diff --git a/.vscode/settings.json b/.vscode/settings.json index 10cb0813..114f66d0 100644 --- a/.vscode/settings.json +++ b/.vscode/settings.json @@ -167,8 +167,8 @@ "torepr", "tosym", "tovalue", - "toxml", - "toxmlentities", + "to_xml", + "to_xmlentities", "traf", "trak", "trex", diff --git a/Makefile b/Makefile index fea6a5a4..2248010c 100644 --- a/Makefile +++ b/Makefile @@ -46,7 +46,7 @@ doc/%.svg: fq (cd doc ; ../$@.sh ../fq) | go run github.com/wader/ansisvg@master > $@ doc/formats.svg: fq - # ignore graphviz version as it causes diff when nothing has changed + @# ignore graphviz version as it causes diff when nothing has changed ./fq -rnf doc/formats_diagram.jq | dot -Tsvg | sed 's/Generated by graphviz.*//' >doc/formats.svg doc/file.mp3: Makefile @@ -88,8 +88,8 @@ update-gomod: always # try to decode crash with all formats in order to see which one paniced: # cat format/testdata/fuzz/FuzzFormats/... | go run dev/fuzzbytes.go | go run . -d bytes '. as $b | formats | keys[] as $f | $b | decode($f)' # convert crash into raw bytes: -# cat format/testdata/fuzz/FuzzFormats/... | go run dev/fuzzbytes.go | fq -d bytes tobase64 -# fq -n '"..." | frombase64 | ...' +# cat format/testdata/fuzz/FuzzFormats/... | go run dev/fuzzbytes.go | fq -d bytes to_base64 +# fq -n '"..." | from_base64 | ...' fuzz: always # in other terminal: tail -f /tmp/repanic FUZZTEST=1 REPANIC_LOG=/tmp/repanic go test -v -run Fuzz -fuzz=Fuzz ./format/ diff --git a/README.md b/README.md index cb0fc45f..e9bf3d4d 100644 --- a/README.md +++ b/README.md @@ -163,7 +163,7 @@ For details see [formats.md](doc/formats.md) and [usage.md](doc/usage.md). Use one of the methods listed below or download a pre-built [release](https://github.com/wader/fq/releases) for macOS, Linux or Windows. Unarchive it and move the executable to `PATH` etc. -On macOS if you don't install using a method below you might have to manually allow the binary to run. This can be done by trying to run the binary, ignore the warning and then go into security preference and allow it. Same can be done with this command: +On macOS if you don't install using one of the method below you might have to manually allow the binary to run. This can be done by trying to run the binary, ignore the warning and then go into security preference and allow it. Same can be done with this command: ```sh xattr -d com.apple.quarantine fq && spctl --add fq @@ -241,7 +241,7 @@ cp "$(go env GOPATH)/bin/fq" /usr/local/bin To build, run and test from source: ```sh -# build an run +# build and run go run . go run . -d mp3 file.mp3 # just build diff --git a/dev/snippets.jq b/dev/snippets.jq index 6ca6c9fa..9a8848d8 100644 --- a/dev/snippets.jq +++ b/dev/snippets.jq @@ -36,8 +36,8 @@ def urldecode: # ex: .frames | changes(.header.sample_rate) def changes(f): streaks_by(f)[].[0]; -def toradix62sp: toradix(62; "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"); -def fromradix62sp: fromradix(62; { +def to_radix62sp: to_radix(62; "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"); +def from_radix62sp: from_radix(62; { "0": 0, "1": 1, "2": 2, "3": 3,"4": 4, "5": 5, "6": 6, "7": 7, "8": 8, "9": 9, "a": 10, "b": 11, "c": 12, "d": 13, "e": 14, "f": 15, "g": 16, "h": 17, "i": 18, "j": 19, "k": 20, "l": 21, "m": 22, "n": 23, diff --git a/doc/demo.svg b/doc/demo.svg index 8ac8d85d..eee01e80 100644 --- a/doc/demo.svg +++ b/doc/demo.svg @@ -1,4 +1,4 @@ - + ` and `" | tovalue' file. ### Force decode a single box ```sh -$ fq -n '"AAAAHGVsc3QAAAAAAAAAAQAAADIAAAQAAAEAAA==" | frombase64 | mp4({force:true}) | d' +$ fq -n '"AAAAHGVsc3QAAAAAAAAAAQAAADIAAAQAAAEAAA==" | from_base64 | mp4({force:true}) | d' ``` ### Lookup mp4 box using a mp4 