wader/fq
1
1
Fork 0
mirror of https://github.com/wader/fq.git synced 2024-11-23 09:56:07 +03:00
Code Issues Projects Releases Wiki Activity

Merge branch 'master' of https://github.com/wader/fq into avro

Browse Source
This commit is contained in:
Xentripetal 2022-02-12 22:16:50 -06:00
commit 9636613ec6
60 changed files with 976 additions and 559 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.github/workflows/ci.yml vendored
View File

@ -52,7 +52,7 @@ jobs:
- name: Setup go
uses: actions/setup-go@v2
with:
go-version: 1.17.6
go-version: 1.17.7
- name: Test
env:
GOARCH: ${{ matrix.goarch }}

2
.github/workflows/release.yml vendored
View File

@ -19,7 +19,7 @@ jobs:
- name: Setup go
uses: actions/setup-go@v2
with:
go-version: 1.17.6
go-version: 1.17.7
- name: Run goreleaser
uses: goreleaser/goreleaser-action@v2
with:

2
Dockerfile
View File

@ -1,5 +1,5 @@
# bump: docker-golang /FROM golang:([\d.]+)/ docker:golang|^1
FROM golang:1.17.6-bullseye AS base
FROM golang:1.17.7-bullseye AS base
# expect is used to test cli
RUN \

2
LICENSE
View File

@ -1,3 +1,5 @@
MIT License
Copyright (c) 2021 Mattias Wadman
colorjson fork and various code in gojqextra package Copyright (c) 2019-2021 itchyny

23
README.md
View File

@ -147,6 +147,14 @@ xattr -d com.apple.quarantine fq && spctl --add fq
brew install wader/tap/fq
```
### Windows
`fq` can be installed via [scoop](https://scoop.sh/).
```powershell
scoop install fq
```
### Arch Linux
`fq` can be installed from the [community repository](https://archlinux.org/packages/community/x86_64/fq/) using [pacman](https://wiki.archlinux.org/title/Pacman):
@ -228,3 +236,18 @@ for inventing the [jq](https://github.com/stedolan/jq) language.
- [GNU poke](https://www.jemarch.net/poke)
- [ffmpeg/ffprobe](https://ffmpeg.org)
- [hexdump](https://git.kernel.org/pub/scm/utils/util-linux/util-linux.git/tree/text-utils/hexdump.c)
## License
`fq` is distributed under the terms of the MIT License.
See the [LICENSE](LICENSE) file for license details.
Licenses of direct dependencies:
- Forked version of gojq https://github.com/itchyny/gojq/blob/main/LICENSE (MIT)
- Forked version of readline https://github.com/chzyer/readline/blob/master/LICENSE (MIT)
- gopacket https://github.com/google/gopacket/blob/master/LICENSE (BSD)
- mapstructure https://github.com/mitchellh/mapstructure/blob/master/LICENSE (MIT)
- go-difflib https://github.com/pmezard/go-difflib/blob/master/LICENSE (BSD)
- golang/x/text https://github.com/golang/text/blob/master/LICENSE (BSD)

3
dev/snippets.jq
View File

@ -41,7 +41,8 @@ def urldecode:
# ex: .frames | changes(.header.sample_rate)
def changes(f): streaks_by(f)[].[0];
def radix62sp: radix(62; "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"; {
def toradix62sp: toradix(62; "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ");
def fromradix62sp: fromradix(62; {
"0": 0, "1": 1, "2": 2, "3": 3,"4": 4, "5": 5, "6": 6, "7": 7, "8": 8, "9": 9,
"a": 10, "b": 11, "c": 12, "d": 13, "e": 14, "f": 15, "g": 16,
"h": 17, "i": 18, "j": 19, "k": 20, "l": 21, "m": 22, "n": 23,

6
doc/TODO.md
View File

@ -1,8 +1,7 @@
### Known bugs to fix
- `fq -n '"aabbccdd" | hex | tobytes[1:] | raw | tobytes'` create buffer `aabbcc` should be `bbccdd`. I think decode (raw in this case) is confused by root value buffer.
- Buffers/string duality is confusing, most string functions should be wrapped to understand buffers.
- `fq -n '[([0xab] | tobits[:4]), ([0xdc] | tobits[:4]), 0] | tobytes'` should create a `ad` buffer, now `a0`. Probably because use of `io.Copy` that will ends up padding on byte boundaries. Should use `bitio.Copy` and create a `bitio.Writer` that can transform to a `io.Writer`.
- `fq -n '"aabbccdd" | hex | tobytes[1:] | raw | tobytes'` create binary `aabbcc` should be `bbccdd`. I think decode (raw in this case) is confused by root value buffer.
- Buffers/string duality is confusing, most string functions should be wrapped to understand binary.
- REPL cancel seems to sometimes exit a sub-REPl without properly cleanup options.
- Value errors, can only be accessed with `._error`.
- Framed (add unknown in gaps) decode should be on struct level not format?
@ -14,6 +13,7 @@
- Rework cli/repl user interrupt (context cancel via ctrl-c), see comment in Interp.Main
- Optimize `Interp.Options` calls, now called per display. Cache per eval? needs to handle nested evals.
- `<array decode value>[{start: ...: end: ...}]` syntax a bit broken.
- REPL completion might have side effcts. Make interp.Function type know and wrap somehow? input, inputs, open, ...
### TODO and ideas

127
doc/dev.md
View File

@ -32,6 +32,133 @@ Flags can be struct with bit-fields.
- Can new formats be added to other formats
- Does the new format include existing formats
### Decoder API
Readers use this convention `d.<Field>?<reader<length>?>|<type>Fn>(... [,scalar.Mapper...])`:
- If starts with `Field` a field will be added and first argument will be name of field. If not it will just read.
- `<reader<length>?>|<type>Fn>` a reader or a reader function
- `<reader<length>?>` reader such as `U16` (unsigned 16 bit) or `UTF8` (utf8 and length as argument). Read bits using some decoder.
- `<type>Fn>` read using a `func(d *decode.D) <type>` function.
- This can be used to implement own custom readers.
All `Field` functions takes a var args of `scalar.Mapper`:s that will be applied after reading.
`<type>` are these go types and their name in the API:
- `uint64` known as `U` (unsigned number)
- `int64` known as `S` (singed number)
- `float64` known as `F`
- `string` known as `Str`
- `bool` known as `Bool`,
- `*big.Int` known as `BigInt`
- `nil` null value known as `Nil`.
TODO: there are some more (BitBuf etc, should be renamed)
To add a struct or array use `d.FieldStruct(...)` and `d.FieldArray(...)`.
For example this decoder:
```go
d.FieldUTF8("magic", 4) // read 4 byte UTF8 string and add it as "magic"
d.FieldStruct("headers", func(d *decode.D) { // create a new struct and add it as "headers"
d.FieldU8("type", scalar.UToSymStr{ // read 8 bit unsigned integer, map it and add it as "type
1: "start",
// ...
})
})
```
will produce something like this:
```go
*decode.Value{
Parent: nil,
V: *decode.Compound{
IsArray: false, // is struct
Children: []*decode.Value{
*decode.Value{
Name: "magic",
V: scalar.S{
Actual: "abcd", // read and set by UTF8 reader
},
},
*decode.Value{
Parent: &... // ref parent *decode.Value>,
Name: "headers",
V: *decode.Compound{
IsArray: false, // is struct
Children: []*decode.Value{
*decode.Value{
Name: "type",
V: scalar.S{
Actual: uint64(1), // read and set by U8 reader
Sym: "start", // set by UToSymStr scalar.Mapper
},
},
},
},
},
},
},
}
```
and will look like this in jq/JSON:
```json
{
"magic": "abcd",
"headers": {
"type": "start"
}
}
```
#### *decode.D
This is the main type used during decoding. It keeps track of:
- A current array or struct `*decode.Value` where fields will be added to.
- Current bit reader
- Decode options
- Default endian
New `*decode.D` are created during decoding when `d.FieldStruct` etc is used. It is also a kitchen sink of all kind functions for reading various standard number and string encodings etc.
Decoder authors do not have to create them.
#### decode.Value
Is what `*decode.D` produce and it used to represent the decoded structure, can be array, struct, number, string etc. It is the underlaying type used by `interp.DecodeValue` that implements `gojq.JQValue` to expose it as various jq types.
It stores:
- Parent `*decode.Value` unless it's a root.
- A decoded value, a `scalar.S` or `*decode.Compound` (struct or array)
- Name in parent struct or array. If parent is a struct the name is unique.
- Index in parent array. Not used if parent is a struct.
- A bit range. Also struct and array have a range that is the min/max range of its children.
- A bit reader where the bit range can be read from.
Decoder authors will probably not have to create them.
#### scalar.S
Keeps track of
- Actual value. Decoded value represented using a go type like `uint64`, `string` etc. For example a value reader by a utf8 or utf16 reader both will ends up as a `string`.
- Symbolic value. Optional symbolic representation of the actual value. For example a `scalar.UToSymStr` would map an actual `uint64` to a symbolic `string`.
- String description of the value.
- Number representation
The `scalar` package has `scalar.Mapper` implementations for all types to map actual to whole `scalar.S` value `scalar.<type>ToScalar` or to just to set symbolic value `scalar.<type>ToSym<type>`. There is also mappers to just set values or to change number representations `scalar.Hex`/`scalar.SymHex` etc.
Decoder authors will probably not have to create them. But you might implement your own `scalar.Mapper` to modify them.
#### *decode.Compound
Used to store struct or array of `*decode.Value`.
Decoder authors do not have to create them.
### Development tips
I ususally use `-d <format>` and `dv` while developing, that way you will get a decode tree

135
doc/usage.md
View File

@ -73,7 +73,7 @@ Default if not explicitly used `display` will only show the root level:
![fq demo](display_decode_value.svg)
First row shows ruler with byte offset into the line and JSON path for the value.
First row shows ruler with byte offset into the line and jq path for the value.
The columns are:
- Start address for the line. For example we see that `type` starts at `0xd60`+`0x09`.
@ -109,7 +109,7 @@ There are also some other `display` aliases:
The interactive [REPL](https://en.wikipedia.org/wiki/Read%E2%80%93eval%E2%80%93print_loop)
has auto completion and nested REPL support:
```sh
```
# start REPL with null input
$ fq -i
null>
@ -196,7 +196,7 @@ fq -n 'def f: .. | select(format=="avc_sps"); diff(input|f; input|f)' a.mp4 b.mp
#### Extract first JPEG found in file
Recursively look for first value that is a `jpeg` decode value root. Use `tobytes` to get bytes buffer for value. Redirect bytes to a file.
Recursively look for first value that is a `jpeg` decode value root. Use `tobytes` to get bytes for value. Redirect bytes to a file.
```sh
fq 'first(.. | select(format=="jpeg")) | tobytes' file > file.jpeg
@ -269,6 +269,85 @@ single argument `1, 2` (a lambda expression that output `1` and then output `2`)
achieved.
- Expressions have one implicit input and output value. This how pipelines like `1 | . * 2` work.
## Types specific to fq
fq has two additional types compared to jq, decode value and binary. In standard jq expressions they will in most case behave as some standard jq type.
### Decode value
This type is returned by decoders and it used to represent parts of the decoed input. It can act as all standard jq types, object, array, number, string etc.
Each decode value has these properties:
- A bit range in the input
- Can be accessed as a binary using `tobits`/`tobytes`. Use the `start` and `size` keys to postion and size.
- `.name` as bytes `.name | tobytes`
- Bit 4-8 of `.name` as bits `.name | tobits[4:8]`
Each non-compound decode value has these properties:
- An actual value:
- This is the decoded representation of the bits, a number, string, bool etc.
- Can be accessed using `toactual`.
- An optional symbolic value:
- Is usually a mapping of the actual to symbolic value, ex: map number to a string value.
- Can be accessed using `tosym`.
- An optional description:
- Can be accessed using `todescription`
- `parent` is the parent decode value
- `parents` is the all parent decode values
- `topath` is the jq path for the decode value
- `torepr` convert decode value to its representation if possible
The value of a decode value is the symbolic value if available and otherwise the actual value. To explicitly access the value use `tovalue`. In most expression this is not needed as it will be done automactically.
### Binary
Binaries are raw bits with a unit size, 1 (bits) or 8 (bytes), that can have a non-byte aligned size. Will act as byte padded strings in standard jq expressions.
Use `tobits` and `tobytes` to create them from a decode values, strings, numbers or binary arrays. `tobytes` will if needed zero pad most significant bits to be byte aligned.
There is also `tobitsrange` and `tobytesrange` which does the same thing but will preserve it's source range when displayed.
- `"string" | tobytes` produces a binary with UTF8 codepoint bytes.
- `1234 | tobits` produces a binary with the unsigned big-endian integer 1234 with enough bits to represent the number. Use `tobytes` to get the same but with enough bytes to represent the number. This is different to how numbers works inside binary arrays where they are limited to 0-255.
- `["abc", 123, ...] | tobytes` produce a binary from a binary array. See [binary array](#binary-array) below.
- `.[index]` access bit or byte at index `index`. Index is in units.
- `[0x12, 0x34, 0x56] | tobytes[1]` is `0x35`
- `[0x12, 0x34, 0x56] | tobits[3]` is `1`
- `.[start:]`, `.[start:end]` or `.[:end]` is normal jq slice syntax and will slice the binary from `start` to `end`. `start` and `end` is in units.
- `[0x12, 0x34, 0x56] | tobytes[1:2]` will be a binary with the byte `0x34`
- `[0x12, 0x34, 0x56] | tobits[4:12]` will be a binary with the byte `0x23`
- `[0x12, 0x34, 0x56] | tobits[4:20]` will be a binary with the byte `0x23`, `0x45`
- `[0x12, 0x34, 0x56] | tobits[4:20] | tobytes[1:]` will be a binary with the byte `0x45`,
Both `.[index]` and `.[start:end]` support negative indices to index from end.
TODO: tobytesrange, padding
#### Binary array
Is an array of numbers, strings, binaries or other nested binary arrays. When used as input to `tobits`/`tobytes` the following rules are used:
- Number is a byte with value be 0-255
- String it's UTF8 codepoint bytes
- Binary as is
- Binary array used recursively
Binary arrays are similar to and inspired by [Erlang iolist](https://www.erlang.org/doc/man/erlang.html#type-iolist).
Some examples:
`[0, 123, 255] | tobytes` will be binary with 3 bytes 0, 123 and 255
`[0, [123, 255]] | tobytes` same as above
`[0, 1, 1, 0, 0, 1, 1, 0 | tobits]` will be binary with 1 byte, 0x66 an "f"
`[(.a | tobytes[-10:]), 255, (.b | tobits[:10])] | tobytes` the concatenation of the last 10 bytes of `.a`, a byte with value 255 and the first 10 bits of `.b`.
The difference between `tobits` and `tobytes` is
TODO: padding and alignment
## Functions
- All standard library functions from jq
@ -297,32 +376,32 @@ unary uses input and if more than one argument all as arguments ignoring the inp
- `todescription` description of value
- `torepr` convert decode value into what it reptresents. For example convert msgpack decode value
into a value representing its JSON representation.
- All regexp functions work with buffers as input and pattern argument with these differences
from the string versions:
- All regexp functions work with binary as input and pattern argument with these differences
compared to when using string input:
- All offset and length will be in bytes.
- For `capture` the `.string` value is a buffer.
- If pattern is a buffer it will be matched literally and not as a regexp.
- If pattern is a buffer or flags include "b" each input byte will be read as separate code points
- `scan_toend($v)`, `scan_toend($v; $flags)` works the same as `scan` but output buffer are from start of match to
end of buffer.
- For `capture` the `.string` value is a binary.
- If pattern is a binary it will be matched literally and not as a regexp.
- If pattern is a binary or flags include "b" each input byte will be read as separate code points
- `scan_toend($v)`, `scan_toend($v; $flags)` works the same as `scan` but output binary are from start of match to
end of binary.
instead of possibly multi-byte UTF-8 codepoints. This allows to match raw bytes. Ex: `match("\u00ff"; "b")`
will match the byte `0xff` and not the UTF-8 encoded codepoint for 255, `match("[^\u00ff]"; "b")` will match
all non-`0xff` bytes.
- `grep` functions take 1 or 2 arguments. First is a scalar to match, where a string is
treated as a regexp. A buffer scalar will be matches exact bytes. Second argument are regexp
flags with addition that "b" will treat each byte in the input buffer as a code point, this
treated as a regexp. A binary will be matches exact bytes. Second argument are regexp
flags with addition that "b" will treat each byte in the input binary as a code point, this
makes it possible to match exact bytes.
- `grep($v)`, `grep($v; $flags)` recursively match value and buffer
- `grep($v)`, `grep($v; $flags)` recursively match value and binary
- `vgrep($v)`, `vgrep($v; $flags)` recursively match value
- `bgrep($v)`, `bgrep($v; $flags)` recursively match buffer
- `bgrep($v)`, `bgrep($v; $flags)` recursively match binary
- `fgrep($v)`, `fgrep($v; $flags)` recursively match field name
- `grep_by(f)` recursively match using a filter. Ex: `grep_by(. > 180 and . < 200)`, `first(grep_by(format == "id3v2"))`.
- Buffers:
- `tobits` - Transform input into a bits buffer not preserving source range, will start at zero.
- `tobitsrange` - Transform input into a bits buffer preserving source range if possible.
- `tobytes` - Transform input into a bytes buffer not preserving source range, will start at zero.
- `tobytesrange` - Transform input into a byte buffer preserving source range if possible.
- `buffer[start:end]`, `buffer[:end]`, `buffer[start:]` - Create a sub buffer from start to end in buffer units preserving source range.
- Binary:
- `tobits` - Transform input to binary with bit as unit, does not preserving source range, will start at zero.
- `tobitsrange` - Transform input to binary with bit as unit, preserves source range if possible.
- `tobytes` - Transform input to binary with byte as unit, does not preserving source range, will start at zero.
- `tobytesrange` - Transform input binary with byte as unit, preserves source range if possible.
- `.[start:end]`, `.[:end]`, `.[start:]` - Slice binary from start to end preserving source range.
- `open` open file for reading
- All decode function takes a optional option argument. The only option currently is `force` to ignore decoder asserts.
For example to decode as mp3 and ignore assets do `mp3({force: true})` or `decode("mp3"; {force: true})`, from command line
@ -330,15 +409,17 @@ you currently have to do `fq -d raw 'mp3({force: true})' file`.
- `decode`, `decode($format)`, `decode($format; $opts)` decode format
- `probe`, `probe($opts)` probe and decode format
- `mp3`, `mp3($opts)`, ..., `<name>`, `<name>($opts)` same as `decode(<name>)($opts)`, `decode($format; $opts)` decode as format
- Display shows hexdump/ASCII/tree for decode values and JSON for other values.
- `d`/`d($opts)` display value and truncate long arrays and buffers
- Display shows hexdump/ASCII/tree for decode values and jq value for other types.
- `d`/`d($opts)` display value and truncate long arrays and binaries
- `da`/`da($opts)` display value and don't truncate arrays
- `dd`/`dd($opts)` display value and don't truncate arrays or buffers
- `dv`/`dv($opts)` verbosely display value and don't truncate arrays but truncate buffers
- `ddv`/`ddv($opts)` verbosely display value and don't truncate arrays or buffers
- `dd`/`dd($opts)` display value and don't truncate arrays or binaries
- `dv`/`dv($opts)` verbosely display value and don't truncate arrays but truncate binaries
- `ddv`/`ddv($opts)` verbosely display value and don't truncate arrays or binaries
- `p`/`preview` show preview of field tree
- `hd`/`hexdump` hexdump value
- `repl` nested REPL, must be last in a pipeline. `1 | repl`, can "slurp" outputs `1, 2, 3 | repl`.
- `paste` read string from stdin until ^D. Useful for pasting text.
- Ex: `paste | frompem | asn1_ber | repl` read from stdin then decode and start a new sub-REPL with result.
## Color and unicode output
@ -397,10 +478,6 @@ A value has these special keys (TODO: remove, are internal)
- TODO: unknown gaps
## Binary and IO lists
- TODO: similar to erlang io lists, [], binary, string (utf8) and numbers
## Own decoders and use as library
TODO

