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

Hyperlink DOIs to preferred resolver #6

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Hyperlink DOIs to preferred resolver #6

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
33c1453
Hyperlink DOIs to preferred resolver
katrinleinweber Nov 19, 2019
b2a04e4
Broaden DOI regex to more resolver variants
katrinleinweber Nov 19, 2019
fbee50d
Update DOI reg-ex to Crossref's recommendation
katrinleinweber Nov 19, 2019
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
22 changes: 11 additions & 11 deletions src/main/java/org/contentmine/cproject/metadata/CMDOI.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,19 +17,19 @@ public class CMDOI extends AbstractCM {

/**
*
http://dx.doi.org/10.5539/cis.v9n2p126
http://dx.doi.org/10.1530/edm-16-0003
http://dx.doi.org/10.12968/bjsn.2016.11.4.166
http://dx.doi.org/10.14358/pers.82.5.320
http://dx.doi.org/10.3109/10715762.2016.1162299
http://dx.doi.org/10.1127/ejm/2015/0027-2502
http://dx.doi.org/10.7467/ksae.2016.24.3.285
http://dx.doi.org/10.20488/austd.22645
http://dx.doi.org/10.1177/2150135116645604
http://dx.doi.org/10.1525/irqr.2016.9.1.29
https://doi.org/10.5539/cis.v9n2p126
https://doi.org/10.1530/edm-16-0003
https://doi.org/10.12968/bjsn.2016.11.4.166
https://doi.org/10.14358/pers.82.5.320
https://doi.org/10.3109/10715762.2016.1162299
https://doi.org/10.1127/ejm/2015/0027-2502
https://doi.org/10.7467/ksae.2016.24.3.285
https://doi.org/10.20488/austd.22645
https://doi.org/10.1177/2150135116645604
https://doi.org/10.1525/irqr.2016.9.1.29
*/

static Pattern PATTERN = Pattern.compile("https?://dx\\.doi\\.org/(10\\.\\d{3,8})/(.*)");
static Pattern PATTERN = Pattern.compile("https?://(dx\\.)?doi\\.org/10.\d{4,9}/[-._;()/:A-Za-z0-9]+");
public static CMDOI DUMMY = new CMDOI(null, null);

public CMDOI(String prefix, String suffix) {
Expand Down
4 changes: 2 additions & 2 deletions src/main/java/org/contentmine/cproject/metadata/DOIResolver.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,8 +29,8 @@ public class DOIResolver {
LOG.setLevel(Level.DEBUG);
}

private static final String HTTP_DOI_ORG_API_HANDLES = "http://doi.org/api/handles/";
private static final String HTTP_DX_DOI_ORG = "http://dx.doi.org/";
private static final String HTTP_DOI_ORG_API_HANDLES = "https://doi.org/api/handles/";
private static final String HTTP_DX_DOI_ORG = "https://doi.org/";
private static final String VALUE = "value";
private static final String DATA = "data";
private static final String VALUES = "values";
Expand Down
2 changes: 1 addition & 1 deletion src/main/java/org/contentmine/cproject/metadata/quickscrape/QSRecord.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@
*/
public class QSRecord {

private static final String HTTP_DX_DOI_ORG = "http://dx.doi.org/";
private static final String HTTP_DX_DOI_ORG = "https://doi.org/";
private static final Logger LOG = Logger.getLogger(QSRecord.class);
static {
LOG.setLevel(Level.DEBUG);
Expand Down
2 changes: 1 addition & 1 deletion src/main/java/org/contentmine/cproject/metadata/quickscrape/QuickscrapeLog.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,7 @@ public class QuickscrapeLog {

// info: URL processed
private final static Pattern OUTER = Pattern.compile("(trace|debug|info|warn|error)\\:\\s(.*)");
// [debug] [phantom] opening url: http://dx.doi.org/10.1093/mnras/stw468, HTTP GET
// [debug] [phantom] opening url: https://doi.org/10.1093/mnras/stw468, HTTP GET
private final static Pattern INNER1 = Pattern.compile("\\s*\\[(trace|debug|info|warn|error)\\]\\s+\\[(phantom)\\]\\s+(.*)");
// private final static Pattern INNER2 = Pattern.compile("\\[(^\\])+\\]\\s+(.*)");