box path. @@ -887,7 +887,7 @@ Which variant to use depends a bit what you want to do. The object variant might to query for a specific value but array might be easier to use to generate xml or to query after all elements of some kind etc. -Encoding is done using the `toxml` function and it will figure what variant that is used based on the input value. +Encoding is done using the `to_xml` function and it will figure what variant that is used based on the input value. Is has two optional options `indent` and `attribute_prefix`. ### Elements as object @@ -930,7 +930,7 @@ $ echo 'bbbccc' | fq '.a.c["#text"]' "ccc" # decode to object and encode to xml -$ echo 'bbbccc' | fq -r -d xml -o seq=true 'toxml({indent:2})' +$ echo 'bbbccc' | fq -r -d xml -o seq=true 'to_xml({indent:2})' bbb @@ -973,7 +973,7 @@ $ echo 'bbbccc' | fq -d xml -o array=true ] # decode to array and encode to xml -$ echo 'bbbccc' | fq -r -d xml -o array=true -o seq=true 'toxml({indent:2})' +$ echo 'bbbccc' | fq -r -d xml -o array=true -o seq=true 'to_xml({indent:2})' bbb diff --git a/doc/formats.svg b/doc/formats.svg index a49e3549..d7f4849f 100644 --- a/doc/formats.svg +++ b/doc/formats.svg @@ -8,21 +8,21 @@ viewBox="0.00 0.00 4055.80 2095.01" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"> formats - + adts - + adts - + adts_frame adts_frame - + adts_frame - + aac_frame @@ -34,7 +34,7 @@ aac_frame - + aac_frame @@ -46,9 +46,9 @@ apev2 - + apev2 - + image @@ -66,11 +66,11 @@ jpeg - + jpeg - + exif - + icc_profile @@ -82,55 +82,55 @@ mp4 - + mp4 - + aac_frame - + av1_ccr - + av1_frame - + avc_au - + avc_dcr - + flac_frame - + flac_metadatablocks - + hevc_au - + hevc_dcr - + icc_profile - + id3v2 - + image - + jpeg - + mp3_frame - + mpeg_es - + mpeg_pes_packet - + opus_packet - + png - + prores_frame - + protobuf_widevine - + pssh_playready - + vorbis_packet - + vp9_frame - + vpx_ccr @@ -142,11 +142,11 @@ png - + png - + icc_profile - + exif @@ -158,9 +158,9 @@ tiff - + tiff - + icc_profile @@ -172,9 +172,9 @@ webp - + webp - + vp8_frame @@ -186,7 +186,7 @@ gif - + gif @@ -198,9 +198,9 @@ ar - + ar - + probe @@ -230,15 +230,15 @@ avi - + avi - + avc_au - + hevc_au - + mp3_frame - + flac_frame @@ -250,9 +250,9 @@ bitcoin_blkdat - + bitcoin_blkdat - + bitcoin_block @@ -264,9 +264,9 @@ bzip2 - + bzip2 - + probe @@ -278,11 +278,11 @@ flac - + flac - + flac_metadatablocks - + flac_frame @@ -294,9 +294,9 @@ gzip - + gzip - + probe @@ -314,9 +314,9 @@ macho_fat - + macho_fat - + macho @@ -328,7 +328,7 @@ macho - + macho @@ -340,45 +340,45 @@ matroska - + matroska - + aac_frame - + av1_ccr - + av1_frame - + avc_au - + avc_dcr - + flac_frame - + flac_metadatablocks - + hevc_au - + hevc_dcr - + image - + mp3_frame - + mpeg_asc - + mpeg_pes_packet - + mpeg_spu - + opus_packet - + vorbis_packet - + vp8_frame - + vp9_cfm - + vp9_frame @@ -390,17 +390,17 @@ mp3 - + mp3 - + id3v2 - + id3v1 - + id3v11 - + apev2 - + mp3_frame @@ -424,17 +424,17 @@ ogg - + ogg - + ogg_page - + vorbis_packet - + opus_packet - + flac_metadatablock - + flac_frame @@ -446,13 +446,13 @@ pcap - + pcap - + link_frame - + tcp_stream - + ipv4_packet @@ -464,13 +464,13 @@ pcapng - + pcapng - + link_frame - + tcp_stream - + ipv4_packet @@ -482,9 +482,9 @@ tar - + tar - + probe @@ -502,13 +502,13 @@ wav - + wav - + id3v2 - + id3v1 - + id3v11 @@ -526,9 +526,9 @@ zip - + zip - + probe @@ -540,7 +540,7 @@ apple_bookmark - + apple_bookmark @@ -552,7 +552,7 @@ avro_ocf - + avro_ocf @@ -564,7 +564,7 @@ bplist - + bplist @@ -576,7 +576,7 @@ elf - + elf @@ -594,7 +594,7 @@ json - + json @@ -606,7 +606,7 @@ jsonl - + jsonl @@ -618,7 +618,7 @@ mpeg_ts - + mpeg_ts @@ -630,7 +630,7 @@ toml - + toml @@ -642,7 +642,7 @@ tzif - + tzif @@ -654,7 +654,7 @@ wasm - + wasm @@ -666,7 +666,7 @@ xml - + xml @@ -678,7 +678,7 @@ yaml - + yaml @@ -690,15 +690,15 @@ av1_frame - + av1_frame - + av1_obu av1_obu - + av1_obu @@ -710,21 +710,21 @@ avc_annexb - + avc_annexb - + avc_nalu avc_nalu - + avc_nalu - + avc_sps - + avc_pps - + avc_sei @@ -736,7 +736,7 @@ avc_sps - + avc_sps @@ -748,7 +748,7 @@ avc_pps - + avc_pps @@ -760,7 +760,7 @@ avc_sei - + avc_sei @@ -772,9 +772,9 @@ avc_au - + avc_au - + avc_nalu @@ -786,9 +786,9 @@ avc_dcr - + avc_dcr - + avc_nalu @@ -806,9 +806,9 @@ hevc_au - + hevc_au - + hevc_nalu @@ -820,9 +820,9 @@ mp3_frame - + mp3_frame - + mp3_frame_tags @@ -834,7 +834,7 @@ flac_frame - + flac_frame @@ -846,13 +846,13 @@ hevc_nalu - + hevc_nalu - + hevc_vps - + hevc_pps - + hevc_sps @@ -876,9 +876,9 @@ bitcoin_block - + bitcoin_block - + bitcoin_transaction @@ -890,9 +890,9 @@ bitcoin_transaction - + bitcoin_transaction - + bitcoin_script @@ -904,7 +904,7 @@ bitcoin_script - + bitcoin_script @@ -916,9 +916,9 @@ bsd_loopback_frame - + bsd_loopback_frame - + inet_packet @@ -936,9 +936,9 @@ ipv4_packet - + ipv4_packet - + ip_packet @@ -950,9 +950,9 @@ ipv6_packet - + ipv6_packet - + ip_packet @@ -970,9 +970,9 @@ ether8023_frame - + ether8023_frame - + inet_packet @@ -990,9 +990,9 @@ flac_metadatablocks - + flac_metadatablocks - + flac_metadatablock @@ -1004,13 +1004,13 @@ flac_metadatablock - + flac_metadatablock - + flac_streaminfo - + flac_picture - + vorbis_comment @@ -1022,7 +1022,7 @@ flac_streaminfo - + flac_streaminfo @@ -1034,9 +1034,9 @@ flac_picture - + flac_picture - + image @@ -1048,9 +1048,9 @@ vorbis_comment - + vorbis_comment - + flac_picture @@ -1080,9 +1080,9 @@ hevc_annexb - + hevc_annexb - + hevc_nalu @@ -1094,7 +1094,7 @@ hevc_vps - + hevc_vps @@ -1106,7 +1106,7 @@ hevc_pps - + hevc_pps @@ -1118,7 +1118,7 @@ hevc_sps - + hevc_sps @@ -1130,9 +1130,9 @@ hevc_dcr - + hevc_dcr - + hevc_nalu @@ -1144,9 +1144,9 @@ id3v2 - + id3v2 - + image @@ -1170,9 +1170,9 @@ udp_datagram - + udp_datagram - + udp_payload @@ -1184,7 +1184,7 @@ icmp - + icmp @@ -1196,7 +1196,7 @@ icmpv6 - + icmpv6 @@ -1208,7 +1208,7 @@ tcp_segment - + tcp_segment @@ -1226,7 +1226,7 @@ exif - + exif @@ -1238,7 +1238,7 @@ icc_profile - + icc_profile @@ -1316,7 +1316,7 @@ av1_ccr - + av1_ccr @@ -1328,7 +1328,7 @@ mpeg_asc - + mpeg_asc @@ -1340,7 +1340,7 @@ mpeg_pes_packet - + mpeg_pes_packet @@ -1352,7 +1352,7 @@ mpeg_spu - + mpeg_spu @@ -1364,9 +1364,9 @@ opus_packet - + opus_packet - + vorbis_comment @@ -1378,9 +1378,9 @@ vorbis_packet - + vorbis_packet - + vorbis_comment @@ -1392,7 +1392,7 @@ vp8_frame - + vp8_frame @@ -1404,7 +1404,7 @@ vp9_cfm - + vp9_cfm @@ -1416,7 +1416,7 @@ vp9_frame - + vp9_frame @@ -1458,7 +1458,7 @@ id3v1 - + id3v1 @@ -1470,7 +1470,7 @@ id3v11 - + id3v11 @@ -1482,7 +1482,7 @@ mp3_frame_vbri - + mp3_frame_vbri @@ -1494,7 +1494,7 @@ mp3_frame_xing - + mp3_frame_xing @@ -1614,11 +1614,11 @@ mpeg_es - + mpeg_es - + mpeg_asc - + vorbis_packet @@ -1636,7 +1636,7 @@ prores_frame - + prores_frame @@ -1648,9 +1648,9 @@ protobuf_widevine - + protobuf_widevine - + protobuf @@ -1662,7 +1662,7 @@ pssh_playready - + pssh_playready @@ -1674,7 +1674,7 @@ vpx_ccr - + vpx_ccr @@ -1710,7 +1710,7 @@ protobuf - + protobuf @@ -1722,11 +1722,11 @@ mpeg_pes - + mpeg_pes - + mpeg_pes_packet - + mpeg_spu @@ -1768,7 +1768,7 @@ ogg_page - + ogg_page @@ -1822,9 +1822,9 @@ sll2_packet - + sll2_packet - + inet_packet @@ -1836,9 +1836,9 @@ sll_packet - + sll_packet - + inet_packet @@ -1850,11 +1850,11 @@ rtmp - + rtmp - + amf0 - + mpeg_asc @@ -1866,7 +1866,7 @@ dns_tcp - + dns_tcp @@ -1902,7 +1902,7 @@ amf0 - + amf0 @@ -1950,7 +1950,7 @@ dns - + dns @@ -1992,67 +1992,67 @@ asn1_ber - + asn1_ber bencode - + bencode bits - + bits bson - + bson bytes - + bytes cbor - + cbor csv - + csv fairplay_spc - + fairplay_spc html - + html markdown - + markdown msgpack - + msgpack diff --git a/doc/formats_diagram.jq b/doc/formats_diagram.jq index cc771bed..edd83fbe 100755 --- a/doc/formats_diagram.jq +++ b/doc/formats_diagram.jq @@ -1,7 +1,7 @@ #!