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

Jump to bottom

improve smart-read backend with new mapping of defined formats, extensions, context and parsers #37

Merged
merged 5 commits into from
Feb 8, 2021
Merged

improve smart-read backend with new mapping of defined formats, extensions, context and parsers #37

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
bdbc183
rewrite of smart-read-backend; cleaner mapping of (ext > format) + co…
thackl Feb 6, 2021
e2dae32
manually read_seqs; added type.convert for parse_desc
thackl Feb 8, 2021
9f4ca1a
Fix context for links
iimog Feb 8, 2021
f6b965d
Fix column names for links from alitv
iimog Feb 8, 2021
415c501
Fix alitv example
iimog Feb 8, 2021
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
2 changes: 1 addition & 1 deletion NAMESPACE
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -94,6 +94,7 @@ export(as_sublinks)
export(bins)
export(check_strand)
export(combine_strands)
export(def_formats)
export(def_names)
export(def_types)
export(drop_feat_layout)
Expand All @@ -103,7 +104,6 @@ export(drop_seq_layout)
export(ex)
export(feats)
export(feats0)
export(file_formats)
export(flip)
export(flip_by_links)
export(flip_seqs)
Expand Down
41 changes: 19 additions & 22 deletions R/global.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,28 +3,25 @@
# manipulated by other packages.
gggenomes_global <- new.env(parent = emptyenv())

# list of contexts of dictionaryish vectors mapping suffixes to file formats
gggenomes_global$file_formats <- map(list(
feats = list(
gff3 = qc(gff, gff3),
gbk = qc(gbk, gb, gbff),
bed = qc(bed),
fasta = qc(fa, fas, fasta, ffn, fna, faa),
blast = qc(m8, o6, o7),
paf = qc(paf),
ambigious = qc(txt, tsv, csv)
),
seqs = list(
fai = qc(fai),
seq_len = qc(fa, fas, fasta, ffn, fna, faa, gff, gbk),
ambigious = qc(txt, tsv, csv)
),
zips = list(
bz2 = qc(bz, bz2),
gz = qc(gz),
xz = qc(xz),
zip = qc(zip))
), ~deframe(stack(.x) %>% mutate(ind=as.character(ind))))
# Mapping of file formats, extensions, contexts, and parsers
#
# parser is a function name, like "read_tsv", ...
#
# context=NA defines fallback parser that is used if no parser is defined for
# the specific context
gggenomes_global$def_formats <- tribble(
~format, ~ext, ~context, ~parser,
"ambigious", qc(txt,tsv,csv), NA, "read_ambigious",
"fasta", qc(fa,fas,fasta,ffn,fna,faa), qc(seqs), qc(read_seq_len),
"fai", qc(fai), qc(seqs), qc(read_fai),
"gff3", qc(gff,gff3), qc(feats, seqs), qc(read_gff3, read_seq_len),
"gbk", qc(gbk,gb,gbff,gpff), qc(feats, seqs), qc(read_gbk, read_seq_len),
"bed", qc(bed), "feats", "read_bed",
"blast", qc(m8,o6,o7), "feats", "read_blast",
"paf", qc(paf), "feats", "read_paf",
"alitv", qc(json), qc(feats, seqs, links),
qc(read_alitv_genes, read_alitv_seqs, read_alitv_links)
)

# Default column names for different formats
gggenomes_global$def_names <- list(
Expand Down
Loading