19
format/fuzz_test.go
View File

@ -15,6 +15,7 @@ import (
_ "github.com/wader/fq/format/all"
"github.com/wader/fq/format/registry"
"github.com/wader/fq/pkg/decode"
"github.com/wader/fq/pkg/interp"
)
@ -26,6 +27,7 @@ func (fuzzFS) Open(name string) (fs.File, error) {
type fuzzTest struct {
b []byte
f decode.Format
}
type fuzzTestInput struct {
@ -47,22 +49,22 @@ func (ft *fuzzTest) Platform() interp.Platform { return interp.Platform{} }
func (ft *fuzzTest) Stdin() interp.Input {
return fuzzTestInput{FileReader: interp.FileReader{R: bytes.NewBuffer(ft.b)}}
}
func (ft *fuzzTest) Stdout() interp.Output { return fuzzTestOutput{os.Stdout} }
func (ft *fuzzTest) Stderr() interp.Output { return fuzzTestOutput{os.Stderr} }
func (ft *fuzzTest) Stdout() interp.Output { return fuzzTestOutput{ioutil.Discard} }
func (ft *fuzzTest) Stderr() interp.Output { return fuzzTestOutput{ioutil.Discard} }
func (ft *fuzzTest) InterruptChan() chan struct{} { return nil }
func (ft *fuzzTest) Environ() []string { return nil }
func (ft *fuzzTest) Args() []string {
return []string{
`fq`,
`-d`, `raw`,
`(_registry.groups | keys[] | select(. != "all")) as $f | decode($f)?`,
`-d`, ft.f.Name,
`.`,
}
}
func (ft *fuzzTest) ConfigDir() (string, error) { return "/config", nil }
func (ft *fuzzTest) FS() fs.FS { return fuzzFS{} }
func (ft *fuzzTest) History() ([]string, error) { return nil, nil }
func (ft *fuzzTest) Readline(prompt string, complete func(line string, pos int) (newLine []string, shared int)) (string, error) {
func (ft *fuzzTest) Readline(opts interp.ReadlineOpts) (string, error) {
return "", io.EOF
}
@ -92,8 +94,11 @@ func FuzzFormats(f *testing.F) {
return nil
})
gi := 0
g := registry.Default.MustAll()
f.Fuzz(func(t *testing.T, b []byte) {
fz := &fuzzTest{b: b}
fz := &fuzzTest{b: b, f: g[gi]}
q, err := interp.New(fz, registry.Default)
if err != nil {
t.Fatal(err)
@ -104,5 +109,7 @@ func FuzzFormats(f *testing.F) {
// // TODO: expect error
// t.Fatal(err)
// }
gi = (gi + 1) % len(g)
})
}

2
format/mpeg/mpeg_spu.go
View File

@ -168,6 +168,8 @@ func spuDecode(d *decode.D, in interface{}) interface{} {
size := d.FieldU16("size")
// TODO
d.FieldRawLen("data", int64(size)*8)
default:
d.Fatalf("unknown command %d", cmd)
}
})
}

2
go.mod
View File

@ -23,7 +23,7 @@ require (
require (
// fork of github.com/itchyny/gojq, see github.com/wader/gojq fq branch
github.com/wader/gojq v0.12.1-0.20220108235115-6a05b6c59ace
github.com/wader/gojq v0.12.1-0.20220212115358-b98ce15ac16e
// fork of github.com/chzyer/readline, see github.com/wader/readline fq branch
github.com/wader/readline v0.0.0-20220117233529-692d84ca36e2
)

4
go.sum
View File

@ -11,8 +11,8 @@ github.com/mitchellh/mapstructure v1.4.3 h1:OVowDSCllw/YjdLkam3/sm7wEtOy59d8ndGg
github.com/mitchellh/mapstructure v1.4.3/go.mod h1:bFUtVrKA4DC2yAKiSyO/QUcy7e+RRV2QTWOzhPopBRo=
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
github.com/wader/gojq v0.12.1-0.20220108235115-6a05b6c59ace h1:pt07NaC7OhePrQVRKRxZy9umeWkjr28AmbtQC9CrtVQ=
github.com/wader/gojq v0.12.1-0.20220108235115-6a05b6c59ace/go.mod h1:tdC5h6dXdwAJs7eJUw4681AzsgfOSBrAV+cZzEbCZs4=
github.com/wader/gojq v0.12.1-0.20220212115358-b98ce15ac16e h1:gDujpnVkZWYgHVrNbN3FikM2Khp+n/J9NsLEQhl3IFc=
github.com/wader/gojq v0.12.1-0.20220212115358-b98ce15ac16e/go.mod h1:tdC5h6dXdwAJs7eJUw4681AzsgfOSBrAV+cZzEbCZs4=
github.com/wader/readline v0.0.0-20220117233529-692d84ca36e2 h1:AK4wt6mSypGEVAzUcCfrJqVD5hju+w81b9J/k0swV/8=
github.com/wader/readline v0.0.0-20220117233529-692d84ca36e2/go.mod h1:TJUJCkylZhI0Z07t2Nw6l6Ck7NiZqUpnMlkjEzN7+yM=
golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=

58
internal/bitioextra/zeroreadatseeker.go Normal file
View File

@ -0,0 +1,58 @@
package bitioextra
import (
"io"
"github.com/wader/fq/pkg/bitio"
)
type ZeroReadAtSeeker struct {
pos int64
nBits int64
}
func NewZeroAtSeeker(nBits int64) *ZeroReadAtSeeker {
return &ZeroReadAtSeeker{nBits: nBits}
}
func (z *ZeroReadAtSeeker) SeekBits(bitOffset int64, whence int) (int64, error) {
p := z.pos
switch whence {
case io.SeekStart:
p = bitOffset
case io.SeekCurrent:
p += bitOffset
case io.SeekEnd:
p = z.nBits + bitOffset
default:
panic("unknown whence")
}
if p < 0 || p > z.nBits {
return z.pos, bitio.ErrOffset
}
z.pos = p
return p, nil
}
func (z *ZeroReadAtSeeker) ReadBitsAt(p []byte, nBits int64, bitOff int64) (n int64, err error) {
if bitOff < 0 || bitOff > z.nBits {
return 0, bitio.ErrOffset
}
if bitOff == z.nBits {
return 0, io.EOF
}
lBits := z.nBits - bitOff
rBits := nBits
if rBits > lBits {
rBits = lBits
}
rBytes := bitio.BitsByteCount(rBits)
for i := int64(0); i < rBytes; i++ {
p[i] = 0
}
return rBits, nil
}

6
internal/script/script.go
View File

@ -149,8 +149,8 @@ func (cr *CaseRun) ConfigDir() (string, error) { return "/config", nil }
func (cr *CaseRun) FS() fs.FS { return cr.Case }
func (cr *CaseRun) Readline(prompt string, complete func(line string, pos int) (newLine []string, shared int)) (string, error) {
cr.ActualStdoutBuf.WriteString(prompt)
func (cr *CaseRun) Readline(opts interp.ReadlineOpts) (string, error) {
cr.ActualStdoutBuf.WriteString(opts.Prompt)
if cr.ReadlinesPos >= len(cr.Readlines) {
return "", io.EOF
}
@ -165,7 +165,7 @@ func (cr *CaseRun) Readline(prompt string, complete func(line string, pos int) (
cr.ActualStdoutBuf.WriteString(lineRaw + "\n")
l := len(line) - 1
newLine, shared := complete(line[0:l], l)
newLine, shared := opts.CompleteFn(line[0:l], l)
// TODO: shared
_ = shared
for _, nl := range newLine {

18
pkg/bitio/README.md
View File

@ -1,18 +0,0 @@
The bitio package tries to mimic the standard library packages io and bytes as much as possible.
- bitio.Buffer same as bytes.Buffer
- bitio.IOBitReadSeeker is a bitio.ReaderAtSeeker that from a io.ReadSeeker
- bitio.IOBitWriter a bitio.BitWriter that write bytes to a io.Writer, use Flush() to write possible unaligned byte
- bitio.IOReader is a io.Reader that reads bytes from a bit reader, will zero pad on unaligned byte eof
- bitio.IOReadSeeker is a io.ReadSeeker that read/seek bytes in a bit stream, will zero pad on unaligned - bitio.NewBitReader same as bytes.NewReader
- bitio.LimitReader same as io.LimitReader
- bitio.MultiReader same as io.MultiReader
- bitio.SectionReader same as io.SectionReader
- bitio.Copy* same as io.Copy*
- bitio.ReadFull same as io.ReadFull
TODO:
- bitio.IOBitReader bitio.Reader that reads from a io.Reader
- bitio.IOBitWriteSeeker bitio.BitWriteSeeker that writes to a io.WriteSeeker
- bitio.CopyN
- speed up read by using a cache somehow ([]byte or just a uint64?)