Expand Down
4 changes: 2 additions & 2 deletions src/main/java/org/contentmine/cproject/util/CMineUtil.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,7 @@ public class CMineUtil {
LOG.setLevel(Level.DEBUG);
}

private static final String HTTP_DX_DOI_ORG2 = "http://dx.doi.org/";
private static final String HTTP_DX_DOI_ORG2 = "https://doi.org/";
private static final String HTML_START = "<";
private static final String PDF_START = "%PDF";
private static final String URL_PUNCT = "[\\/\\$\\%\\*\\(\\)\\[\\]]";
Expand Down Expand Up @@ -310,7 +310,7 @@ public static String stripChars(String s, String regex, String replace) {
return s == null ? null : s.replaceAll(regex, replace);
}

/** removes "http://dx.doi.org/" from start of string.
/** removes "https://doi.org/" from start of string.
*
* @param string
* @return
Expand Down
2 changes: 1 addition & 1 deletion src/main/java/org/contentmine/norma/biblio/EPMCResultsJsonEntry.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -87,7 +87,7 @@ public class EPMCResultsJsonEntry extends AbstractMetadata {
new CellRenderer(SOURCE).setVisible(false),
new CellRenderer(AUTHOR_STRING).setBrief(20),
new CellRenderer(ABSTRACT_TEXT).setBrief(20),
new CellRenderer(DOI).setHref0("http://doi.org/"),
new CellRenderer(DOI).setHref0("https://doi.org/"),
new CellRenderer(ID).setVisible(false),
new CellRenderer(PMID).setVisible(false),
new CellRenderer(PMCID).setHref0("foo/").setHref1("/bar").setVisible(false),
Expand Down
23,122 changes: 11,561 additions & 11,561 deletions src/main/resources/org/contentmine/ami/plugins/dictionary/funders.xml
View file
Open in desktop

Large diffs are not rendered by default.

23,124 changes: 11,562 additions & 11,562 deletions src/main/resources/org/contentmine/ami/plugins/dictionary/organization.xml
View file
Open in desktop

Large diffs are not rendered by default.

2 changes: 1 addition & 1 deletion src/main/resources/org/contentmine/ami/tagger/hindawi/documentTagger.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@
Volume 2014 (2014), Article ID 801626, 8 pages
<br></br>
// doi
<a href="http://dx.doi.org/10.1155/2014/801626">http://dx.doi.org/10.1155/2014/801626</a>
<a href="https://doi.org/10.1155/2014/801626">https://doi.org/10.1155/2014/801626</a>
</pre>
// articleType
<div class="article_type">Research Article</div>
Expand Down
50 changes: 25 additions & 25 deletions src/main/resources/org/contentmine/graphics/html/badhtml1.html
View file
Open in desktop

Large diffs are not rendered by default.