/usr/bin/env fq -rnf def color: - tomd5 | [.[range(3)]] | map(band(.; 0x7f)+60 | toradix(16) | "0"[length:]+.) | join(""); + to_md5 | [.[range(3)]] | map(band(.; 0x7f)+60 | to_radix(16) | "0"[length:]+.) | join(""); def _formats_dot: def _record($title; $fields): diff --git a/doc/usage.md b/doc/usage.md index b4ff5f40..b6bb0838 100644 --- a/doc/usage.md +++ b/doc/usage.md @@ -38,7 +38,7 @@ fq dv file # same as fq 'd({verbose: true})' file -# JSON repersenation for whole file +# JSON representation for whole file fq tovalue file # JSON but raw bit fields truncated fq -o bits_format=truncate tovalue file @@ -51,7 +51,7 @@ fq 'grep(123)' file # grep whole tree by condition fq 'grep_by(. >= 100 and . =< 100)' file -# recursively look for values fullfilling some condition +# recursively look for values fulfilling some condition fq '.. | select(.type=="trak")?' file fq 'grep_by(.type=="trak")' file # grep_by(f) is alias for .. | select(f)?, that is: recuse, select and ignore errors @@ -73,7 +73,7 @@ fq -o force=true -d mp4 file.mp4 ### Display output -`display` or `d` is the main function for displying values and is also the function that will be used if no other output function is explicitly used. If its input is a decode value it will output a dump and tree structure or otherwise it will output as JSON. +`display` or `d` is the main function for displaying values and is also the function that will be used if no other output function is explicitly used. If its input is a decode value it will output a dump and tree structure or otherwise it will output as JSON. Below demonstrates some usages: @@ -81,17 +81,17 @@ First and second example does the same thing, inputs `"hello"` to `display`. ![fq demo](display_json.svg) -In the next few examples we select out the first "edit list" box in an mp4 file, it's a list of which part of media track to be included during playback, and displays it in various ways. +In the next few examples we select out the first "edit list" box in an mp4 file, it's a list of which part of the media track to be included during playback, and displays it in various ways. 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 jq path for the value. +First row shows a 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`. -- Hex repersenation of input bits for value. Will show the whole byte even if the value only partially uses bits from it. +- Hex representation of input bits for value. Will show the whole byte even if the value only partially uses bits from it. - ASCII representation of input bits for value. Will show the whole byte even if the value only partially uses bits from it. - Tree structure of decoded value, symbolic value and description. @@ -110,7 +110,7 @@ Same but verbose `dv`: In verbose mode bit ranges and array element names as shown. -Bit range uses `bytes.bits` notation. For example `type` start at byte `0xd69` bit `0` (left out if zero) and ends at `0xd6c` bit `7` (inclusive) and have byte size of `4`. +Bit range uses `bytes.bits` notation. For example `type` starts at byte `0xd69` bit `0` (left out if zero) and ends at `0xd6c` bit `7` (inclusive) and have byte size of `4`. There are also some other `display` aliases: - `da` same as `display({array_truncate: 0})` which will not truncate long arrays. @@ -195,13 +195,13 @@ fq '.frames[0:10] | map(tobytesrange.start)' file.mp3 ```sh # decode byte range 100 to end as mp3_frame fq -d bytes '.