Look up PDFs on crossref.org in DevonThink

crossref-lookup.applescript

-- Look up document metadata on CrossRef.org in DevonThink 3
-- 
-- Currently sets:
-- * Created date to the document's publication date
-- * Title in document properties
-- * Author in document properties (first author only)
-- * Crossref DOI URL in document properties
-- * A tag for the type of document
-- * Finder comments to a formatted citation (see below)
-- 
--
-- To install:
-- 0. Quit DevonThink
-- 1. Place this script in the DevonThink Scripts folder (`Scripts -> Open Scripts Folder`)
-- 2. In Terminal, navigate to that folder and run `osacompile -o Crossref\ Lookup.scpt crossref-lookup.applescript; rm crossref-lookup.applescript`
-- 3. Install JSON Helper: https://apps.apple.com/au/app/json-helper-for-applescript/id453114608?mt=12
-- 4. Install exiftool: `brew install exiftool` (using homebrew; see https://brew.sh)
-- 5. Give the script a keyboard shortcut (`System Preferences -> Keyboard -> Shortcuts -> App Shortcuts`) (optional)
--
-- To use:
-- 0. Open a PDF in DevonThink
-- 1. Using your cursor, select a paper's title, ISSN, or similar identifying information
-- 2. Trigger the script (e.g., using they keyboard shortcut
-- 3. Select the best fitting candidate from the list
-- 4. Click `OK`
--
-- To set your citation format:
-- 0. Look up your desired format here: <https://github.com/citation-style-language/styles>
-- 1. Set CitationName below to the name of the apppopriate file *without* the `.csl` extension


set CitationName to "australian-guide-to-legal-citation"
set UAString to "XRefLookup/1.0 (https://gist.github.com/mnot/0d7825bde9b9d3233f623c71765f20ca; mailto:[email protected])"


tell application id "DNtp"
	try
		if not (exists think window 1) then error "No window open."
		if not (exists content record) then error "No document selected."
	on error error_message number error_number
		if the error_number is not -128 then display alert "DEVONthink" message error_message as warning
		return
	end try
	
	set theRecord to content record
	set query to the selected text of think window 1 as string
	if query is "" then
		set query to name of theRecord
	end if
	
	show progress indicator "Looking up references..." steps -1
	set theJson to my crossrefLookup(query)
	hide progress indicator
	
	-- Populate and display a dialogue
	try
		set theItems to |items| of message of theJson
		set theChoices to {}
		repeat with a from 1 to length of theItems
			set currentItem to item a of theItems
			set titleList to title of currentItem
			set title to item 1 of titleList
			set dateString to my extractDate(currentItem)
			set detailString to my extractAuthor(currentItem)
			if not detailString is equal to "" then
				set detailString to detailString & ", "
			end if
			set detailString to detailString & dateString
			set theChoice to title & " (" & detailString & ")"
			set end of theChoices to theChoice
		end repeat
	on error error_message number error_number
		if the error_number is not -128 then display alert "DEVONthink" message error_message as warning
		return
	end try
	
	set theChoice to choose from list theChoices with prompt "Select:"
	if theChoice is false then return
	
	repeat with a from 1 to length of theChoices
		set currentItem to item a of theChoices
		if currentItem as string is equal to theChoice as string then
			set chosenItem to item a of theItems
		end if
	end repeat
	
	-- update document
	set dateString to my extractDate(chosenItem)
	set dateStruct to my appleDate(dateString)
	
	try
		set recordPath to path of theRecord
		-- date
		set the date of theRecord to dateStruct
		-- tags
		set typeTag to |type| of chosenItem
		if typeTag is not in tags of theRecord then
			set tagList to tags of theRecord
			set end of tagList to typeTag
			set tags of theRecord to tagList
		end if
		-- url
		set uri to |URL| of chosenItem
		set the URL of theRecord to uri
		-- comment
		set citation to my lookupCitation(uri)
		set the comment of theRecord to citation
		-- title
		set recordTitle to item 1 of title of chosenItem
		my setPDFMetadata("Title", recordTitle, recordPath)
		-- author
		set authorString to my extractAuthor(chosenItem)
		my setPDFMetadata("Author", authorString, recordPath)
		
	on error error_message number error_number
		if the error_number is not -128 then display alert "DEVONthink" message error_message as warning
	end try
end tell

on crossrefLookup(query)
	set apiURL to "https://api.crossref.org/works"
	set shellScript to ("curl -A \"" & my UAString & "\" -G " & apiURL ¬
		& " --data-urlencode query.bibliographic=" & quoted form of query ¬
		& " -d rows=5 -d select=author,title,type,publisher,issued,subject,URL")
	set apiResult to (do shell script shellScript)
	
	-- parse json
	tell application "JSON Helper"
		set jsonResponse to read JSON from apiResult
	end tell
	
	if not status of jsonResponse is equal to "OK" then
		error "API response not OK: " & message of jsonResponse
		return
	end if
	return jsonResponse
end crossrefLookup

on extractDate(record_item)
	try
		set [iyear, imonth, iday] to item 1 of |date-parts| of issued of record_item
		set dateString to ((iday as string) & "-" & imonth as string) & "-" & iyear as string
	on error
		try
			set [iyear, imonth] to item 1 of |date-parts| of issued of record_item
			set dateString to "01-" & (imonth as string) & "-" & iyear as string
		on error
			try
				set iyear to item 1 of |date-parts| of issued of record_item
				set dateString to "01-01-" & iyear as string
			on error
				set dateString to ""
			end try
		end try
	end try
	return dateString
end extractDate

on appleDate(date_string)
	return date (date_string)
end appleDate

on extractAuthor(record_item)
	set firstAuthor to ""
	try
		set author_entries to author of record_item
	on error
		return ""
	end try
	repeat with a from 1 to length of author_entries
		set this_entry to item a of author_entries
		if sequence of this_entry is equal to "first" then
			set firstAuthor to this_entry
		end if
	end repeat
	if firstAuthor is equal to "" then
		return ""
	end if
	try
		set authorString to |given| of firstAuthor & " " & family of firstAuthor
	on error
		try
			set authorString to family of firstAuthor
		on error
			set authorString to |name| of firstAuthor
		end try
	end try
	return authorString
end extractAuthor

on setPDFMetadata(mdKey, mdValue, recordPath)
	set shellCommand to "/opt/homebrew/bin/exiftool -overwrite_original -" & mdKey & "=" & quoted form of mdValue & " " & quoted form of recordPath
	set exifresult to do shell script shellCommand
end setPDFMetadata

on lookupCitation(uri)
	set shellScript to ("curl -A \"" & my UAString & "\" " & ¬
		"-LH \"Accept: text/bibliography; style=" & my CitationName & "\" " & uri)
	set apiResult to (do shell script shellScript)
	return apiResult
end lookupCitation