43
pkg/bitio/bitio.go
View File

@ -8,40 +8,43 @@ import (
"strings"
)
// ErrOffset means seek positions is invalid
var ErrOffset = errors.New("invalid seek offset")
// ErrNegativeNBits means read tried to read negative number of bits
var ErrNegativeNBits = errors.New("negative number of bits")
// Reader is something that reads bits
// Similar to io.Reader
// Reader is something that reads bits.
// Similar to io.Reader.
type Reader interface {
ReadBits(p []byte, nBits int64) (n int64, err error)
}
// Writer is something that writs bits
// Similar to io.Writer
// Writer is something that writs bits.
// Similar to io.Writer.
type Writer interface {
WriteBits(p []byte, nBits int64) (n int64, err error)
}
// Seeker is something that seeks bits
// Similar to io.Seeker
// Similar to io.Seeker.
type Seeker interface {
SeekBits(bitOffset int64, whence int) (int64, error)
}
// ReaderAt is something that reads bits at an offset
// Similar to io.ReaderAt
// ReaderAt is something that reads bits at an offset.
// Similar to io.ReaderAt.
type ReaderAt interface {
ReadBitsAt(p []byte, nBits int64, bitOff int64) (n int64, err error)
}
// ReadSeeker is bitio.Reader and bitio.Seeker
// ReadSeeker is bitio.Reader and bitio.Seeker.
type ReadSeeker interface {
Reader
Seeker
}
// ReadAtSeeker is bitio.ReaderAt and bitio.Seeker
// ReadAtSeeker is bitio.ReaderAt and bitio.Seeker.
type ReadAtSeeker interface {
ReaderAt
Seeker
@ -54,9 +57,9 @@ type ReaderAtSeeker interface {
Seeker
}
// NewBitReader reader reading nBits bits from a []byte
// NewBitReader reader reading nBits bits from a []byte.
// If nBits is -1 all bits will be used.
// Similar to bytes.NewReader
// Similar to bytes.NewReader.
func NewBitReader(buf []byte, nBits int64) *SectionReader {
if nBits < 0 {
nBits = int64(len(buf)) * 8
@ -68,7 +71,7 @@ func NewBitReader(buf []byte, nBits int64) *SectionReader {
)
}
// BitsByteCount returns smallest amount of bytes to fit nBits bits
// BitsByteCount returns smallest amount of bytes to fit nBits bits.
func BitsByteCount(nBits int64) int64 {
n := nBits / 8
if nBits%8 != 0 {
@ -77,7 +80,7 @@ func BitsByteCount(nBits int64) int64 {
return n
}
// BytesFromBitString []byte from bit string, ex: "0101" -> ([]byte{0x50}, 4)
// BytesFromBitString from []byte to bit string, ex: "0101" -> ([]byte{0x50}, 4)
func BytesFromBitString(s string) ([]byte, int64) {
r := len(s) % 8
bufLen := len(s) / 8
@ -97,7 +100,7 @@ func BytesFromBitString(s string) ([]byte, int64) {
return buf, int64(len(s))
}
// BitStringFromBytes string from []byte], ex: ([]byte{0x50}, 4) -> "0101"
// BitStringFromBytes from string to []byte, ex: ([]byte{0x50}, 4) -> "0101"
func BitStringFromBytes(buf []byte, nBits int64) string {
sb := &strings.Builder{}
for i := int64(0); i < nBits; i++ {
@ -110,8 +113,8 @@ func BitStringFromBytes(buf []byte, nBits int64) string {
return sb.String()
}
// CopyBuffer bits from src to dst using provided buffer
// Similar to io.CopyBuffer
// CopyBuffer bits from src to dst using provided byte buffer.
// Similar to io.CopyBuffer.
func CopyBuffer(dst Writer, src Reader, buf []byte) (n int64, err error) {
// same default size as io.Copy
if buf == nil {
@ -144,8 +147,8 @@ func CopyBuffer(dst Writer, src Reader, buf []byte) (n int64, err error) {
return written, err
}
// Copy bits from src to dst
// Similar to io.Copy
// Copy bits from src to dst.
// Similar to io.Copy.
func Copy(dst Writer, src Reader) (n int64, err error) {
return CopyBuffer(dst, src, nil)
}
@ -214,12 +217,16 @@ func readFull(p []byte, nBits int64, bitOff int64, fn func(p []byte, nBits int64
return nBits, nil
}
// ReadAtFull expects to read nBits from r at bitOff.
// Similar to io.ReadFull.
func ReadAtFull(r ReaderAt, p []byte, nBits int64, bitOff int64) (int64, error) {
return readFull(p, nBits, bitOff, func(p []byte, nBits int64, bitOff int64) (int64, error) {
return r.ReadBitsAt(p, nBits, bitOff)
})
}
// ReadFull expects to read nBits from r.
// Similar to io.ReadFull.
func ReadFull(r Reader, p []byte, nBits int64) (int64, error) {
return readFull(p, nBits, 0, func(p []byte, nBits int64, bitOff int64) (int64, error) {
return r.ReadBits(p, nBits)

4
pkg/bitio/buffer.go
View File

@ -6,8 +6,8 @@ import (
"io"
)
// Buffer is a bitio.Reader and bitio.Writer providing a bit buffer
// Similar to bytes.Buffer
// Buffer is a bitio.Reader and bitio.Writer providing a bit buffer.
// Similar to bytes.Buffer.
type Buffer struct {
buf []byte
bufBits int64

34
pkg/bitio/doc.go Normal file
View File

@ -0,0 +1,34 @@
// Package bitio tries to mimic the standard library packages io and bytes but for bits.
//
// - bitio.Buffer same as bytes.Buffer
//
// - bitio.IOBitReadSeeker is a bitio.ReaderAtSeeker that reads from a io.ReadSeeker
//
// - bitio.IOBitWriter a bitio.BitWriter that writes to a io.Writer, use Flush() to write possible zero padded unaligned byte
//
// - bitio.IOReader is a io.Reader that reads bytes from a bitio.Reader, will zero pad unaligned byte at EOF
//
// - bitio.IOReadSeeker is a io.ReadSeeker that reads from a bitio.ReadSeeker, will zero pad unaligned byte at EOF
//
// - bitio.NewBitReader same as bytes.NewReader
//
// - bitio.LimitReader same as io.LimitReader
//
// - bitio.MultiReader same as io.MultiReader
//
// - bitio.SectionReader same as io.SectionReader
//
// - bitio.Copy* same as io.Copy*
//
// - bitio.ReadFull same as io.ReadFull
//
// TODO:
//
// - bitio.IOBitReader bitio.Reader that reads from a io.Reader
//
// - bitio.IOBitWriteSeeker bitio.BitWriteSeeker that writes to a io.WriteSeeker
//
// - bitio.CopyN
//
// - Speed up read by using a cache somehow ([]byte or just a uint64?)
package bitio

3
pkg/bitio/iobitreadseeker.go
View File

@ -5,13 +5,14 @@ import (
"io"
)
// IOBitReadSeeker is a bitio.BitReadAtSeeker reading from a io.ReadSeeker
// IOBitReadSeeker is a bitio.ReadAtSeeker reading from a io.ReadSeeker.
type IOBitReadSeeker struct {
bitPos int64
rs io.ReadSeeker
buf []byte
}
// NewIOBitReadSeeker returns a new bitio.IOBitReadSeeker
func NewIOBitReadSeeker(rs io.ReadSeeker) *IOBitReadSeeker {
return &IOBitReadSeeker{
bitPos: 0,

4
pkg/bitio/iobitwriter.go
View File

@ -4,14 +4,14 @@ import (
"io"
)
// IOBitWriter is a bitio.BitWriter that writes to a io.Writer
// IOBitWriter is a bitio.Writer that writes to a io.Writer.
// Use Flush to write possible unaligned byte zero bit padded.
type IOBitWriter struct {
w io.Writer
b Buffer
}
// NewIOBitWriter returns a new bitio.IOBitWriter
// NewIOBitWriter returns a new bitio.IOBitWriter.
func NewIOBitWriter(w io.Writer) *IOBitWriter {
return &IOBitWriter{w: w}
}

10
pkg/bitio/ioreader.go
View File

@ -5,15 +5,15 @@ import (
"io"
)
// IOReader is a io.Reader and io.ByteReader that reads from a bitio.Reader
// Unaligned byte at EOF will be zero bit padded
// IOReader is a io.Reader and io.ByteReader that reads from a bitio.Reader.
// Unaligned byte at EOF will be zero bit padded.
type IOReader struct {
r Reader
rErr error
b Buffer
}
// NewIOReader returns a new bitio.IOReader
// NewIOReader returns a new bitio.IOReader.
func NewIOReader(r Reader) *IOReader {
return &IOReader{r: r}
}
@ -22,8 +22,6 @@ func (r *IOReader) Read(p []byte) (n int, err error) {
var ns int64
for {
var err error
// uses p even if returning nothing, io.Reader docs says:
// "it may use all of p as scratch space during the call"
if r.rErr == nil {
@ -62,7 +60,7 @@ func (r *IOReader) Read(p []byte) (n int, err error) {
if err != nil {
return 0, err
}
return 1, nil
return 1, r.rErr
}
return 0, r.rErr
}

6
pkg/bitio/ioreadseeker.go
View File

@ -1,14 +1,14 @@
package bitio
// IOReadSeeker is a io.ReadSeeker that reads and seeks from a bitio.BitReadSeeker
// Unaligned byte at EOF will be zero bit padded
// IOReadSeeker is a io.ReadSeeker that reads from a bitio.ReadSeeker.
// Unaligned byte at EOF will be zero bit padded.
type IOReadSeeker struct {
IOReader
s Seeker
sPos int64
}
// NewIOReadSeeker return a new bitio.IOReadSeeker
// NewIOReadSeeker return a new bitio.IOReadSeeker.
func NewIOReadSeeker(rs ReadSeeker) *IOReadSeeker {
return &IOReadSeeker{
IOReader: IOReader{r: rs},

2
pkg/bitio/ioreadseeker_test.go
View File

@ -108,7 +108,7 @@ func Test(t *testing.T) {
for _, p := range bsParts {
bsBRs = append(bsBRs, sb(p))
}
bsBR, err := bitio.NewMultiBitReader(bsBRs...)
bsBR, err := bitio.NewMultiReader(bsBRs...)
if err != nil {
panic(err)
}

6
pkg/bitio/limitreader.go
View File

@ -4,14 +4,14 @@ import (
"io"
)
// LimitReader is a bitio.Reader that reads a limited amount of bits from a bitio.Reader
// Similar to bytes.LimitedReader
// LimitReader is a bitio.Reader that reads a limited amount of bits from a bitio.Reader.
// Similar to bytes.LimitedReader.
type LimitReader struct {
r Reader
n int64
}
// NewLimitReader returns a new bitio.LimitReader
// NewLimitReader returns a new bitio.LimitReader.
func NewLimitReader(r Reader, n int64) *LimitReader { return &LimitReader{r, n} }
func (l *LimitReader) ReadBits(p []byte, nBits int64) (n int64, err error) {

7
pkg/bitio/multireader.go
View File

@ -23,15 +23,16 @@ func endPos(rs Seeker) (int64, error) {
return e, nil
}
// MultiReader is a bitio.ReaderAtSeeker concatinating multiple bitio.ReadAtSeeker:s
// Similar to io.MultiReader
// MultiReader is a bitio.ReaderAtSeeker concatinating multiple bitio.ReadAtSeeker:s.
// Similar to io.MultiReader.
type MultiReader struct {
pos int64
readers []ReadAtSeeker
readerEnds []int64
}
func NewMultiBitReader(rs ...ReadAtSeeker) (*MultiReader, error) {
// NewMultiReader returns a new bitio.MultiReader.
func NewMultiReader(rs ...ReadAtSeeker) (*MultiReader, error) {
readerEnds := make([]int64, len(rs))
var esSum int64
for i, r := range rs {

2
pkg/bitio/readwrite64.go
View File

@ -90,6 +90,8 @@ func Read64(buf []byte, firstBit int64, nBits int64) uint64 {
return n
}
// Write64 writes nBits bits large unsigned integer to buf starting from firstBit.
// Integer is written most significant bit first.
func Write64(v uint64, nBits int64, buf []byte, firstBit int64) {
if nBits < 0 || nBits > 64 {
panic(fmt.Sprintf("nBits must be 0-64 (%d)", nBits))

4
pkg/bitio/reversebytes64.go
View File

@ -2,8 +2,8 @@ package bitio
import "fmt"
// ReverseBytes64 reverses the bytes part of the lowest nBits
// Similar to bits.ReverseBytes64 but only rotates the lowest bytes and rest of bytes will be zero
// ReverseBytes64 reverses the bytes part of the lowest nBits.
// Similar to bits.ReverseBytes64 but only rotates the lowest bytes and rest of bytes will be zero.
func ReverseBytes64(nBits int, n uint64) uint64 {
switch {
case nBits <= 8:

6
pkg/bitio/sectiontreader.go
View File

@ -4,8 +4,8 @@ import (
"io"
)
// SectionReader is a bitio.BitReaderAtSeeker reading a section of a bitio.ReaderAt
// Similar to io.SectionReader
// SectionReader is a bitio.BitReaderAtSeeker reading a section of a bitio.ReaderAt.
// Similar to io.SectionReader.
type SectionReader struct {
r ReaderAt
bitBase int64
@ -13,7 +13,7 @@ type SectionReader struct {
bitLimit int64
}
// NewSectionReader returns a new bitio.SectionReader
// NewSectionReader returns a new bitio.SectionReader.
func NewSectionReader(r ReaderAt, bitOff int64, nBits int64) *SectionReader {
return &SectionReader{
r: r,

8
pkg/cli/cli.go
View File

@ -158,7 +158,7 @@ func (stdOSFS) Open(name string) (fs.File, error) { return os.Open(name) }
func (*stdOS) FS() fs.FS { return stdOSFS{} }
func (o *stdOS) Readline(prompt string, complete func(line string, pos int) (newLine []string, shared int)) (string, error) {
func (o *stdOS) Readline(opts interp.ReadlineOpts) (string, error) {
if o.rl == nil {
var err error
@ -179,9 +179,9 @@ func (o *stdOS) Readline(prompt string, complete func(line string, pos int) (new
}
}
if complete != nil {
if opts.CompleteFn != nil {
o.rl.Config.AutoComplete = autoCompleterFn(func(line []rune, pos int) (newLine [][]rune, length int) {
names, shared := complete(string(line), pos)
names, shared := opts.CompleteFn(string(line), pos)
var runeNames [][]rune
for _, name := range names {
runeNames = append(runeNames, []rune(name[shared:]))
@ -191,7 +191,7 @@ func (o *stdOS) Readline(prompt string, complete func(line string, pos int) (new
})
}
o.rl.SetPrompt(prompt)
o.rl.SetPrompt(opts.Prompt)
line, err := o.rl.Readline()
if errors.Is(err, readline.ErrInterrupt) {
return "", interp.ErrInterrupt