[100:] | mp3_frame | d' file.mp3 -# decode byte range 10 bytes from .somefield and preseve relative position in file +# decode byte range 10 bytes from .somefield and preserve relative position in file fq '.somefield | tobytesrange[10:] | mp3_frame | d' file.mp3 ``` #### Show AVC SPS difference between two mp4 files -`-n` tells fq to not have an implicit `input`, `f` is function to select out some interesting value, call `diff` with two arguments, +`-n` tells fq to not have an implicit `input`, `f` is a function to select out some interesting value, call `diff` with two arguments, decoded value for `a.mp4` and `b.mp4` filtered thru `f`. ```sh @@ -210,7 +210,7 @@ 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 for value. Redirect bytes to a file. +Recursively look for the 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 @@ -218,7 +218,7 @@ fq 'first(.. | select(format=="jpeg")) | tobytes' file > file.jpeg #### Sample size histogram -Recursively look for a all sample size boxes "stsz" and use `?` to ignore errors when doing `.type` on arrays etc. Save reference to box, count unique values, save the max, output the path to the box and output a historgram scaled to 0-100. +Recursively look for a all sample size boxes "stsz" and use `?` to ignore errors when doing `.type` on arrays etc. Save reference to box, count unique values, save the max, output the path to the box and output a histogram scaled to 0-100. ```sh fq '.. | select(.type=="stsz")? as $stsz | .entries | count | max_by(.[1])[1] as $m | ($stsz | topath | path_to_expr), (.[] | "\(.[0]): \((100*.[1]/$m)*"=") \(.[1])") | println' file.mp4 @@ -281,21 +281,21 @@ For a more convenient jq experience these might be interesting: - [vscode-jq](https://github.com/wader/vscode-jq) - [jq-lsp](https://github.com/wader/jq-lsp) -Common beginner gotcha are: +Common beginner gotchas are: - jq's use of `;` and `,`. jq uses `;` as argument separator and `,` as output separator. To call a function `f` with two arguments use `f(1; 2)`. If you do `f(1, 2)` you pass a -single argument `1, 2` (a lambda expression that output `1` and then output `2`) to `f`. +single argument `1, 2` (a lambda expression that outputs `1` and then outputs `2`) to `f`. - Expressions can return or "output" zero or more values. This is how loops, foreach etc is 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. +fq has two additional types compared to jq, decode value and binary. In standard jq expressions they will in most cases 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. +This type is returned by decoders and it is used to represent parts of the decoded 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 @@ -317,18 +317,18 @@ Each non-compound decode value has these properties: - `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. +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 expressions this is not needed as it will be done automatically. ### 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. +Use `tobits` and `tobytes` to create them from 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. +There is also `tobitsrange` and `tobytesrange` which does the same thing but will preserve its 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. +- `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 work 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` @@ -369,13 +369,19 @@ TODO: padding and alignment ## Functions +All decode functions are available in two forms, just `` (like `mp3`) that returns a decode value on error and `from_` which throws error on decode error. + +Note that jq sometimes uses the notation `name/0`, `name/1` etc in error messages and documentation which means `/`. Same function names with different arity are treated as separate functions, but are usually related in some way in practice. + +### Function added in fq + - All standard library functions from jq - Adds a few new general functions: - `print`, `println`, `printerr`, `printerrln` prints to stdout and stderr. - `group` group values, same as `group_by(.)