50 changes: 25 additions & 25 deletions src/main/resources/org/contentmine/graphics/html/badhtml1a.html
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -182,7 +182,7 @@
<em>Arts</em>
<b>2014</b>,
<em>3</em>(1), 27-45; doi:
<a href="http://dx.doi.org/10.3390/arts3010027">10.3390/arts3010027</a>
<a href="https://doi.org/10.3390/arts3010027">10.3390/arts3010027</a>
</div>
<div class="pubdates">
Received: 30 September 2013; in revised form: 28 October 2013 / Accepted: 1 December 2013 / Published: 3 January 2014
Expand Down Expand Up @@ -221,7 +221,7 @@
<em>Symmetry</em>
<b>2014</b>,
<em>6</em>(1), 23-66; doi:
<a href="http://dx.doi.org/10.3390/sym6010023">10.3390/sym6010023</a>
<a href="https://doi.org/10.3390/sym6010023">10.3390/sym6010023</a>
</div>
<div class="pubdates">
Received: 28 October 2013; in revised form: 13 December 2013 / Accepted: 13 December 2013 / Published: 3 January 2014
Expand Down Expand Up @@ -263,7 +263,7 @@
<em>Processes</em>
<b>2014</b>,
<em>2</em>(1), 34-57; doi:
<a href="http://dx.doi.org/10.3390/pr2010034">10.3390/pr2010034</a>
<a href="https://doi.org/10.3390/pr2010034">10.3390/pr2010034</a>
</div>
<div class="pubdates">
Received: 18 September 2013; in revised form: 5 December 2013 / Accepted: 19 December 2013 / Published: 3 January 2014
Expand Down Expand Up @@ -310,7 +310,7 @@
<em>Plants</em>
<b>2014</b>,
<em>3</em>(1), 27-57; doi:
<a href="http://dx.doi.org/10.3390/plants3010027">10.3390/plants3010027</a>
<a href="https://doi.org/10.3390/plants3010027">10.3390/plants3010027</a>
</div>
<div class="pubdates">
Received: 4 November 2013; in revised form: 18 December 2013 / Accepted: 20 December 2013 / Published: 3 January 2014
Expand Down Expand Up @@ -362,7 +362,7 @@
<em>Forests</em>
<b>2014</b>,
<em>5</em>(1), 21-71; doi:
<a href="http://dx.doi.org/10.3390/f5010021">10.3390/f5010021</a>
<a href="https://doi.org/10.3390/f5010021">10.3390/f5010021</a>
</div>
<div class="pubdates">
Received: 4 November 2013; in revised form: 15 December 2013 / Accepted: 18 December 2013 / Published: 3 January 2014
Expand Down Expand Up @@ -404,7 +404,7 @@
<em>Adm. Sci.</em>
<b>2014</b>,
<em>4</em>(1), 1-14; doi:
<a href="http://dx.doi.org/10.3390/admsci4010001">10.3390/admsci4010001</a>
<a href="https://doi.org/10.3390/admsci4010001">10.3390/admsci4010001</a>
</div>
<div class="pubdates">
Received: 8 October 2013; in revised form: 16 December 2013 / Accepted: 19 December 2013 / Published: 3 January 2014
Expand Down Expand Up @@ -442,7 +442,7 @@
<em>Arts</em>
<b>2014</b>,
<em>3</em>(1), 15-26; doi:
<a href="http://dx.doi.org/10.3390/arts3010015">10.3390/arts3010015</a>
<a href="https://doi.org/10.3390/arts3010015">10.3390/arts3010015</a>
</div>
<div class="pubdates">
Received: 27 October 2013; in revised form: 2 December 2013 / Accepted: 17 December 2013 / Published: 3 January 2014
Expand Down Expand Up @@ -485,7 +485,7 @@
<em>J. Funct. Biomater.</em>
<b>2014</b>,
<em>5</em>(1), 1-14; doi:
<a href="http://dx.doi.org/10.3390/jfb5010001">10.3390/jfb5010001</a>
<a href="https://doi.org/10.3390/jfb5010001">10.3390/jfb5010001</a>
</div>
<div class="pubdates">
Received: 27 August 2013; in revised form: 26 November 2013 / Accepted: 27 November 2013 / Published: 3 January 2014
Expand Down Expand Up @@ -526,7 +526,7 @@
<em>Int. J. Environ. Res. Public Health</em>
<b>2014</b>,
<em>11</em>(1), 713-733; doi:
<a href="http://dx.doi.org/10.3390/ijerph110100713">10.3390/ijerph110100713</a>
<a href="https://doi.org/10.3390/ijerph110100713">10.3390/ijerph110100713</a>
</div>
<div class="pubdates">
Received: 14 October 2013; in revised form: 16 December 2013 / Accepted: 18 December 2013 / Published: 3 January 2014
Expand Down Expand Up @@ -567,7 +567,7 @@
<em>Diversity</em>
<b>2014</b>,
<em>6</em>(1), 33-42; doi:
<a href="http://dx.doi.org/10.3390/d6010033">10.3390/d6010033</a>
<a href="https://doi.org/10.3390/d6010033">10.3390/d6010033</a>