18
pkg/decode/decode.go
View File

@ -112,7 +112,7 @@ func decode(ctx context.Context, br bitio.ReaderAtSeeker, group Group, opts Opti
if err := d.Value.WalkRootPreOrder(func(v *Value, rootV *Value, depth int, rootDepth int) error {
minMaxRange = ranges.MinMax(minMaxRange, v.Range)
v.Range.Start += decodeRange.Start
v.RootBitBuf = br
v.RootReader = br
return nil
}); err != nil {
return nil, nil, err
@ -165,7 +165,7 @@ func newDecoder(ctx context.Context, format Format, br bitio.ReaderAtSeeker, opt
Value: &Value{
Name: name,
V: rootV,
RootBitBuf: br,
RootReader: br,
Range: ranges.Range{Start: 0, Len: 0},
IsRoot: opts.IsRoot,
},
@ -184,7 +184,7 @@ func (d *D) FieldDecoder(name string, bitBuf bitio.ReaderAtSeeker, v interface{}
Name: name,
V: v,
Range: ranges.Range{Start: d.Pos(), Len: 0},
RootBitBuf: bitBuf,
RootReader: bitBuf,
},
Options: d.Options,
@ -289,7 +289,7 @@ func (d *D) FillGaps(r ranges.Range, namePrefix string) {
for i, gap := range gaps {
br, err := bitioextra.Range(d.bitBuf, gap.Start, gap.Len)
if err != nil {
d.IOPanic(err, "FillGaps: BitBufRange")
d.IOPanic(err, "FillGaps: Range")
}
v := &Value{
@ -298,7 +298,7 @@ func (d *D) FillGaps(r ranges.Range, namePrefix string) {
Actual: br,
Unknown: true,
},
RootBitBuf: d.bitBuf,
RootReader: d.bitBuf,
Range: gap,
}
@ -779,7 +779,7 @@ func (d *D) FieldArrayLoop(name string, condFn func() bool, fn func(d *D)) *D {
func (d *D) FieldRangeFn(name string, firstBit int64, nBits int64, fn func() *Value) *Value {
v := fn()
v.Name = name
v.RootBitBuf = d.bitBuf
v.RootReader = d.bitBuf
v.Range = ranges.Range{Start: firstBit, Len: nBits}
d.AddChild(v)
@ -892,7 +892,7 @@ func (d *D) RangeFn(firstBit int64, nBits int64, fn func(d *D)) int64 {
// TODO: refactor, similar to decode()
if err := sd.Value.WalkRootPreOrder(func(v *Value, rootV *Value, depth int, rootDepth int) error {
//v.Range.Start += firstBit
v.RootBitBuf = d.Value.RootBitBuf
v.RootReader = d.Value.RootReader
endPos = mathextra.MaxInt64(endPos, v.Range.Stop())
return nil
@ -1070,7 +1070,7 @@ func (d *D) FieldRootBitBuf(name string, br bitio.ReaderAtSeeker, sms ...scalar.
v := &Value{}
v.V = &scalar.S{Actual: br}
v.Name = name
v.RootBitBuf = br
v.RootReader = br
v.IsRoot = true
v.Range = ranges.Range{Start: d.Pos(), Len: brLen}
@ -1164,7 +1164,7 @@ func (d *D) TryFieldValue(name string, fn func() (*Value, error)) (*Value, error
v, err := fn()
stop := d.Pos()
v.Name = name
v.RootBitBuf = d.bitBuf
v.RootReader = d.bitBuf
v.Range = ranges.Range{Start: start, Len: stop - start}
if err != nil {
return nil, err

2
pkg/decode/value.go
View File

@ -27,7 +27,7 @@ type Value struct {
V interface{} // scalar.S or Compound (array/struct)
Index int // index in parent array/struct
Range ranges.Range
RootBitBuf bitio.ReaderAtSeeker
RootReader bitio.ReaderAtSeeker
IsRoot bool // TODO: rework?
}

212
pkg/interp/buffer.go → pkg/interp/binary.go
View File

@ -16,29 +16,43 @@ import (
"github.com/wader/fq/internal/progressreadseeker"
"github.com/wader/fq/pkg/bitio"
"github.com/wader/fq/pkg/ranges"
"github.com/wader/gojq"
)
func init() {
functionRegisterFns = append(functionRegisterFns, func(i *Interp) []Function {
return []Function{
{"_tobitsrange", 0, 2, i._toBitsRange, nil},
{"open", 0, 0, i._open, nil},
{"_tobits", 3, 3, i._toBits, nil},
{"open", 0, 0, nil, i._open},
}
})
}
type ToBuffer interface {
ToBuffer() (Buffer, error)
type ToBinary interface {
ToBinary() (Binary, error)
}
func toBitBuf(v interface{}) (bitio.ReaderAtSeeker, error) {
return toBitBufEx(v, false)
}
func toBitBufEx(v interface{}, inArray bool) (bitio.ReaderAtSeeker, error) {
func toBinary(v interface{}) (Binary, error) {
switch vv := v.(type) {
case ToBuffer:
bv, err := vv.ToBuffer()
case ToBinary:
return vv.ToBinary()
default:
br, err := toBitReader(v)
if err != nil {
return Binary{}, err
}
return newBinaryFromBitReader(br, 8, 0)
}
}
func toBitReader(v interface{}) (bitio.ReaderAtSeeker, error) {
return toBitReaderEx(v, false)
}
func toBitReaderEx(v interface{}, inArray bool) (bitio.ReaderAtSeeker, error) {
switch vv := v.(type) {
case ToBinary:
bv, err := vv.ToBinary()
if err != nil {
return nil, err
}
@ -53,7 +67,7 @@ func toBitBufEx(v interface{}, inArray bool) (bitio.ReaderAtSeeker, error) {
if inArray {
if bi.Cmp(big.NewInt(255)) > 0 || bi.Cmp(big.NewInt(0)) < 0 {
return nil, fmt.Errorf("buffer byte list must be bytes (0-255) got %v", bi)
return nil, fmt.Errorf("byte in binary list must be bytes (0-255) got %v", bi)
}
n := bi.Uint64()
b := [1]byte{byte(n)}
@ -78,106 +92,95 @@ func toBitBufEx(v interface{}, inArray bool) (bitio.ReaderAtSeeker, error) {
rr := make([]bitio.ReadAtSeeker, 0, len(vv))
// TODO: optimize byte array case, flatten into one slice
for _, e := range vv {
eBR, eErr := toBitBufEx(e, true)
eBR, eErr := toBitReaderEx(e, true)
if eErr != nil {
return nil, eErr
}
rr = append(rr, eBR)
}
mb, err := bitio.NewMultiBitReader(rr...)
mb, err := bitio.NewMultiReader(rr...)
if err != nil {
return nil, err
}
return mb, nil
default:
return nil, fmt.Errorf("value can't be a buffer")
return nil, fmt.Errorf("value can't be a binary")
}
}
func toBuffer(v interface{}) (Buffer, error) {
switch vv := v.(type) {
case ToBuffer:
return vv.ToBuffer()
default:
br, err := toBitBuf(v)
if err != nil {
return Buffer{}, err
}
return newBufferFromBuffer(br, 8)
}
}
// note is used to implement tobytes*/0 also
func (i *Interp) _toBitsRange(c interface{}, a []interface{}) interface{} {
var unit int
var r bool
var ok bool
if len(a) >= 1 {
unit, ok = gojqextra.ToInt(a[0])
// note is used to implement tobytes* also
func (i *Interp) _toBits(c interface{}, a []interface{}) interface{} {
unit, ok := gojqextra.ToInt(a[0])
if !ok {
return gojqextra.FuncTypeError{Name: "_tobitsrange", V: a[0]}
return gojqextra.FuncTypeError{Name: "_tobits", V: a[0]}
}
} else {
unit = 1
}
if len(a) >= 2 {
r, ok = gojqextra.ToBoolean(a[1])
keepRange, ok := gojqextra.ToBoolean(a[1])
if !ok {
return gojqextra.FuncTypeError{Name: "_tobitsrange", V: a[1]}
return gojqextra.FuncTypeError{Name: "_tobits", V: a[1]}
}
} else {
r = true
padToUnits, ok := gojqextra.ToInt(a[2])
if !ok {
return gojqextra.FuncTypeError{Name: "_tobits", V: a[2]}
}
// TODO: unit > 8?
bv, err := toBuffer(c)
bv, err := toBinary(c)
if err != nil {
return err
}
bv.unit = unit
if !r {
br, err := bv.toBuffer()
pad := int64(unit * padToUnits)
if pad == 0 {
pad = int64(unit)
}
bv.unit = unit
bv.pad = (pad - bv.r.Len%pad) % pad
if keepRange {
return bv
}
br, err := bv.toReader()
if err != nil {
return err
}
bb, err := newBufferFromBuffer(br, unit)
bb, err := newBinaryFromBitReader(br, bv.unit, bv.pad)
if err != nil {
return err
}
return bb
}
return bv
}
type openFile struct {
Buffer
Binary
filename string
progressFn progressreadseeker.ProgressFn
}
var _ Value = (*openFile)(nil)
var _ ToBuffer = (*openFile)(nil)
var _ ToBinary = (*openFile)(nil)
func (of *openFile) Display(w io.Writer, opts Options) error {
_, err := fmt.Fprintf(w, "<openfile %q>\n", of.filename)
return err
}
func (of *openFile) ToBuffer() (Buffer, error) {
return newBufferFromBuffer(of.br, 8)
func (of *openFile) ToBinary() (Binary, error) {
return newBinaryFromBitReader(of.br, 8, 0)
}
// def open: #:: string| => buffer
// def open: #:: string| => binary
// opens a file for reading from filesystem
// TODO: when to close? when br loses all refs? need to use finalizer somehow?
func (i *Interp) _open(c interface{}, a []interface{}) interface{} {
func (i *Interp) _open(c interface{}, a []interface{}) gojq.Iter {
if i.evalContext.isCompleting {
return gojq.NewIter()
}
var err error
var f fs.File
var path string
@ -189,11 +192,11 @@ func (i *Interp) _open(c interface{}, a []interface{}) interface{} {
default:
path, err = toString(c)
if err != nil {
return fmt.Errorf("%s: %w", path, err)
return gojq.NewIter(fmt.Errorf("%s: %w", path, err))
}
f, err = i.os.FS().Open(path)
if err != nil {
return err
return gojq.NewIter(err)
}
}
@ -203,7 +206,7 @@ func (i *Interp) _open(c interface{}, a []interface{}) interface{} {
fFI, err := f.Stat()
if err != nil {
f.Close()
return err
return gojq.NewIter(err)
}
// ctxreadseeker is used to make sure any io calls can be canceled
@ -221,7 +224,7 @@ func (i *Interp) _open(c interface{}, a []interface{}) interface{} {
buf, err := ioutil.ReadAll(ctxreadseeker.New(i.evalContext.ctx, &ioextra.ReadErrSeeker{Reader: f}))
if err != nil {
f.Close()
return err
return gojq.NewIter(err)
}
fRS = bytes.NewReader(buf)
bEnd = int64(len(buf))
@ -248,35 +251,37 @@ func (i *Interp) _open(c interface{}, a []interface{}) interface{} {
bbf.br = bitio.NewIOBitReadSeeker(aheadRs)
if err != nil {
return err
return gojq.NewIter(err)
}
return bbf
return gojq.NewIter(bbf)
}
var _ Value = Buffer{}
var _ ToBuffer = Buffer{}
var _ Value = Binary{}
var _ ToBinary = Binary{}
type Buffer struct {
type Binary struct {
br bitio.ReaderAtSeeker
r ranges.Range
unit int
pad int64
}
func newBufferFromBuffer(br bitio.ReaderAtSeeker, unit int) (Buffer, error) {
func newBinaryFromBitReader(br bitio.ReaderAtSeeker, unit int, pad int64) (Binary, error) {
l, err := bitioextra.Len(br)
if err != nil {
return Buffer{}, err
return Binary{}, err
}
return Buffer{
return Binary{
br: br,
r: ranges.Range{Start: 0, Len: l},
unit: unit,
pad: pad,
}, nil
}
func (b Buffer) toBytesBuffer(r ranges.Range) (*bytes.Buffer, error) {
func (b Binary) toBytesBuffer(r ranges.Range) (*bytes.Buffer, error) {
br, err := bitioextra.Range(b.br, r.Start, r.Len)
if err != nil {
return nil, err
@ -289,9 +294,9 @@ func (b Buffer) toBytesBuffer(r ranges.Range) (*bytes.Buffer, error) {
return buf, nil
}
func (Buffer) ExtType() string { return "buffer" }
func (Binary) ExtType() string { return "binary" }
func (Buffer) ExtKeys() []string {
func (Binary) ExtKeys() []string {
return []string{
"size",
"start",
@ -301,18 +306,18 @@ func (Buffer) ExtKeys() []string {
}
}
func (b Buffer) ToBuffer() (Buffer, error) {
func (b Binary) ToBinary() (Binary, error) {
return b, nil
}
func (b Buffer) JQValueLength() interface{} {
func (b Binary) JQValueLength() interface{} {
return int(b.r.Len / int64(b.unit))
}
func (b Buffer) JQValueSliceLen() interface{} {
func (b Binary) JQValueSliceLen() interface{} {
return b.JQValueLength()
}
func (b Buffer) JQValueIndex(index int) interface{} {
func (b Binary) JQValueIndex(index int) interface{} {
if index < 0 {
return nil
}
@ -326,17 +331,17 @@ func (b Buffer) JQValueIndex(index int) interface{} {
return new(big.Int).Rsh(new(big.Int).SetBytes(buf.Bytes()), extraBits)
}
func (b Buffer) JQValueSlice(start int, end int) interface{} {
func (b Binary) JQValueSlice(start int, end int) interface{} {
rStart := int64(start * b.unit)
rLen := int64((end - start) * b.unit)
return Buffer{
return Binary{
br: b.br,
r: ranges.Range{Start: b.r.Start + rStart, Len: rLen},
unit: b.unit,
}
}
func (b Buffer) JQValueKey(name string) interface{} {
func (b Binary) JQValueKey(name string) interface{} {
switch name {
case "size":
return new(big.Int).SetInt64(b.r.Len / int64(b.unit))
@ -353,28 +358,28 @@ func (b Buffer) JQValueKey(name string) interface{} {
if b.unit == 1 {
return b
}
return Buffer{br: b.br, r: b.r, unit: 1}
return Binary{br: b.br, r: b.r, unit: 1}
case "bytes":
if b.unit == 8 {
return b
}
return Buffer{br: b.br, r: b.r, unit: 8}
return Binary{br: b.br, r: b.r, unit: 8}
}
return nil
}
func (b Buffer) JQValueEach() interface{} {
func (b Binary) JQValueEach() interface{} {
return nil
}
func (b Buffer) JQValueType() string {
return "buffer"
func (b Binary) JQValueType() string {
return "binary"
}
func (b Buffer) JQValueKeys() interface{} {
return gojqextra.FuncTypeNameError{Name: "keys", Typ: "buffer"}
func (b Binary) JQValueKeys() interface{} {
return gojqextra.FuncTypeNameError{Name: "keys", Typ: "binary"}
}
func (b Buffer) JQValueHas(key interface{}) interface{} {
return gojqextra.HasKeyTypeError{L: "buffer", R: fmt.Sprintf("%v", key)}
func (b Binary) JQValueHas(key interface{}) interface{} {
return gojqextra.HasKeyTypeError{L: "binary", R: fmt.Sprintf("%v", key)}
}
func (b Buffer) JQValueToNumber() interface{} {
func (b Binary) JQValueToNumber() interface{} {
buf, err := b.toBytesBuffer(b.r)
if err != nil {
return err
@ -382,23 +387,23 @@ func (b Buffer) JQValueToNumber() interface{} {
extraBits := uint((8 - b.r.Len%8) % 8)
return new(big.Int).Rsh(new(big.Int).SetBytes(buf.Bytes()), extraBits)
}
func (b Buffer) JQValueToString() interface{} {
func (b Binary) JQValueToString() interface{} {
return b.JQValueToGoJQ()
}
func (b Buffer) JQValueToGoJQ() interface{} {
func (b Binary) JQValueToGoJQ() interface{} {
buf, err := b.toBytesBuffer(b.r)
if err != nil {
return err
}
return buf.String()
}
func (b Buffer) JQValueUpdate(key interface{}, u interface{}, delpath bool) interface{} {
return gojqextra.NonUpdatableTypeError{Key: fmt.Sprintf("%v", key), Typ: "buffer"}
func (b Binary) JQValueUpdate(key interface{}, u interface{}, delpath bool) interface{} {
return gojqextra.NonUpdatableTypeError{Key: fmt.Sprintf("%v", key), Typ: "binary"}
}
func (b Buffer) Display(w io.Writer, opts Options) error {
func (b Binary) Display(w io.Writer, opts Options) error {
if opts.RawOutput {
br, err := b.toBuffer()
br, err := b.toReader()
if err != nil {
return err
}
@ -413,6 +418,13 @@ func (b Buffer) Display(w io.Writer, opts Options) error {
return hexdump(w, b, opts)
}
func (b Buffer) toBuffer() (bitio.ReaderAtSeeker, error) {
return bitioextra.Range(b.br, b.r.Start, b.r.Len)
func (b Binary) toReader() (bitio.ReaderAtSeeker, error) {
br, err := bitioextra.Range(b.br, b.r.Start, b.r.Len)
if err != nil {
return nil, err
}
if b.pad == 0 {
return br, nil
}
return bitio.NewMultiReader(bitioextra.NewZeroAtSeeker(b.pad), br)
}

