
       howpublished = {\url{google.com}},
@@ -83,12 +87,16 @@ After downloading the tarball and using `cd` to go where the files are, simply d
 
     @misc{felipe-s-s-schneider,
       title = {Felipe S. S. Schneider},
-      howpublished = {\url{http://schneiderfelipe.xyz/}},
+      howpublished = {\url{https://schneiderfelipe.github.io/}},
       note = {Accessed: 2020-01-27}
     }
 
-    @misc{github-schneiderfelipe-doi2bib-convert-dois-and-urls-to-bibtex,
-      title = {GitHub - schneiderfelipe/doi2bib: Convert DOIs and URLs to BibTeX},
-      howpublished = {\url{https://github.com/schneiderfelipe/doi2bib}},
+    @misc{github-schneiderfelipe-doi-convert-dois-and-urls-to-bibtex,
+      title = {GitHub - schneiderfelipe/doi: Convert DOIs and URLs to BibTeX},
+      howpublished = {\url{https://github.com/schneiderfelipe/doi}},
       note = {Accessed: 2020-01-27}
     }
+
+## Citing doi2bib
+
+If you use doi2bib in your research, please cite it.

src/bibmagic.py

@@ -0,0 +1,17 @@
+#!/usr/bin/env python
+
+import sys
+import bibtexparser as btp
+from bibtexparser.bparser import BibTexParser
+from bibtexparser.customization import homogenize_latex_encoding
+
+with open(sys.argv[1]) as bib_file:
+    parser = BibTexParser()
+    # parser.customization = homogenize_latex_encoding
+    bib_db = btp.load(bib_file, parser=parser)
+
+if len(sys.argv) > 2:
+    with open(sys.argv[2], 'w') as bib_file:
+        btp.dump(bib_db, bib_file)
+else:
+    print(btp.dumps(bib_db))

src/bin/doi2bib.rs

@@ -0,0 +1,63 @@
+use std::process;
+use std::str::FromStr;
+
+use clap::Parser;
+use doi::Doi;
+use either::Either;
+use itertools::Itertools;
+use itertools::Position;
+use nom_bibtex::Bibliography;
+use nom_bibtex::Bibtex;
+use reqwest::blocking::Client;
+use reqwest::blocking::Response;
+use reqwest::header;
+use reqwest::Url;
+
+/// Retrieve BibTeX data for a given DOI.
+#[derive(Clone, Debug, Parser)]
+#[command(author, version, about, arg_required_else_help(true))]
+struct Cli {
+    /// DOI to retrieve BibTeX data for.
+    #[arg(value_parser(Doi::from_str))]
+    doi: Vec<Doi>,
+}
+
+fn main() {
+    let cli = Cli::parse();
+
+    for doi in cli.doi {
+        match Client::new()
+            .get(Url::from(&doi))
+            .header(header::ACCEPT, "text/bibliography; style=bibtex")
+            .send()
+            .and_then(Response::text)
+            .map_err(Either::Left)
+            .and_then(|text| Bibtex::parse(&text).map_err(Either::Right))
+        {
+            Ok(bibtex) => {
+                bibtex.bibliographies().iter().for_each(|biblio| {
+                    print(biblio);
+                });
+            }
+            Err(e) => {
+                eprintln!("Error retrieving DOI {doi}: {e}");
+                process::exit(1);
+            }
+        }
+    }
+}
+
+fn print(biblio: &Bibliography) {
+    println!("@{}{{{},", biblio.entry_type(), biblio.citation_key());
+    biblio.tags().iter().with_position().for_each(|item| {
+        match item {
+            Position::First((key, value)) | Position::Middle((key, value)) => {
+                println!("  {key:9} = {{{value}}},");
+            }
+            Position::Last((key, value)) | Position::Only((key, value)) => {
+                println!("  {key:9} = {{{value}}}");
+            }
+        }
+    });
+    println!("}}\n");
+}

