JabRef version 5.2--2020-09-06--c0b139a on Windows 10 10.0 amd64, Java 14.0.2
Steps to reproduce the behavior:
- Save the file
@Misc{TrustedSlind,
author = {Konrad Slind},
title = {Trusted Extensions of Interactive Theorem Provers: Workshop Summary},
date = {2010-08},
location = {Cambridge, England},
url = {http://www.cs.utexas.edu/users/kaufmann/itp-trusted-extensions-aug-2010/summary/summary.pdf},
}as a .bib file.
- Open this file in JabRef
- Click on the one entry to select it
- Click Quality -> Cleanup entries / Alt+F8
- Ensure that only the first item ("Move DOIs from note and URL field to DOI field and remove http prefix") is checked
- Click OK
- Double-click on the entry and click "BibTeX source"
Note that the new source is
@Misc{TrustedSlind,
author = {Konrad Slind},
title = {Trusted Extensions of Interactive Theorem Provers: Workshop Summary},
date = {2010-08},
doi = {10/summary},
location = {Cambridge, England},
}This url is not a DOI link, though! Presumably this is because the matcher code at
|
// Regex |
|
// (see http://www.doi.org/doi_handbook/2_Numbering.html) |
|
private static final String DOI_EXP = "" |
|
+ "(?:urn:)?" // optional urn |
|
+ "(?:doi:)?" // optional doi |
|
+ "(" // begin group \1 |
|
+ "10" // directory indicator |
|
+ "(?:\\.[0-9]+)+" // registrant codes |
|
+ "[/:%]" // divider |
|
+ "(?:.+)" // suffix alphanumeric string |
|
+ ")"; // end group \1 |
|
private static final String FIND_DOI_EXP = "" |
|
+ "(?:urn:)?" // optional urn |
|
+ "(?:doi:)?" // optional doi |
|
+ "(" // begin group \1 |
|
+ "10" // directory indicator |
|
+ "(?:\\.[0-9]+)+" // registrant codes |
|
+ "[/:]" // divider |
|
+ "(?:[^\\s]+)" // suffix alphanumeric without space |
|
+ ")"; // end group \1 |
|
|
|
// Regex (Short DOI) |
|
private static final String SHORT_DOI_EXP = "" |
|
+ "(?:urn:)?" // optional urn |
|
+ "(?:doi:)?" // optional doi |
|
+ "(" // begin group \1 |
|
+ "10" // directory indicator |
|
+ "[/:%]" // divider |
|
+ "[a-zA-Z0-9]+" |
|
+ ")"; // end group \1 |
|
private static final String FIND_SHORT_DOI_EXP = "" |
|
+ "(?:urn:)?" // optional urn |
|
+ "(?:doi:)?" // optional doi |
|
+ "(" // begin group \1 |
|
+ "10" // directory indicator |
|
+ "[/:]" // divider |
|
+ "[a-zA-Z0-9]+" |
|
+ "(?:[^\\s]+)" // suffix alphanumeric without space |
|
+ ")"; // end group \1 |
|
|
|
private static final String HTTP_EXP = "https?://[^\\s]+?" + DOI_EXP; |
|
private static final String SHORT_DOI_HTTP_EXP = "https?://[^\\s]+?" + SHORT_DOI_EXP; |
|
// Pattern |
|
private static final Pattern EXACT_DOI_PATT = Pattern.compile("^(?:https?://[^\\s]+?)?" + DOI_EXP + "$", Pattern.CASE_INSENSITIVE); |
|
private static final Pattern DOI_PATT = Pattern.compile("(?:https?://[^\\s]+?)?" + FIND_DOI_EXP, Pattern.CASE_INSENSITIVE); |
|
// Pattern (short DOI) |
|
private static final Pattern EXACT_SHORT_DOI_PATT = Pattern.compile("^(?:https?://[^\\s]+?)?" + SHORT_DOI_EXP, Pattern.CASE_INSENSITIVE); |
|
private static final Pattern SHORT_DOI_PATT = Pattern.compile("(?:https?://[^\\s]+?)?" + FIND_SHORT_DOI_EXP, Pattern.CASE_INSENSITIVE); |
considers all non-space text starting with
http:// or
https://, followed by
10/ followed by any non-space text, to be a DOI. This is absurd. The character immediately preceding the
10,
doi:, or
urn: should at the very least be required to be a url separator character such as
/,
:,
?,
&, or
=.
JabRef version 5.2--2020-09-06--c0b139a on Windows 10 10.0 amd64, Java 14.0.2
Steps to reproduce the behavior:
as a
.bibfile.Note that the new source is
This url is not a DOI link, though! Presumably this is because the matcher code at
jabref/src/main/java/org/jabref/model/entry/identifier/DOI.java
Lines 30 to 77 in ba68c09
considers all non-space text starting with
http://orhttps://, followed by10/followed by any non-space text, to be a DOI. This is absurd. The character immediately preceding the10,doi:, orurn:should at the very least be required to be a url separator character such as/,:,?,&, or=.