8
pkg/interp/binary.jq Normal file
View File

@ -0,0 +1,8 @@
def tobits: _tobits(1; false; 0);
def tobytes: _tobits(8; false; 0);
def tobitsrange: _tobits(1; true; 0);
def tobytesrange: _tobits(8; true; 0);
def tobits($pad): _tobits(1; false; $pad);
def tobytes($pad): _tobits(8; false; $pad);
def tobitsrange($pad): _tobits(1; true; $pad);
def tobytesrange($pad): _tobits(8; true; $pad);

4
pkg/interp/buffer.jq
View File

@ -1,4 +0,0 @@
def tobitsrange: _tobitsrange;
def tobytesrange: _tobitsrange(8);
def tobits: _tobitsrange(1; false);
def tobytes: _tobitsrange(8; false);

24
pkg/interp/decode.go
View File

@ -44,7 +44,7 @@ func (err expectedExtkeyError) Error() string {
// used by _isDecodeValue
type DecodeValue interface {
Value
ToBuffer
ToBinary
DecodeValue() *decode.Value
}
@ -162,7 +162,7 @@ func (i *Interp) _decode(c interface{}, a []interface{}) interface{} {
c,
opts.Progress,
nil,
ioextra.DiscardCtxWriter{Ctx: i.evalContext.ctx},
EvalOpts{output: ioextra.DiscardCtxWriter{Ctx: i.evalContext.ctx}},
)
}
lastProgress := time.Now()
@ -188,7 +188,7 @@ func (i *Interp) _decode(c interface{}, a []interface{}) interface{} {
}
}
bv, err := toBuffer(c)
bv, err := toBinary(c)
if err != nil {
return err
}
@ -276,7 +276,7 @@ func makeDecodeValue(dv *decode.Value) interface{} {
switch vv := vv.Value().(type) {
case bitio.ReaderAtSeeker:
// is lazy so that in situations where the decode value is only used to
// create another buffer we don't have to read and create a string, ex:
// create another binary we don't have to read and create a string, ex:
// .unknown0 | tobytes[1:] | ...
return decodeValue{
JQValue: &gojqextra.Lazy{
@ -364,8 +364,8 @@ func (dvb decodeValueBase) DecodeValue() *decode.Value {
}
func (dvb decodeValueBase) Display(w io.Writer, opts Options) error { return dump(dvb.dv, w, opts) }
func (dvb decodeValueBase) ToBuffer() (Buffer, error) {
return Buffer{br: dvb.dv.RootBitBuf, r: dvb.dv.InnerRange(), unit: 8}, nil
func (dvb decodeValueBase) ToBinary() (Binary, error) {
return Binary{br: dvb.dv.RootReader, r: dvb.dv.InnerRange(), unit: 8}, nil
}
func (decodeValueBase) ExtType() string { return "decode_value" }
func (dvb decodeValueBase) ExtKeys() []string {
@ -479,14 +479,14 @@ func (dvb decodeValueBase) JQValueKey(name string) interface{} {
return nil
}
case "_bits":
return Buffer{
br: dv.RootBitBuf,
return Binary{
br: dv.RootReader,
r: dv.Range,
unit: 1,
}
case "_bytes":
return Buffer{
br: dv.RootBitBuf,
return Binary{
br: dv.RootReader,
r: dv.Range,
unit: 8,
}
@ -543,11 +543,11 @@ func (v decodeValue) JQValueToGoJQEx(optsFn func() Options) interface{} {
return v.JQValueToGoJQ()
}
bv, err := v.decodeValueBase.ToBuffer()
bv, err := v.decodeValueBase.ToBinary()
if err != nil {
return err
}
br, err := bv.toBuffer()
br, err := bv.toReader()
if err != nil {
return err
}

10
pkg/interp/dump.go
View File

@ -219,7 +219,7 @@ func dumpEx(v *decode.Value, buf []byte, cw *columnwriter.Writer, depth int, roo
printErrs(depth, valueErr)
}
rootBitLen, err := bitioextra.Len(rootV.RootBitBuf)
rootBitLen, err := bitioextra.Len(rootV.RootReader)
if err != nil {
return err
}
@ -267,7 +267,7 @@ func dumpEx(v *decode.Value, buf []byte, cw *columnwriter.Writer, depth int, roo
cfmt(colAddr, "%s%s\n",
rootIndent, deco.DumpAddr.F(mathextra.PadFormatInt(startLineByte, opts.AddrBase, true, addrWidth)))
vBR, err := bitioextra.Range(rootV.RootBitBuf, startByte*8, displaySizeBits)
vBR, err := bitioextra.Range(rootV.RootReader, startByte*8, displaySizeBits)
if err != nil {
return err
}
@ -364,8 +364,8 @@ func dump(v *decode.Value, w io.Writer, opts Options) error {
}))
}
func hexdump(w io.Writer, bv Buffer, opts Options) error {
br, err := bv.toBuffer()
func hexdump(w io.Writer, bv Binary, opts Options) error {
br, err := bv.toReader()
if err != nil {
return err
}
@ -389,7 +389,7 @@ func hexdump(w io.Writer, bv Buffer, opts Options) error {
// TODO: hack
V: &scalar.S{Actual: br},
Range: bv.r,
RootBitBuf: biib,
RootReader: biib,
},
w,
opts,

40
pkg/interp/funcs.go
View File

@ -23,26 +23,26 @@ func init() {
return []Function{
{"_hexdump", 1, 1, nil, i._hexdump},
{"hex", 0, 0, makeStringBitBufTransformFn(
{"hex", 0, 0, makeStringBinaryTransformFn(
func(r io.Reader) (io.Reader, error) { return hex.NewDecoder(r), nil },
func(r io.Writer) (io.Writer, error) { return hex.NewEncoder(r), nil },
), nil},
{"base64", 0, 0, makeStringBitBufTransformFn(
{"base64", 0, 0, makeStringBinaryTransformFn(
func(r io.Reader) (io.Reader, error) { return base64.NewDecoder(base64.StdEncoding, r), nil },
func(r io.Writer) (io.Writer, error) { return base64.NewEncoder(base64.StdEncoding, r), nil },
), nil},
{"rawbase64", 0, 0, makeStringBitBufTransformFn(
{"rawbase64", 0, 0, makeStringBinaryTransformFn(
func(r io.Reader) (io.Reader, error) { return base64.NewDecoder(base64.RawURLEncoding, r), nil },
func(r io.Writer) (io.Writer, error) { return base64.NewEncoder(base64.RawURLEncoding, r), nil },
), nil},
{"urlbase64", 0, 0, makeStringBitBufTransformFn(
{"urlbase64", 0, 0, makeStringBinaryTransformFn(
func(r io.Reader) (io.Reader, error) { return base64.NewDecoder(base64.URLEncoding, r), nil },
func(r io.Writer) (io.Writer, error) { return base64.NewEncoder(base64.URLEncoding, r), nil },
), nil},
{"nal_unescape", 0, 0, makeBitBufTransformFn(func(r io.Reader) (io.Reader, error) {
{"nal_unescape", 0, 0, makeBinaryTransformFn(func(r io.Reader) (io.Reader, error) {
return &decode.NALUnescapeReader{Reader: r}, nil
}), nil},
@ -57,15 +57,15 @@ func init() {
})
}
// transform byte string <-> buffer using fn:s
func makeStringBitBufTransformFn(
// transform byte string <-> binary using fn:s
func makeStringBinaryTransformFn(
decodeFn func(r io.Reader) (io.Reader, error),
encodeFn func(w io.Writer) (io.Writer, error),
) func(c interface{}, a []interface{}) interface{} {
return func(c interface{}, a []interface{}) interface{} {
switch c := c.(type) {
case string:
br, err := toBitBuf(c)
br, err := toBitReader(c)
if err != nil {
return err
}
@ -80,13 +80,13 @@ func makeStringBitBufTransformFn(
return err
}
bb, err := newBufferFromBuffer(bitio.NewBitReader(buf.Bytes(), -1), 8)
bb, err := newBinaryFromBitReader(bitio.NewBitReader(buf.Bytes(), -1), 8, 0)
if err != nil {
return err
}
return bb
default:
br, err := toBitBuf(c)
br, err := toBitReader(c)
if err != nil {
return err
}
@ -110,10 +110,10 @@ func makeStringBitBufTransformFn(
}
}
// transform to buffer using fn
func makeBitBufTransformFn(fn func(r io.Reader) (io.Reader, error)) func(c interface{}, a []interface{}) interface{} {
// transform to binary using fn
func makeBinaryTransformFn(fn func(r io.Reader) (io.Reader, error)) func(c interface{}, a []interface{}) interface{} {
return func(c interface{}, a []interface{}) interface{} {
inBR, err := toBitBuf(c)
inBR, err := toBitReader(c)
if err != nil {
return err
}
@ -130,7 +130,7 @@ func makeBitBufTransformFn(fn func(r io.Reader) (io.Reader, error)) func(c inter
outBR := bitio.NewBitReader(outBuf.Bytes(), -1)
bb, err := newBufferFromBuffer(outBR, 8)
bb, err := newBinaryFromBitReader(outBR, 8, 0)
if err != nil {
return err
}
@ -138,10 +138,10 @@ func makeBitBufTransformFn(fn func(r io.Reader) (io.Reader, error)) func(c inter
}
}
// transform to buffer using fn
// transform to binary using fn
func makeHashFn(fn func() (hash.Hash, error)) func(c interface{}, a []interface{}) interface{} {
return func(c interface{}, a []interface{}) interface{} {
inBR, err := toBitBuf(c)
inBR, err := toBitReader(c)
if err != nil {
return err
}
@ -156,7 +156,7 @@ func makeHashFn(fn func() (hash.Hash, error)) func(c interface{}, a []interface{
outBR := bitio.NewBitReader(h.Sum(nil), -1)
bb, err := newBufferFromBuffer(outBR, 8)
bb, err := newBinaryFromBitReader(outBR, 8, 0)
if err != nil {
return err
}
@ -234,7 +234,7 @@ func (i *Interp) aesCtr(c interface{}, a []interface{}) interface{} {
ivBytes = make([]byte, block.BlockSize())
}
br, err := toBitBuf(c)
br, err := toBitReader(c)
if err != nil {
return err
}
@ -245,7 +245,7 @@ func (i *Interp) aesCtr(c interface{}, a []interface{}) interface{} {
return err
}
bb, err := newBufferFromBuffer(bitio.NewBitReader(buf.Bytes(), -1), 8)
bb, err := newBinaryFromBitReader(bitio.NewBitReader(buf.Bytes(), -1), 8, 0)
if err != nil {
return err
}
@ -254,7 +254,7 @@ func (i *Interp) aesCtr(c interface{}, a []interface{}) interface{} {
func (i *Interp) _hexdump(c interface{}, a []interface{}) gojq.Iter {
opts := i.Options(a[0])
bv, err := toBuffer(c)
bv, err := toBinary(c)
if err != nil {
return gojq.NewIter(err)
}