src/bin/doi2text.rs

@@ -0,0 +1,3 @@
+fn main() {
+    println!("Hello, world!");
+}

src/bin/url2bib.rs

@@ -0,0 +1,62 @@
+use std::process;
+use std::str::FromStr;
+
+use clap::Parser;
+use itertools::Itertools;
+use itertools::Position;
+use nom_bibtex::Bibliography;
+use reqwest::blocking::Client;
+use reqwest::blocking::Response;
+use reqwest::Url;
+
+/// Retrieve BibTeX data for a given URL.
+#[derive(Clone, Debug, Parser)]
+#[command(author, version, about, arg_required_else_help(true))]
+struct Cli {
+    /// URL to retrieve BibTeX data for.
+    #[arg(value_parser(Url::from_str))]
+    url: Vec<Url>,
+}
+
+fn main() {
+    let cli = Cli::parse();
+
+    for url in cli.url {
+        match Client::new()
+            .get(url.as_str())
+            .send()
+            .and_then(Response::text)
+        {
+            Ok(html) => {
+                let title: String = todo!("Hello world!");
+                let slug: String = todo!("hello-world");
+                let today: String = todo!("%Y-%m-%d");
+                let biblio = Bibliography::new("misc".into(), slug, vec![
+                    ("title".into(), title),
+                    ("howpublished".into(), format!(r"\url{{{}}}", url)),
+                    ("note".into(), format!("Accessed: {}", today)),
+                ]);
+                print(&biblio);
+            }
+            Err(e) => {
+                eprintln!("Error retrieving URL {url}: {e}");
+                process::exit(1);
+            }
+        }
+    }
+}
+
+fn print(biblio: &Bibliography) {
+    println!("@{}{{{},", biblio.entry_type(), biblio.citation_key());
+    biblio.tags().iter().with_position().for_each(|item| {
+        match item {
+            Position::First((key, value)) | Position::Middle((key, value)) => {
+                println!("  {key:9} = {{{value}}},");
+            }
+            Position::Last((key, value)) | Position::Only((key, value)) => {
+                println!("  {key:9} = {{{value}}}");
+            }
+        }
+    });
+    println!("}}\n");
+}

src/doi2bib

@@ -39,16 +39,16 @@
 #?
 #? License:
 #?
-#?   doi2bib <https://github.com/schneiderfelipe/doi2bib>
+#?   doi2bib <https://github.com/schneiderfelipe/doi>
 #?   is licensed under the MIT License.
 
 while getopts ":hv" opt "$@"; do
   case $opt in
-    h)  # help
+    h) # help
       grep "^#?" "$0" | cut -c 4-
       exit 0
       ;;
-    v)  # version
+    v) # version
       grep "^#? doi2bib" "$0" | cut -c 4-
       exit 0
       ;;
@@ -64,18 +64,21 @@ while getopts ":hv" opt "$@"; do
 done
 
 # recover $@
-shift $((OPTIND-1))
+shift $((OPTIND - 1))
 
 # we consider everything after the command a list of DOIs.
 for doi in "$@"; do
   # we do some encoding as needed.
   doi=${doi//+/%2B}
   http_headers="Accept: text/bibliography; style=bibtex"
 
+  echo "$http_headers"
+  echo
+
   # we retrieve the data from https://doi.org/
-  curl -s -LH "$http_headers" "https://doi.org/${doi}" | \
-    sed -e $'s/^ *//' \
-        -e $'s/}, /},\\\n  /g' \
-        -e $'s/, /,\\\n  /1' \
-        -e $'s/}}$/}\\\n}\\\n/'
+  curl -LH "$http_headers" "https://doi.org/${doi}" \
+    | sed -e $'s/^ *//' \
+      -e $'s/}, /},\\\n  /g' \
+      -e $'s/, /,\\\n  /1' \
+      -e $'s/}}$/}\\\n}\\\n/'
 done