</div>
<div class="pubdates">
Received: 2 October 2013; in revised form: 20 December 2013 / Accepted: 27 December 2013 / Published: 3 January 2014
Expand Down Expand Up @@ -618,7 +618,7 @@
<em>Diversity</em>
<b>2014</b>,
<em>6</em>(1), 18-32; doi:
<a href="http://dx.doi.org/10.3390/d6010018">10.3390/d6010018</a>
<a href="https://doi.org/10.3390/d6010018">10.3390/d6010018</a>
</div>
<div class="pubdates">
Received: 27 October 2013; in revised form: 3 December 2013 / Accepted: 24 December 2013 / Published: 3 January 2014
Expand Down Expand Up @@ -652,7 +652,7 @@
<em>Sustainability</em>
<b>2014</b>,
<em>6</em>(1), 251-266; doi:
<a href="http://dx.doi.org/10.3390/su6010251">10.3390/su6010251</a>
<a href="https://doi.org/10.3390/su6010251">10.3390/su6010251</a>
</div>
<div class="pubdates">
Received: 11 November 2013; in revised form: 13 December 2013 / Accepted: 27 December 2013 / Published: 3 January 2014
Expand Down Expand Up @@ -698,7 +698,7 @@
<em>Membranes</em>
<b>2014</b>,
<em>4</em>(1), 20-39; doi:
<a href="http://dx.doi.org/10.3390/membranes4010020">10.3390/membranes4010020</a>
<a href="https://doi.org/10.3390/membranes4010020">10.3390/membranes4010020</a>
</div>
<div class="pubdates">
Received: 6 November 2013; in revised form: 26 November 2013 / Accepted: 21 December 2013 / Published: 3 January 2014
Expand Down Expand Up @@ -743,7 +743,7 @@
<em>Energies</em>
<b>2014</b>,
<em>7</em>(1), 130-149; doi:
<a href="http://dx.doi.org/10.3390/en7010130">10.3390/en7010130</a>
<a href="https://doi.org/10.3390/en7010130">10.3390/en7010130</a>
</div>
<div class="pubdates">
Received: 21 October 2013; in revised form: 11 December 2013 / Accepted: 27 December 2013 / Published: 3 January 2014
Expand Down Expand Up @@ -781,7 +781,7 @@
<em>Societies</em>
<b>2014</b>,
<em>4</em>(1), 16-29; doi:
<a href="http://dx.doi.org/10.3390/soc4010016">10.3390/soc4010016</a>
<a href="https://doi.org/10.3390/soc4010016">10.3390/soc4010016</a>
</div>
<div class="pubdates">
Received: 31 October 2013; in revised form: 24 December 2013 / Accepted: 24 December 2013 / Published: 3 January 2014
Expand Down Expand Up @@ -820,7 +820,7 @@
<em>J. Sens. Actuator Netw.</em>
<b>2014</b>,
<em>3</em>(1), 44-63; doi:
<a href="http://dx.doi.org/10.3390/jsan3010044">10.3390/jsan3010044</a>
<a href="https://doi.org/10.3390/jsan3010044">10.3390/jsan3010044</a>
</div>
<div class="pubdates">
Received: 26 November 2013; in revised form: 15 December 2013 / Accepted: 23 December 2013 / Published: 3 January 2014
Expand Down Expand Up @@ -859,7 +859,7 @@
<em>Mar. Drugs</em>
<b>2014</b>,
<em>12</em>(1), 115-127; doi:
<a href="http://dx.doi.org/10.3390/md12010115">10.3390/md12010115</a>
<a href="https://doi.org/10.3390/md12010115">10.3390/md12010115</a>
</div>
<div class="pubdates">
Received: 14 October 2013; in revised form: 25 November 2013 / Accepted: 12 December 2013 / Published: 3 January 2014
Expand Down Expand Up @@ -914,7 +914,7 @@
<em>Energies</em>
<b>2014</b>,
<em>7</em>(1), 115-129; doi:
<a href="http://dx.doi.org/10.3390/en7010115">10.3390/en7010115</a>
<a href="https://doi.org/10.3390/en7010115">10.3390/en7010115</a>
</div>
<div class="pubdates">
Received: 22 October 2013; in revised form: 17 December 2013 / Accepted: 27 December 2013 / Published: 3 January 2014
Expand Down Expand Up @@ -961,7 +961,7 @@
<em>Materials</em>
<b>2014</b>,
<em>7</em>(1), 218-231; doi:
<a href="http://dx.doi.org/10.3390/ma7010218">10.3390/ma7010218</a>
<a href="https://doi.org/10.3390/ma7010218">10.3390/ma7010218</a>
</div>
<div class="pubdates">
Received: 28 November 2013; in revised form: 17 December 2013 / Accepted: 23 December 2013 / Published: 3 January 2014
Expand Down Expand Up @@ -1007,7 +1007,7 @@
<em>Int. J. Mol. Sci.</em>
<b>2014</b>,
<em>15</em>(1), 525-544; doi:
<a href="http://dx.doi.org/10.3390/ijms15010525">10.3390/ijms15010525</a>