106
pkg/interp/funcs.jq
View File

@ -202,22 +202,9 @@ def table(colmap; render):
)
end;
# convert number to array of bytes
def number_to_bytes($bits):
def _number_to_bytes($d):
if . > 0 then
. % $d, (intdiv(.; $d) | _number_to_bytes($d))
else
empty
end;
if . == 0 then [0]
else [_number_to_bytes(pow(2; $bits) | _to_int)] | reverse
end;
def number_to_bytes:
number_to_bytes(8);
def from_radix($base; $table):
( split("")
def fromradix($base; $table):
( if type != "string" then error("cannot fromradix convert: \(.)") end
| split("")
| reverse
| map($table[.])
| if . == null then error("invalid char \(.)") end
@ -229,9 +216,23 @@ def from_radix($base; $table):
)
| .[1]
);
def fromradix($base):
fromradix($base; {
"0": 0, "1": 1, "2": 2, "3": 3,"4": 4, "5": 5, "6": 6, "7": 7, "8": 8, "9": 9,
"a": 10, "b": 11, "c": 12, "d": 13, "e": 14, "f": 15, "g": 16,
"h": 17, "i": 18, "j": 19, "k": 20, "l": 21, "m": 22, "n": 23,
"o": 24, "p": 25, "q": 26, "r": 27, "s": 28, "t": 29, "u": 30,
"v": 31, "w": 32, "x": 33, "y": 34, "z": 35,
"A": 36, "B": 37, "C": 38, "D": 39, "E": 40, "F": 41, "G": 42,
"H": 43, "I": 44, "J": 45, "K": 46, "L": 47, "M": 48, "N": 49,
"O": 50, "P": 51, "Q": 52, "R": 53, "S": 54, "T": 55, "U": 56,
"V": 57, "W": 58, "X": 59, "Y": 60, "Z": 61,
"@": 62, "_": 63,
});
def to_radix($base; $table):
if . == 0 then "0"
def toradix($base; $table):
( if type != "number" then error("cannot toradix convert: \(.)") end
| if . == 0 then "0"
else
( [ recurse(if . > 0 then intdiv(.; $base) else empty end) | . % $base]
| reverse
@ -242,62 +243,18 @@ def to_radix($base; $table):
error("base too large")
end
)
end;
def radix($base; $to_table; $from_table):
if . | type == "number" then to_radix($base; $to_table)
elif . | type == "string" then from_radix($base; $from_table)
else error("needs to be number or string")
end;
def radix2: radix(2; "01"; {"0": 0, "1": 1});
def radix8: radix(8; "01234567"; {"0": 0, "1": 1, "2": 2, "3": 3,"4": 4, "5": 5, "6": 6, "7": 7});
def radix16: radix(16; "0123456789abcdef"; {
"0": 0, "1": 1, "2": 2, "3": 3,"4": 4, "5": 5, "6": 6, "7": 7, "8": 8, "9": 9,
"a": 10, "b": 11, "c": 12, "d": 13, "e": 14, "f": 15
});
def radix62: radix(62; "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"; {
"0": 0, "1": 1, "2": 2, "3": 3,"4": 4, "5": 5, "6": 6, "7": 7, "8": 8, "9": 9,
"A": 10, "B": 11, "C": 12, "D": 13, "E": 14, "F": 15, "G": 16,
"H": 17, "I": 18, "J": 19, "K": 20, "L": 21, "M": 22, "N": 23,
"O": 24, "P": 25, "Q": 26, "R": 27, "S": 28, "T": 29, "U": 30,
"V": 31, "W": 32, "X": 33, "Y": 34, "Z": 35,
"a": 36, "b": 37, "c": 38, "d": 39, "e": 40, "f": 41, "g": 42,
"h": 43, "i": 44, "j": 45, "k": 46, "l": 47, "m": 48, "n": 49,
"o": 50, "p": 51, "q": 52, "r": 53, "s": 54, "t": 55, "u": 56,
"v": 57, "w": 58, "x": 59, "y": 60, "z": 61
});
def radix62: radix(62; "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789"; {
"A": 0, "B": 1, "C": 2, "D": 3, "E": 4, "F": 5, "G": 6,
"H": 7, "I": 8, "J": 9, "K": 10, "L": 11, "M": 12, "N": 13,
"O": 14, "P": 15, "Q": 16, "R": 17, "S": 18, "T": 19, "U": 20,
"V": 21, "W": 22, "X": 23, "Y": 24, "Z": 25,
"a": 26, "b": 27, "c": 28, "d": 29, "e": 30, "f": 31, "g": 32,
"h": 33, "i": 34, "j": 35, "k": 36, "l": 37, "m": 38, "n": 39,
"o": 40, "p": 41, "q": 42, "r": 43, "s": 44, "t": 45, "u": 46,
"v": 47, "w": 48, "x": 49, "y": 50, "z": 51,
"0": 52, "1": 53, "2": 54, "3": 55, "4": 56, "5": 57, "6": 58, "7": 59, "8": 60, "9": 61
});
def radix64: radix(64; "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"; {
"A": 0, "B": 1, "C": 2, "D": 3, "E": 4, "F": 5, "G": 6,
"H": 7, "I": 8, "J": 9, "K": 10, "L": 11, "M": 12, "N": 13,
"O": 14, "P": 15, "Q": 16, "R": 17, "S": 18, "T": 19, "U": 20,
"V": 21, "W": 22, "X": 23, "Y": 24, "Z": 25,
"a": 26, "b": 27, "c": 28, "d": 29, "e": 30, "f": 31, "g": 32,
"h": 33, "i": 34, "j": 35, "k": 36, "l": 37, "m": 38, "n": 39,
"o": 40, "p": 41, "q": 42, "r": 43, "s": 44, "t": 45, "u": 46,
"v": 47, "w": 48, "x": 49, "y": 50, "z": 51,
"0": 52, "1": 53, "2": 54, "3": 55, "4": 56, "5": 57, "6": 58, "7": 59, "8": 60, "9": 61,
"+": 62, "/": 63
});
end
);
def toradix($base):
toradix($base; "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ@_");
# TODO: rename keys and add more, ascii/utf8/utf16/codepoint name?, le/be, signed/unsigned?
def iprint:
{
bin: "0b\(radix2)",
oct: "0o\(radix8)",
bin: "0b\(toradix(2))",
oct: "0o\(toradix(8))",
dec: "\(.)",
hex: "0x\(radix16)",
hex: "0x\(toradix(16))",
str: (try ([.] | implode) catch null),
};
@ -348,3 +305,14 @@ def topem($label):
| join("\n")
);
def topem: topem("");
def paste:
if _is_completing | not then
( [ _repeat_break(
try _stdin(64*1024)
catch if . == "eof" then error("break") end
)
]
| join("")
)
end;

29
pkg/interp/funcs_test.jq
View File

@ -45,33 +45,4 @@ include "funcs";
["1234", 2, ["12","34"]],
["1234", 3, ["123","4"]]
][] | . as $t | assert("\($t[0]) | chunk(\($t[1]))"; $t[2]; $t[0] | chunk($t[1])))
,
([
# 0xfffffffffffffffffffffffffffffffffffffffffffff
[1532495540865888858358347027150309183618739122183602175, 8, [
15,
255,
255,
255,
255,
255,
255,
255,
255,
255,
255,
255,
255,
255,
255,
255,
255,
255,
255,
255,
255,
255,
255
]]
][] | . as $t | assert("\($t[0]) | number_to_bytes(\($t[1]))"; $t[2]; $t[0] | number_to_bytes($t[1])))
)

224
pkg/interp/interp.go
View File

@ -11,6 +11,7 @@ import (
"fmt"
"io"
"io/fs"
"io/ioutil"
"math/big"
"path"
"strconv"
@ -22,6 +23,7 @@ import (
"github.com/wader/fq/internal/bitioextra"
"github.com/wader/fq/internal/colorjson"
"github.com/wader/fq/internal/ctxstack"
"github.com/wader/fq/internal/gojqextra"
"github.com/wader/fq/internal/ioextra"
"github.com/wader/fq/internal/mathextra"
"github.com/wader/fq/internal/pos"
@ -35,7 +37,7 @@ import (
//go:embed interp.jq
//go:embed internal.jq
//go:embed options.jq
//go:embed buffer.jq
//go:embed binary.jq
//go:embed decode.jq
//go:embed match.jq
//go:embed funcs.jq
@ -53,11 +55,11 @@ var functionRegisterFns []func(i *Interp) []Function
func init() {
functionRegisterFns = append(functionRegisterFns, func(i *Interp) []Function {
return []Function{
{"_readline", 0, 2, i.readline, nil},
{"_readline", 0, 1, nil, i._readline},
{"eval", 1, 2, nil, i.eval},
{"_stdin", 0, 0, nil, i.makeStdioFn(i.os.Stdin())},
{"_stdout", 0, 0, nil, i.makeStdioFn(i.os.Stdout())},
{"_stderr", 0, 0, nil, i.makeStdioFn(i.os.Stderr())},
{"_stdin", 0, 1, nil, i.makeStdioFn("stdin", i.os.Stdin())},
{"_stdout", 0, 0, nil, i.makeStdioFn("stdout", i.os.Stdout())},
{"_stderr", 0, 0, nil, i.makeStdioFn("stderr", i.os.Stderr())},
{"_extkeys", 0, 0, i._extKeys, nil},
{"_exttype", 0, 0, i._extType, nil},
{"_global_state", 0, 1, i.makeStateFn(i.state), nil},
@ -65,6 +67,7 @@ func init() {
{"_display", 1, 1, nil, i._display},
{"_can_display", 0, 0, i._canDisplay, nil},
{"_print_color_json", 0, 1, nil, i._printColorJSON},
{"_is_completing", 0, 1, i._isCompleting, nil},
}
})
}
@ -95,7 +98,7 @@ func (ce compileError) Value() interface{} {
func (ce compileError) Error() string {
filename := ce.filename
if filename == "" {
filename = "src"
filename = "expr"
}
return fmt.Sprintf("%s:%d:%d: %s: %s", filename, ce.pos.Line, ce.pos.Column, ce.what, ce.err.Error())
}
@ -133,6 +136,11 @@ type Platform struct {
Arch string
}
type ReadlineOpts struct {
Prompt string
CompleteFn func(line string, pos int) (newLine []string, shared int)
}
type OS interface {
Platform() Platform
Stdin() Input
@ -144,7 +152,7 @@ type OS interface {
ConfigDir() (string, error)
// FS.File returned by FS().Open() can optionally implement io.Seeker
FS() fs.FS
Readline(prompt string, complete func(line string, pos int) (newLine []string, shared int)) (string, error)
Readline(opts ReadlineOpts) (string, error)
History() ([]string, error)
}
@ -270,7 +278,7 @@ func toBigInt(v interface{}) (*big.Int, error) {
func toBytes(v interface{}) ([]byte, error) {
switch v := v.(type) {
default:
br, err := toBitBuf(v)
br, err := toBitReader(v)
if err != nil {
return nil, fmt.Errorf("value is not bytes")
}
@ -283,14 +291,14 @@ func toBytes(v interface{}) ([]byte, error) {
}
}
func queryErrorPosition(src string, v error) pos.Pos {
func queryErrorPosition(expr string, v error) pos.Pos {
var offset int
if tokIf, ok := v.(interface{ Token() (string, int) }); ok { //nolint:errorlint
_, offset = tokIf.Token()
}
if offset >= 0 {
return pos.NewFromOffset(src, offset)
return pos.NewFromOffset(expr, offset)
}
return pos.Pos{}
}
@ -319,15 +327,16 @@ const (
type evalContext struct {
ctx context.Context
output io.Writer
isCompleting bool
}
type Interp struct {
registry *registry.Registry
os OS
initFqQuery *gojq.Query
initQuery *gojq.Query
includeCache map[string]*gojq.Query
interruptStack *ctxstack.Stack
// global state, is ref as Interp i cloned per eval
// global state, is ref as Interp is cloned per eval
state *interface{}
// new for each run, other values are copied by value
@ -343,7 +352,7 @@ func New(os OS, registry *registry.Registry) (*Interp, error) {
}
i.includeCache = map[string]*gojq.Query{}
i.initFqQuery, err = gojq.Parse(initSource)
i.initQuery, err = gojq.Parse(initSource)
if err != nil {
return nil, fmt.Errorf("init:%s: %w", queryErrorPosition(initSource, err), err)
}
@ -380,7 +389,7 @@ func (i *Interp) Main(ctx context.Context, output Output, versionStr string) err
"arch": platform.Arch,
}
iter, err := i.EvalFunc(ctx, input, "_main", nil, output)
iter, err := i.EvalFunc(ctx, input, "_main", nil, EvalOpts{output: output})
if err != nil {
fmt.Fprintln(i.os.Stderr(), err)
return err
@ -414,28 +423,24 @@ func (i *Interp) Main(ctx context.Context, output Output, versionStr string) err
return nil
}
func (i *Interp) readline(c interface{}, a []interface{}) interface{} {
func (i *Interp) _readline(c interface{}, a []interface{}) gojq.Iter {
if i.evalContext.isCompleting {
return gojq.NewIter()
}
var opts struct {
Promopt string `mapstructure:"prompt"`
Complete string `mapstructure:"complete"`
Timeout float64 `mapstructure:"timeout"`
}
var err error
prompt := ""
if len(a) > 0 {
prompt, err = toString(a[0])
if err != nil {
return fmt.Errorf("prompt: %w", err)
}
}
if len(a) > 1 {
_ = mapstructure.Decode(a[1], &opts)
_ = mapstructure.Decode(a[0], &opts)
}
src, err := i.os.Readline(
prompt,
func(line string, pos int) (newLine []string, shared int) {
expr, err := i.os.Readline(ReadlineOpts{
Prompt: opts.Promopt,
CompleteFn: func(line string, pos int) (newLine []string, shared int) {
completeCtx := i.evalContext.ctx
if opts.Timeout > 0 {
var completeCtxCancelFn context.CancelFunc
@ -450,7 +455,10 @@ func (i *Interp) readline(c interface{}, a []interface{}) interface{} {
c,
opts.Complete,
[]interface{}{line, pos},
ioextra.DiscardCtxWriter{Ctx: completeCtx},
EvalOpts{
output: ioextra.DiscardCtxWriter{Ctx: completeCtx},
isCompleting: true,
},
)
if err != nil {
return nil, pos, err
@ -485,24 +493,24 @@ func (i *Interp) readline(c interface{}, a []interface{}) interface{} {
return names, shared
},
)
})
if errors.Is(err, ErrInterrupt) {
return valueError{"interrupt"}
return gojq.NewIter(valueError{"interrupt"})
} else if errors.Is(err, ErrEOF) {
return valueError{"eof"}
return gojq.NewIter(valueError{"eof"})
} else if err != nil {
return err
return gojq.NewIter(err)
}
return src
return gojq.NewIter(expr)
}
func (i *Interp) eval(c interface{}, a []interface{}) gojq.Iter {
var err error
src, err := toString(a[0])
expr, err := toString(a[0])
if err != nil {
return gojq.NewIter(fmt.Errorf("src: %w", err))
return gojq.NewIter(fmt.Errorf("expr: %w", err))
}
var filenameHint string
if len(a) >= 2 {
@ -512,7 +520,10 @@ func (i *Interp) eval(c interface{}, a []interface{}) gojq.Iter {
}
}
iter, err := i.Eval(i.evalContext.ctx, c, src, filenameHint, i.evalContext.output)
iter, err := i.Eval(i.evalContext.ctx, c, expr, EvalOpts{
filename: filenameHint,
output: i.evalContext.output,
})
if err != nil {
return gojq.NewIter(err)
}
@ -547,25 +558,57 @@ func (i *Interp) makeStateFn(state *interface{}) func(c interface{}, a []interfa
}
}
func (i *Interp) makeStdioFn(t Terminal) func(c interface{}, a []interface{}) gojq.Iter {
func (i *Interp) makeStdioFn(name string, t Terminal) func(c interface{}, a []interface{}) gojq.Iter {
return func(c interface{}, a []interface{}) gojq.Iter {
if c == nil {
switch {
case len(a) == 1:
if i.evalContext.isCompleting {
return gojq.NewIter("")
}
r, ok := t.(io.Reader)
if !ok {
return gojq.NewIter(fmt.Errorf("%s is not readable", name))
}
l, ok := gojqextra.ToInt(a[0])
if !ok {
return gojq.NewIter(gojqextra.FuncTypeError{Name: name, V: a[0]})
}
buf := make([]byte, l)
n, err := io.ReadFull(r, buf)
s := string(buf[0:n])
vs := []interface{}{s}
switch {
case errors.Is(err, io.EOF), errors.Is(err, io.ErrUnexpectedEOF):
vs = append(vs, valueError{"eof"})
default:
vs = append(vs, err)
}
return gojq.NewIter(vs...)
case c == nil:
w, h := t.Size()
return gojq.NewIter(map[string]interface{}{
"is_terminal": t.IsTerminal(),
"width": w,
"height": h,
})
default:
if i.evalContext.isCompleting {
return gojq.NewIter()
}
if w, ok := t.(io.Writer); ok {
w, ok := t.(io.Writer)
if !ok {
return gojq.NewIter(fmt.Errorf("%v: it not writeable", c))
}
if _, err := fmt.Fprint(w, c); err != nil {
return gojq.NewIter(err)
}
return gojq.NewIter()
}
return gojq.NewIter(fmt.Errorf("%v: it not writeable", c))
}
}
@ -595,6 +638,11 @@ func (i *Interp) _display(c interface{}, a []interface{}) gojq.Iter {
}
}
func (i *Interp) _canDisplay(c interface{}, a []interface{}) interface{} {
_, ok := c.(Display)
return ok
}
func (i *Interp) _printColorJSON(c interface{}, a []interface{}) gojq.Iter {
opts := i.Options(a[0])
@ -609,64 +657,77 @@ func (i *Interp) _printColorJSON(c interface{}, a []interface{}) gojq.Iter {
return gojq.NewIter()
}
func (i *Interp) _canDisplay(c interface{}, a []interface{}) interface{} {
_, ok := c.(Display)
return ok
func (i *Interp) _isCompleting(c interface{}, a []interface{}) interface{} {
return i.evalContext.isCompleting
}
type pathResolver struct {
prefix string
open func(filename string) (io.ReadCloser, error)
open func(filename string) (io.ReadCloser, string, error)
}
func (i *Interp) lookupPathResolver(filename string) (pathResolver, error) {
configDir, err := i.os.ConfigDir()
if err != nil {
return pathResolver{}, err
}
func (i *Interp) lookupPathResolver(filename string) (pathResolver, bool) {
resolvePaths := []pathResolver{
{
"@builtin/",
func(filename string) (io.ReadCloser, error) { return builtinFS.Open(filename) },
},
{
"@config/", func(filename string) (io.ReadCloser, error) {
configDir, err := i.os.ConfigDir()
if err != nil {
return nil, err
}
return i.os.FS().Open(path.Join(configDir, filename))
func(filename string) (io.ReadCloser, string, error) {
f, err := builtinFS.Open(filename)
return f, "@builtin/" + filename, err
},
},
{
"", func(filename string) (io.ReadCloser, error) {
"@config/", func(filename string) (io.ReadCloser, string, error) {
p := path.Join(configDir, filename)
f, err := i.os.FS().Open(p)
return f, p, err
},
},
{
"", func(filename string) (io.ReadCloser, string, error) {
if path.IsAbs(filename) {
return i.os.FS().Open(filename)
f, err := i.os.FS().Open(filename)
return f, filename, err
}
// TODO: jq $ORIGIN
for _, includePath := range append([]string{"./"}, i.includePaths()...) {
p := path.Join(includePath, filename)
if f, err := i.os.FS().Open(path.Join(includePath, filename)); err == nil {
return f, nil
return f, p, nil
}
}
return nil, &fs.PathError{Op: "open", Path: filename, Err: fs.ErrNotExist}
return nil, "", &fs.PathError{Op: "open", Path: filename, Err: fs.ErrNotExist}
},
},
}
for _, p := range resolvePaths {
if strings.HasPrefix(filename, p.prefix) {
return p, true
return p, nil
}
}
return pathResolver{}, false
return pathResolver{}, fmt.Errorf("could not resolve path: %s", filename)
}
func (i *Interp) Eval(ctx context.Context, c interface{}, src string, srcFilename string, output io.Writer) (gojq.Iter, error) {
gq, err := gojq.Parse(src)
type EvalOpts struct {
filename string
output io.Writer
isCompleting bool
}
func (i *Interp) Eval(ctx context.Context, c interface{}, expr string, opts EvalOpts) (gojq.Iter, error) {
gq, err := gojq.Parse(expr)
if err != nil {
p := queryErrorPosition(src, err)
p := queryErrorPosition(expr, err)
return nil, compileError{
err: err,
what: "parse",
filename: srcFilename,
filename: opts.filename,
pos: p,
}
}
@ -701,7 +762,7 @@ func (i *Interp) Eval(ctx context.Context, c interface{}, src string, srcFilenam
compilerOpts = append(compilerOpts, gojq.WithVariables(variableNames))
compilerOpts = append(compilerOpts, gojq.WithModuleLoader(loadModule{
init: func() ([]*gojq.Query, error) {
return []*gojq.Query{i.initFqQuery}, nil
return []*gojq.Query{i.initQuery}, nil
},
load: func(name string) (*gojq.Query, error) {
if err := ctx.Err(); err != nil {
@ -719,9 +780,9 @@ func (i *Interp) Eval(ctx context.Context, c interface{}, src string, srcFilenam
}
filename = filename + ".jq"
pr, ok := i.lookupPathResolver(filename)
if !ok {
return nil, fmt.Errorf("could not resolve path: %s", filename)
pr, err := i.lookupPathResolver(filename)
if err != nil {
return nil, err
}
if q, ok := ni.includeCache[filename]; ok {
@ -730,7 +791,7 @@ func (i *Interp) Eval(ctx context.Context, c interface{}, src string, srcFilenam
filenamePart := strings.TrimPrefix(filename, pr.prefix)
f, err := pr.open(filenamePart)
f, absPath, err := pr.open(filenamePart)
if err != nil {
if !isTry {
return nil, err
@ -750,7 +811,7 @@ func (i *Interp) Eval(ctx context.Context, c interface{}, src string, srcFilenam
return nil, compileError{
err: err,
what: "parse",
filename: filenamePart,
filename: absPath,
pos: p,
}
}
@ -819,18 +880,25 @@ func (i *Interp) Eval(ctx context.Context, c interface{}, src string, srcFilenam
gc, err := gojq.Compile(gq, compilerOpts...)
if err != nil {
p := queryErrorPosition(src, err)
p := queryErrorPosition(expr, err)
return nil, compileError{
err: err,
what: "compile",
filename: srcFilename,
filename: opts.filename,
pos: p,
}
}
output := opts.output
if opts.output == nil {
output = ioutil.Discard
}
runCtx, runCtxCancelFn := i.interruptStack.Push(ctx)
ni.evalContext.ctx = runCtx
ni.evalContext.output = ioextra.CtxWriter{Writer: output, Ctx: runCtx}
// inherit or set
ni.evalContext.isCompleting = i.evalContext.isCompleting || opts.isCompleting
iter := gc.RunWithContext(runCtx, c, variableValues...)
iterWrapper := iterFn(func() (interface{}, bool) {
@ -845,7 +913,7 @@ func (i *Interp) Eval(ctx context.Context, c interface{}, src string, srcFilenam
return iterWrapper, nil
}
func (i *Interp) EvalFunc(ctx context.Context, c interface{}, name string, args []interface{}, output io.Writer) (gojq.Iter, error) {
func (i *Interp) EvalFunc(ctx context.Context, c interface{}, name string, args []interface{}, opts EvalOpts) (gojq.Iter, error) {
var argsExpr []string
for i := range args {
argsExpr = append(argsExpr, fmt.Sprintf("$_args[%d]", i))
@ -862,15 +930,15 @@ func (i *Interp) EvalFunc(ctx context.Context, c interface{}, name string, args
// _args to mark variable as internal and hide it from completion
// {input: ..., args: [...]} | .args as {args: $_args} | .input | name[($_args[0]; ...)]
trampolineExpr := fmt.Sprintf(". as {args: $_args} | .input | %s%s", name, argExpr)
iter, err := i.Eval(ctx, trampolineInput, trampolineExpr, "", output)
iter, err := i.Eval(ctx, trampolineInput, trampolineExpr, opts)
if err != nil {
return nil, err
}
return iter, nil
}
func (i *Interp) EvalFuncValues(ctx context.Context, c interface{}, name string, args []interface{}, output io.Writer) ([]interface{}, error) {
iter, err := i.EvalFunc(ctx, c, name, args, output)
func (i *Interp) EvalFuncValues(ctx context.Context, c interface{}, name string, args []interface{}, opts EvalOpts) ([]interface{}, error) {
iter, err := i.EvalFunc(ctx, c, name, args, opts)
if err != nil {
return nil, err
}