`. - `streaks`, `streaks_by(f)` like `group` but groups streaks based on condition. - `count`, `count_by(f)` like `group` but counts groups lengths. - - `debug(f)` like `debug` but uses arg to produce debug message. `{a: 123} | debug({a}) | ...`. + - `debug(f)` like `debug` but uses arg to produce a debug message. `{a: 123} | debug({a}) | ...`. - `path_to_expr` from `["key", 1]` to `".key[1]"`. - `expr_to_path` from `".key[1]"` to `["key", 1]`. - `diff($a; $b)` produce diff object between two values. @@ -394,7 +400,7 @@ unary uses input and if more than one argument all as arguments ignoring the inp - `toactual`, `toactual($opts)` actual value (usually the decoded value) - `tosym`, `tosym($opts)` symbolic value (mapped etc) - `todescription` description of value - - `torepr` convert decode value into what it reptresents. For example convert msgpack decode value + - `torepr` converts decode value into what it reptresents. For example convert msgpack decode value into a value representing its JSON representation. - All regexp functions work with binary as input and pattern argument with these differences compared to when using string input: @@ -402,14 +408,14 @@ unary uses input and if more than one argument all as arguments ignoring the inp - For `capture` the `.string` value is a binary. - If pattern is a binary it will be matched literally and not as a regexp. - If pattern is a binary or flags include "b" each input byte will be read as separate code points - - String function are not overloaded to support binary for now as some of them are bahaviours that might be confusing. + - String functions are not overloaded to support binary for now as some of them might have behaviors that might be confusing. - `explode` is overloaded to work with binary. Will explode into array of the unit of the binary. end of binary. instead of possibly multi-byte UTF-8 codepoints. This allows to match raw bytes. Ex: `match("\u00ff"; "b")` will match the byte `0xff` and not the UTF-8 encoded codepoint for 255, `match("[^\u00ff]"; "b")` will match all non-`0xff` bytes. - `grep` functions take 1 or 2 arguments. First is a scalar to match, where a string is - treated as a regexp. A binary will be matches exact bytes. Second argument are regexp + treated as a regexp. A binary will match exact bytes. Second argument are regexp flags with addition that "b" will treat each byte in the input binary as a code point, this makes it possible to match exact bytes. - `grep($v)`, `grep($v; $flags)` recursively match value and binary @@ -418,39 +424,55 @@ unary uses input and if more than one argument all as arguments ignoring the inp - `fgrep($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"))`. - Binary: - - `tobits` - Transform input to binary with bit as unit, does not preserving source range, will start at zero. + - `tobits` - Transform input to binary with bit as unit, does not preserve 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. + - `tobytes` - Transform input to binary with byte as unit, does not preserve 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. + - `.[start:end]`, `.[:end]`, `.