Add documents_doi.csv to tabs_collection export

[Copilot]

Adds documents_doi.csv to tabs_collection.zip containing DOI/language pairs for each document. Each document can generate multiple rows (one per DOI/language pair).

Implementation

• publication/documents_doi.py: New dumper implementing xylose's doi_and_lang logic

  • Extracts DOI/language pairs from v337 field
  • Validates DOI format with regex and auto-corrects swapped lang/DOI values
  • Falls back to original_language() then languages()[0] for main DOI
  • Skips documents without DOI information

• publication/dumper.py: Integrated new dumper into main export loop

CSV Schema

"extraction date","study unit","collection","document publishing ID (PID SciELO)","document language","doi corresponding language"
"2026-02-04","document","scl","S0102-67202009000300001","pt","10.1590/S0102-67202009000300001"
"2026-02-04","document","scl","S0102-67202009000300001","en","10.1590/S0102-67202009000300002"

Key Logic

# Handles swapped values: checks if 'l' field contains DOI pattern
if len(DOI_REGEX.findall(lang)) == 1 and len(doi) == 2:
    lang, doi = doi, lang

Original prompt

---

This section details on the original issue you should resolve

<issue_title>Crie mais um csv para fazer parte do tabs_collection.zip: documents_doi.csv</issue_title>
<issue_description>Crie mais um csv para fazer parte do tabs_collection.zip: documents_doi.csv

Colunas:

• extraction date
• study unit
• collection
• document publishing ID (PID SciELO)
• document language
• doi corresponding language

# class Document
    @property
    def doi_and_lang(self):
        """
        This method retrieves the lang and DOI.
        """
        raw_doi = self.data.get('article', {}).get('v337')
        items = []
        for item in raw_doi or []:
            lang = item.get("l")
            doi = item.get("d")
            if lang and doi:
                if len(DOI_REGEX.findall(lang)) == 1 and len(doi) == 2:
                    lang, doi = doi, lang
                if len(DOI_REGEX.findall(doi)) == 1 and len(lang) == 2:
                    items.append((lang, doi))
        if self.doi:
            item = (self.original_language(), self.doi)
            if all(item) and item not in items:
                items.insert(0, item)
        return items

fonte: https://github.com/scieloorg/xylose/blob/573994f80705eb7f6d4928de69e079468172dda1/xylose/scielodocument.py#L2183C5-L2202C21
</issue_description>

Comments on the Issue (you are @copilot in this section)

• Fixes Crie mais um csv para fazer parte do tabs_collection.zip: documents_doi.csv #86

---

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.