2
pkg/interp/interp.jq
View File

@ -1,6 +1,6 @@
include "internal";
include "options";
include "buffer";
include "binary";
include "decode";
include "match";
include "funcs";

12
pkg/interp/match.go
View File

@ -15,15 +15,15 @@ import (
func init() {
functionRegisterFns = append(functionRegisterFns, func(i *Interp) []Function {
return []Function{
{"_match_buffer", 1, 2, nil, i._bufferMatch},
{"_match_binary", 1, 2, nil, i._binaryMatch},
}
})
}
func (i *Interp) _bufferMatch(c interface{}, a []interface{}) gojq.Iter {
func (i *Interp) _binaryMatch(c interface{}, a []interface{}) gojq.Iter {
var ok bool
bv, err := toBuffer(c)
bv, err := toBinary(c)
if err != nil {
return gojq.NewIter(err)
}
@ -70,7 +70,7 @@ func (i *Interp) _bufferMatch(c interface{}, a []interface{}) gojq.Iter {
}
sreNames := sre.SubexpNames()
br, err := bv.toBuffer()
br, err := bv.toReader()
if err != nil {
return gojq.NewIter(err)
}
@ -92,7 +92,7 @@ func (i *Interp) _bufferMatch(c interface{}, a []interface{}) gojq.Iter {
var off int64
prevOff := int64(-1)
return iterFn(func() (interface{}, bool) {
// TODO: correct way to handle empty match for buffer, move one byte forward?
// TODO: correct way to handle empty match for binary, move one byte forward?
// > "asdasd" | [match(""; "g")], [(tobytes | match(""; "g"))] | length
// 7
// 1
@ -127,7 +127,7 @@ func (i *Interp) _bufferMatch(c interface{}, a []interface{}) gojq.Iter {
if start != -1 {
matchBitOff := (off + int64(start)) * 8
matchLength := int64(end-start) * 8
bbo := Buffer{
bbo := Binary{
br: bv.br,
r: ranges.Range{
Start: bv.r.Start + matchBitOff,

52
pkg/interp/match.jq
View File

@ -1,10 +1,10 @@
def _buffer_fn(f):
def _binary_fn(f):
( . as $c
| tobytesrange
| f
);
def _buffer_try_orig(bfn; fn):
def _binary_try_orig(bfn; fn):
( . as $c
| if type == "string" then fn
else
@ -15,27 +15,27 @@ def _buffer_try_orig(bfn; fn):
end
);
# overloads to support buffer
# overloads to support binary
def _orig_test($val): test($val);
def _orig_test($regex; $flags): test($regex; $flags);
def _test_buffer($regex; $flags):
( isempty(_match_buffer($regex; $flags))
def _test_binary($regex; $flags):
( isempty(_match_binary($regex; $flags))
| not
);
def test($val): _buffer_try_orig(_test_buffer($val; ""); _orig_test($val));
def test($regex; $flags): _buffer_try_orig(_test_buffer($regex; $flags); _orig_test($regex; $flags));
def test($val): _binary_try_orig(_test_binary($val; ""); _orig_test($val));
def test($regex; $flags): _binary_try_orig(_test_binary($regex; $flags); _orig_test($regex; $flags));
def _orig_match($val): match($val);
def _orig_match($regex; $flags): match($regex; $flags);
def match($val): _buffer_try_orig(_match_buffer($val); _orig_match($val));
def match($regex; $flags): _buffer_try_orig(_match_buffer($regex; $flags); _orig_match($regex; $flags));
def match($val): _binary_try_orig(_match_binary($val); _orig_match($val));
def match($regex; $flags): _binary_try_orig(_match_binary($regex; $flags); _orig_match($regex; $flags));
def _orig_capture($val): capture($val);
def _orig_capture($regex; $flags): capture($regex; $flags);
def _capture_buffer($regex; $flags):
def _capture_binary($regex; $flags):
( . as $b
| _match_buffer($regex; $flags)
| _match_binary($regex; $flags)
| .captures
| map(
( select(.name)
@ -44,25 +44,25 @@ def _capture_buffer($regex; $flags):
)
| from_entries
);
def capture($val): _buffer_try_orig(_capture_buffer($val; ""); _orig_capture($val));
def capture($regex; $flags): _buffer_try_orig(_capture_buffer($regex; $flags); _orig_capture($regex; $flags));
def capture($val): _binary_try_orig(_capture_binary($val; ""); _orig_capture($val));
def capture($regex; $flags): _binary_try_orig(_capture_binary($regex; $flags); _orig_capture($regex; $flags));
def _orig_scan($val): scan($val);
def _orig_scan($regex; $flags): scan($regex; $flags);
def _scan_buffer($regex; $flags):
def _scan_binary($regex; $flags):
( . as $b
| _match_buffer($regex; $flags)
| _match_binary($regex; $flags)
| $b[.offset:.offset+.length]
);
def scan($val): _buffer_try_orig(_scan_buffer($val; "g"); _orig_scan($val));
def scan($regex; $flags): _buffer_try_orig(_scan_buffer($regex; "g"+$flags); _orig_scan($regex; $flags));
def scan($val): _binary_try_orig(_scan_binary($val; "g"); _orig_scan($val));
def scan($regex; $flags): _binary_try_orig(_scan_binary($regex; "g"+$flags); _orig_scan($regex; $flags));
def _orig_splits($val): splits($val);
def _orig_splits($regex; $flags): splits($regex; $flags);
def _splits_buffer($regex; $flags):
def _splits_binary($regex; $flags):
( . as $b
# last null output is to do a last iteration that output from end of last match to end of buffer
| foreach (_match_buffer($regex; $flags), null) as $m (
# last null output is to do a last iteration that output from end of last match to end of binary
| foreach (_match_binary($regex; $flags), null) as $m (
{prev: null, curr: null};
( .prev = .curr
| .curr = $m
@ -73,8 +73,8 @@ def _splits_buffer($regex; $flags):
end
)
);
def splits($val): _buffer_try_orig(_splits_buffer($val; "g"); _orig_splits($val));
def splits($regex; $flags): _buffer_try_orig(_splits_buffer($regex; "g"+$flags); _orig_splits($regex; $flags));
def splits($val): _binary_try_orig(_splits_binary($val; "g"); _orig_splits($val));
def splits($regex; $flags): _binary_try_orig(_splits_binary($regex; "g"+$flags); _orig_splits($regex; $flags));
# same as regexp.QuoteMeta
def _quote_meta:
@ -87,11 +87,11 @@ def split($val): [splits($val | _quote_meta)];
def split($regex; $flags): [splits($regex; $flags)];
# TODO: rename
# same as scan but outputs buffer from start of match to end of buffer
# same as scan but outputs binary from start of match to end of binary
def _scan_toend($regex; $flags):
( . as $b
| _match_buffer($regex; $flags)
| _match_binary($regex; $flags)
| $b[.offset:]
);
def scan_toend($val): _buffer_fn(_scan_toend($val; "g"));
def scan_toend($regex; $flags): _buffer_fn(_scan_toend($regex; "g"+$flags));
def scan_toend($val): _binary_fn(_scan_toend($val; "g"));
def scan_toend($regex; $flags): _binary_fn(_scan_toend($regex; "g"+$flags));

