XML/Input: Difference between revisions

# PEG to jq transcription is based on these equivalences:

# Sequence: e1 e2 e1 | e2

# Ordered choice: e1 / e2 e1 // e2

# Zero-or-more: e* star(E)

# One-or-more: e+ plus(E)

# Optional: e? optional(E)

# And-predicate: &e amp(E) # no input is consumed

# Not-predicate: !e neg(E) # no input is consumed

# The idea is to pass a JSON object {remainder:_, result:_ } through a

# pipeline, consuming the text in .remainder and building up .result.

def star(E): ((E | star(E)) // .) ;

def plus(E): E | (plus(E) // . );

def optional(E): (E // .);

def amp(E): . as $in | E | $in;

def neg(E): select( [E] == [] );

### Helper functions:

# Consume a regular expression rooted at the start of .remainder, or emit empty;

# on success, update .remainder and set .match but do NOT update .result

def consume($re):

# on failure, match yields empty

(.remainder | match("^" + $re)) as $match

| .remainder |= .[$match.length :]

| .match = $match.string;

def parse($re):

consume($re)

| .result = .result + [.match] ;

# consume the literal string $s

def q($s):

select(.remainder | startswith($s))

| .remainder |= .[$s | length :] ;

def literal($s):

q($s)

| .result += [$s];

# Tagging

def box(E):

((.result = null) | E) as $e

| .remainder = $e.remainder

| .result += [$e.result] # the magic sauce

;

def box(name; E):

((.result = null) | E) as $e

| .remainder = $e.remainder

| .result += [{(name): (try ($e.result|join("")) catch $e.result) }] # the magic sauce

;

def objectify(E):

box(E)

| .result[-1] |= {(.[0]): .[1:]} ;

def keyvalue(E):

box(E)

| .result[-1] |= {(.[0]): .[1]} ;

# optional whitespace

def ws: consume("[ \n\r\t]*");

def string_except($regex):

box(star(neg( parse($regex) ) | parse("."))) | .result[-1] |= add;

</syntaxhighlight>