<a href="https://doi.org/10.3390/ijms15010525">10.3390/ijms15010525</a>
</div>
<div class="pubdates">
Received: 13 November 2013; in revised form: 19 December 2013 / Accepted: 23 December 2013 / Published: 3 January 2014
Expand Down Expand Up @@ -1051,7 +1051,7 @@
<em>Materials</em>
<b>2014</b>,
<em>7</em>(1), 206-217; doi:
<a href="http://dx.doi.org/10.3390/ma7010206">10.3390/ma7010206</a>
<a href="https://doi.org/10.3390/ma7010206">10.3390/ma7010206</a>
</div>
<div class="pubdates">
Received: 8 October 2013; in revised form: 14 December 2013 / Accepted: 19 December 2013 / Published: 3 January 2014
Expand Down Expand Up @@ -1107,7 +1107,7 @@
<em>Int. J. Mol. Sci.</em>
<b>2014</b>,
<em>15</em>(1), 504-524; doi:
<a href="http://dx.doi.org/10.3390/ijms15010504">10.3390/ijms15010504</a>
<a href="https://doi.org/10.3390/ijms15010504">10.3390/ijms15010504</a>
</div>
<div class="pubdates">
Received: 30 October 2013; in revised form: 16 December 2013 / Accepted: 27 December 2013 / Published: 3 January 2014
Expand Down Expand Up @@ -1152,7 +1152,7 @@
<em>Remote Sens.</em>
<b>2014</b>,
<em>6</em>(1), 540-554; doi:
<a href="http://dx.doi.org/10.3390/rs6010540">10.3390/rs6010540</a>
<a href="https://doi.org/10.3390/rs6010540">10.3390/rs6010540</a>
</div>
<div class="pubdates">
Received: 30 October 2013; in revised form: 25 December 2013 / Accepted: 27 December 2013 / Published: 3 January 2014
Expand Down Expand Up @@ -1193,7 +1193,7 @@
<em>Remote Sens.</em>
<b>2014</b>,
<em>6</em>(1), 521-539; doi:
<a href="http://dx.doi.org/10.3390/rs6010521">10.3390/rs6010521</a>
<a href="https://doi.org/10.3390/rs6010521">10.3390/rs6010521</a>
</div>
<div class="pubdates">
Received: 27 September 2013; in revised form: 13 December 2013 / Accepted: 23 December 2013 / Published: 3 January 2014
Expand Down Expand Up @@ -1238,7 +1238,7 @@
<em>Toxins</em>
<b>2014</b>,
<em>6</em>(1), 229-253; doi:
<a href="http://dx.doi.org/10.3390/toxins6010229">10.3390/toxins6010229</a>
<a href="https://doi.org/10.3390/toxins6010229">10.3390/toxins6010229</a>
</div>
<div class="pubdates">
Received: 11 November 2013; in revised form: 24 December 2013 / Accepted: 27 December 2013 / Published: 3 January 2014
Expand Down
2 changes: 1 addition & 1 deletion src/main/resources/org/contentmine/norma/pubstyle/hindawi/metadata.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -106,7 +106,7 @@
Volume 2014 (2014), Article ID 801626, 8 pages
<br></br>
// doi
<a href="http://dx.doi.org/10.1155/2014/801626">http://dx.doi.org/10.1155/2014/801626</a>
<a href="https://doi.org/10.1155/2014/801626">https://doi.org/10.1155/2014/801626</a>
</pre>
// article type
<div class="article_type">Research Article</div>
Expand Down
4 changes: 2 additions & 2 deletions src/main/resources/org/contentmine/norma/pubstyle/nlm/toHtml copy.xsl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@

<xsl:output method="xhtml"/>

<xsl:variable name="doiroot">https://dx.doi.org/</xsl:variable>
<xsl:variable name="doiroot">https://doi.org/</xsl:variable>
<xsl:variable name="nlmroot">http://www.ncbi.nlm.nih.gov/pubmed/</xsl:variable>
<xsl:variable name="lowercase" select="'abcdefghijklmnopqrstuvwxyz'" />
<xsl:variable name="uppercase" select="'ABCDEFGHIJKLMNOPQRSTUVWXYZ'" />
Expand Down Expand Up @@ -817,7 +817,7 @@
<xsl:template match="*[local-name()='fig']">
<div class="fig" title="fig">
<div class="figure" title="figure">
<a href="http://doi.org/{*[local-name()='object-id' and @pub-id-type='doi']}"><xsl:apply-templates select="*[local-name()='label']"/></a>
<a href="https://doi.org/{*[local-name()='object-id' and @pub-id-type='doi']}"><xsl:apply-templates select="*[local-name()='label']"/></a>
</div>
<caption class="caption" title="caption"><xsl:apply-templates select="*[local-name()='caption']"/></caption>
<!-- the <graphic> links to files we don't have -->
Expand Down
Loading