18
pkg/interp/repl.jq
View File

@ -28,6 +28,8 @@ def _complete_keywords:
def _complete_scope:
[scope[], _complete_keywords[]];
def _complete_keys:
[keys[]?, _extkeys[]?];
# TODO: handle variables via ast walk?
# TODO: refactor this
@ -55,10 +57,7 @@ def _complete($line; $cursor_pos):
# TODO: move map/add logic to here?
| _query_completion(
if .type | . == "func" or . == "var" then "_complete_scope"
elif .type == "index" then
if (.prefix | startswith("_")) then "_extkeys"
else "keys"
end
elif .type == "index" then "_complete_keys"
else error("unreachable")
end
) as {$type, $query, $prefix}
@ -79,7 +78,7 @@ def _complete($line; $cursor_pos):
strings and
# TODO: var type really needed? just func?
(_is_ident or $type == "var") and
((_is_internal | not) or $prefix_is_internal or $type == "index") and
((_is_internal | not) or $prefix_is_internal) and
startswith($prefix)
)
)
@ -182,7 +181,7 @@ def _repl($opts): #:: a|(Opts) => @
def _read_expr:
_repeat_break(
# both _prompt and _complete want input arrays
( _readline(_prompt; {complete: "_complete", timeout: 1})
( _readline({prompt: _prompt, complete: "_complete", timeout: 1})
| if trim == "" then empty
else (., error("break"))
end
@ -216,12 +215,15 @@ def _repl($opts): #:: a|(Opts) => @
else error
end
);
if _is_completing | not then
( _options_stack(. + [$opts]) as $_
| _finally(
_repeat_break(_repl_loop);
_options_stack(.[:-1])
)
);
)
else empty
end;
def _repl_slurp($opts): _repl($opts);
def _repl_slurp: _repl({});
@ -229,7 +231,7 @@ def _repl_slurp: _repl({});
# TODO: introspect and show doc, reflection somehow?
def help:
( "Type expression to evaluate"
, "\\t Auto completion"
, "\\t Completion"
, "Up/Down History"
, "^C Interrupt execution"
, "... | repl Start a new REPL"

92
pkg/interp/testdata/buffer.fqtest vendored
View File

@ -51,9 +51,9 @@ mp3> [1, 2, 3, [1, 2, 3], .headers[0].magic] | tobytes
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0|01 02 03 01 02 03 49 44 33| |......ID3| |.: raw bits 0x0-0x8.7 (9)
mp3> [-1] | tobytes
error: buffer byte list must be bytes (0-255) got -1
error: byte in binary list must be bytes (0-255) got -1
mp3> [256] | tobytes
error: buffer byte list must be bytes (0-255) got 256
error: byte in binary list must be bytes (0-255) got 256
mp3> ^D
$ fq -d mp3 -i . /test.mp3
mp3> .frames[1] | tobits | ., .start, .stop, .size, .[4:17], (tobits, tobytes, tobitsrange, tobytesrange | ., .start, .stop, .size, .[4:17])
@ -256,41 +256,59 @@ mp3> "fq" | tobits | chunk(range(17)+1) | tobytes | tostring
"fq"
"fq"
"fq"
mp3> range(17) | [range(.) | 1 | tobits] | tobytes
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
| | |.: raw bits 0x0-NA (0)
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0|80| |.| |.: raw bits 0x0-0x0 (0.1)
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0|c0| |.| |.: raw bits 0x0-0x0.1 (0.2)
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0|e0| |.| |.: raw bits 0x0-0x0.2 (0.3)
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0|f0| |.| |.: raw bits 0x0-0x0.3 (0.4)
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0|f8| |.| |.: raw bits 0x0-0x0.4 (0.5)
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0|fc| |.| |.: raw bits 0x0-0x0.5 (0.6)
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0|fe| |.| |.: raw bits 0x0-0x0.6 (0.7)
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0|ff| |.| |.: raw bits 0x0-0x0.7 (1)
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0|ff 80| |..| |.: raw bits 0x0-0x1 (1.1)
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0|ff c0| |..| |.: raw bits 0x0-0x1.1 (1.2)
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0|ff e0| |..| |.: raw bits 0x0-0x1.2 (1.3)
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0|ff f0| |..| |.: raw bits 0x0-0x1.3 (1.4)
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0|ff f8| |..| |.: raw bits 0x0-0x1.4 (1.5)
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0|ff fc| |..| |.: raw bits 0x0-0x1.5 (1.6)
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0|ff fe| |..| |.: raw bits 0x0-0x1.6 (1.7)
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0|ff ff| |..| |.: raw bits 0x0-0x1.7 (2)
mp3> 1 | tobits(range(10)) | hex
"80"
"80"
"40"
"20"
"10"
"08"
"04"
"02"
"01"
"0080"
mp3> 1 | tobytes(range(5)) | hex
"01"
"01"
"0001"
"000001"
"00000001"
mp3> range(17) | [range(.) | 1 | tobits] | tobits | hex
""
"80"
"c0"
"e0"
"f0"
"f8"
"fc"
"fe"
"ff"
"ff80"
"ffc0"
"ffe0"
"fff0"
"fff8"
"fffc"
"fffe"
"ffff"
mp3> range(17) | [range(.) | 1 | tobits] | tobytes | hex
""
"01"
"03"
"07"
"0f"
"1f"
"3f"
"7f"
"ff"
"01ff"
"03ff"
"07ff"
"0fff"
"1fff"
"3fff"
"7fff"
"ffff"
mp3> "c9dfdac2f6ef68e5db666b6fbeee66d9c7deda66bebfbfe860bfbfbfe9d1636bbfbebf" | hex | tobits | reduce chunk(8)[] as $c ({h:[],g:[]}; .h += [(0|tobits), $c[0:7]] | .g |= . + [if length % 8 == 0 then (0|tobits) else empty end, $c[7:8]]) | .h, .g | tobytes
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x00|64 6f 6d 61 7b 77 34 72 6d 33 35 37 5f 77 33 6c|doma{w4rm357_w3l|.: raw bits 0x0-0x22.7 (35)

8
pkg/interp/testdata/completion.fqtest vendored
View File

@ -56,4 +56,12 @@ mp3> .frames\t
frames[]
mp3> .frames[]\t
.
mp3> "abc" | tobitsrange.s\t
size
start
stop
mp3> options.c\t
color
colors
compact
mp3> ^D

21
pkg/interp/testdata/funcs.fqtest vendored
View File

@ -5,4 +5,25 @@ null> "abc" | topem | "before" + . + "between" + . + "after" | frompem | tostrin
"abc"
"abc"
null>
null> (0,1,1024,99999999999999999999) as $n | (2,8,16,62,64) as $r | "\($r): \($n) \($n | toradix($r)) \($n | toradix($r) | fromradix($r))" | println
2: 0 0 0
8: 0 0 0
16: 0 0 0
62: 0 0 0
64: 0 0 0
2: 1 1 1
8: 1 1 1
16: 1 1 1
62: 1 1 1
64: 1 1 1
2: 1024 10000000000 1024
8: 1024 2000 1024
16: 1024 400 1024
62: 1024 gw 1024
64: 1024 g0 1024
2: 99999999999999999999 1010110101111000111010111100010110101100011000011111111111111111111 99999999999999999999
8: 99999999999999999999 12657072742654303777777 99999999999999999999
16: 99999999999999999999 56bc75e2d630fffff 99999999999999999999
62: 99999999999999999999 1V973MbJYWoT 99999999999999999999
64: 99999999999999999999 1mL7nyRz3___ 99999999999999999999
null> ^D

5
pkg/interp/testdata/gojq.fqtest vendored
View File

@ -1,4 +1,9 @@
# TODO: various gojq fq fork regression tests, should probably be move to fork code instead
# 0xf_ffff_ffff_fffff_fffff-1 | toradix(2,8,16)
$ fq -n '0b1111111111111111111111111111111111111111111111111111111111111111111111111110, 0o17777777777777777777777776, 0xffffffffffffffffffe'
75557863725914323419134
75557863725914323419134
75557863725914323419134
$ fq -n '[true] | all'
true
$ fq -n '{a:1, b: 2} | tostream'

12
pkg/interp/testdata/incudepath.fqtest vendored
View File

@ -1,5 +1,7 @@
/library/a.jq:
def a: "a";
/config/has_error.jq:
)
$ fq -L /library -n 'include "a"; a'
"a"
$ fq --include-path /library -n 'include "a"; a'
@ -12,3 +14,13 @@ $ fq -L /wrong -n 'include "a"; a'
exitcode: 3
stderr:
error: arg:1:0: open a.jq: file does not exist
$ fq -n 'include "@config/a";'
exitcode: 3
stderr:
error: arg:1:0: open testdata/config/a.jq: no such file or directory
$ fq -n 'include "@config/missing?";'
null
$ fq -n 'include "@config/has_error?";'
exitcode: 3
stderr:
error: arg:1:0: /config/has_error.jq:1:1: parse: unexpected token ")"

6
pkg/interp/testdata/paste.fqtest vendored Normal file
View File

@ -0,0 +1,6 @@
$ fq -i
null> paste
"test\n"
null> ^D
stdin:
test

4
pkg/interp/testdata/value_array.fqtest vendored
View File

@ -166,14 +166,14 @@ mp3> .headers._bits | ., type, length?
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x00|49 44 33 04 00 00 00 00 00 23 54 53 53 45 00 00|ID3......#TSSE..|.: raw bits 0x0-0x2c.7 (45)
* |until 0x2c.7 (45) | |
"buffer"
"binary"
360
mp3>
mp3> .headers._bytes | ., type, length?
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x00|49 44 33 04 00 00 00 00 00 23 54 53 53 45 00 00|ID3......#TSSE..|.: raw bits 0x0-0x2c.7 (45)
* |until 0x2c.7 (45) | |
"buffer"
"binary"
45
mp3>
mp3> .headers._error | ., type, length?

4
pkg/interp/testdata/value_boolean.fqtest vendored
View File

@ -72,13 +72,13 @@ mp3> .headers[0].flags.unsynchronisation._path | ., type, length?
mp3> .headers[0].flags.unsynchronisation._bits | ., type, length?
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0| 00 | . |.: raw bits 0x5-0x5 (0.1)
"buffer"
"binary"
1
mp3>
mp3> .headers[0].flags.unsynchronisation._bytes | ., type, length?
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0| 00 | . |.: raw bits 0x5-0x5 (0.1)
"buffer"
"binary"
0
mp3>
mp3> .headers[0].flags.unsynchronisation._error | ., type, length?

4
pkg/interp/testdata/value_json_array.fqtest vendored
View File

@ -81,13 +81,13 @@ json> (.)._path | ., type, length?
json> (.)._bits | ., type, length?
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0|5b 5d| |[]| |.: raw bits 0x0-0x1.7 (2)
"buffer"
"binary"
16
json>
json> (.)._bytes | ., type, length?
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0|5b 5d| |[]| |.: raw bits 0x0-0x1.7 (2)
"buffer"
"binary"
2
json>
json> (.)._error | ., type, length?

4
pkg/interp/testdata/value_json_object.fqtest vendored
View File

@ -71,13 +71,13 @@ json> (.)._path | ., type, length?
json> (.)._bits | ., type, length?
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0|7b 7d| |{}| |.: raw bits 0x0-0x1.7 (2)
"buffer"
"binary"
16
json>
json> (.)._bytes | ., type, length?
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0|7b 7d| |{}| |.: raw bits 0x0-0x1.7 (2)
"buffer"
"binary"
2
json>
json> (.)._error | ., type, length?

4
pkg/interp/testdata/value_null.fqtest vendored
View File

@ -84,13 +84,13 @@ mp3> .headers[0].padding._path | ., type, length?
mp3> .headers[0].padding._bits | ., type, length?
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x20| 00 00 00 00 00 00 00 00 00 00 | .......... |.: raw bits 0x23-0x2c.7 (10)
"buffer"
"binary"
80
mp3>
mp3> .headers[0].padding._bytes | ., type, length?
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x20| 00 00 00 00 00 00 00 00 00 00 | .......... |.: raw bits 0x23-0x2c.7 (10)
"buffer"
"binary"
10
mp3>
mp3> .headers[0].padding._error | ., type, length?

4
pkg/interp/testdata/value_number.fqtest vendored
View File

@ -72,13 +72,13 @@ mp3> .headers[0].version._path | ., type, length?
mp3> .headers[0].version._bits | ., type, length?
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0| 04 | . |.: raw bits 0x3-0x3.7 (1)
"buffer"
"binary"
8
mp3>
mp3> .headers[0].version._bytes | ., type, length?
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0| 04 | . |.: raw bits 0x3-0x3.7 (1)
"buffer"
"binary"
1
mp3>
mp3> .headers[0].version._error | ., type, length?

4
pkg/interp/testdata/value_object.fqtest vendored
View File

@ -88,13 +88,13 @@ mp3> .headers[0].flags._path | ., type, length?
mp3> .headers[0].flags._bits | ., type, length?
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0| 00 | . |.: raw bits 0x5-0x5.7 (1)
"buffer"
"binary"
8
mp3>
mp3> .headers[0].flags._bytes | ., type, length?
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0| 00 | . |.: raw bits 0x5-0x5.7 (1)
"buffer"
"binary"
1
mp3>
mp3> .headers[0].flags._error | ., type, length?

4
pkg/interp/testdata/value_string.fqtest vendored
View File

@ -84,13 +84,13 @@ mp3> .headers[0].magic._path | ., type, length?
mp3> .headers[0].magic._bits | ., type, length?
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0|49 44 33 |ID3 |.: raw bits 0x0-0x2.7 (3)
"buffer"
"binary"
24
mp3>
mp3> .headers[0].magic._bytes | ., type, length?
|00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|
0x0|49 44 33 |ID3 |.: raw bits 0x0-0x2.7 (3)
"buffer"
"binary"
3
mp3>
mp3> .headers[0].magic._error | ., type, length?

2
pkg/scalar/scalar.go
View File

@ -42,7 +42,7 @@ func (df DisplayFormat) FormatBase() int {
}
type S struct {
Actual interface{} // int, int64, uint64, float64, string, bool, []byte, bitio.BitReaderAtSeeker,
Actual interface{} // nil, int, int64, uint64, float64, string, bool, []byte, *bit.Int, bitio.BitReaderAtSeeker,
ActualDisplay DisplayFormat
Sym interface{}
SymDisplay DisplayFormat