[start:]` - Slice binary from start to end preserve 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. +- All decode functions take an 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 you currently have to do `fq -d bytes 'mp3({force: true})' file`. - `decode`, `decode("")`, `decode(""; $opts)` decode format - `probe`, `probe($opts)` probe and decode format -- `mp3`, `mp3($opts)`, ..., ``, `($opts)` same as `decode("")`, `decode(""; $opts)` decode as format +- `mp3`, `mp3($opts)`, ..., ``, `($opts)` same as `decode("")`, `decode(""; $opts)` decode as format and return decode value even on decode error. +- `from_mp3`, `from_mp3($opts)`, ..., `from_`, `from_($opts)` same as `decode("")`, `decode(""; $opts)` decode as format but throw error on decode error. - Display shows hexdump/ASCII/tree for decode values and jq value for other types. - `d`/`d($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 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`/`repl($opts)` nested REPL, must be last in a pipeline. `1 | repl`, can "slurp" outputs. Ex: `1, 2, 3 | repl`, `[1,2,3] | repl({compact: true})`. -- `slurp("")` slurp outputs and save them to `$name`, must be last in pipeline. Will be available as global array `$name`. Ex `1,2,3 | slurp("a")`, `$a[]` same as `spew("a")`. -- `spew`/`spew("")` output previously slurped values. `spew` outputs all slurps as an object, `spew("")` outouts one slurp. Ex: `spew("a")`. +- `slurp("")` slurp outputs and save them to `$name`, must be last in the pipeline. Will be available as a global array `$name`. Ex `1,2,3 | slurp("a")`, `$a[]` same as `spew("a")`. +- `spew`/`spew("")` output previously slurped values. `spew` outputs all slurps as an object, `spew("")` outputs one slurp. Ex: `spew("a")`. - `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. + - Ex: `paste | from_pem | asn1_ber | repl` read from stdin then decode and start a new sub-REPL with result. + +### Naming inconsistencies + +jq's naming conversion is a bit inconsistent, some standard library functions are named `tojson` while others `from_entries`. fq follows this tradition a bit by but tries to use snake_case unless there is a good reason. + +Here are all the non-snake_case functions added by. Most of them deal with decode and binary values which are new "primitive" types: +- `toactual` +- `tobits` +- `tobitsrange` +- `tobytes` +- `tobytesrange` +- `todescription` +- `topath` +- `torepr` +- `tosym` +- `tovalue` ### Encodings, serializations and hashes -In an addition to binary formats fq also support reading to and from encodings and serialization formats. +In addition to binary formats fq also support reading to and from encodings and serialization formats. At the moment fq does not have any dedicated argument for serialization formats but raw string input `-R` slurp `-s` and raw string output `-r` can make things easier. The combination `-Rs` will read all inputs into one string (same as jq). -Note that `from*` functions output jq values and `to*` takes jq values as input so in some cases not all information will be properly preserved. For example for the element and attribute order might change and text and comment nodes might move or be merged. [yq](https://github.com/mikefarah/yq) might be a better tool if that is needed. +Note that `from*` functions output jq values and `to*` takes jq values as input so in some cases not all information will be properly preserved. For example, for the element and attribute order might change and text and comment nodes might move or be merged. [yq](https://github.com/mikefarah/yq) might be a better tool if that is needed. Some example usages: @@ -463,19 +485,19 @@ $ fq '...' file.yml $ fq -r 'tojson({indent:2})' file.yml # add token to URL -$ echo -n "https://host.org" | fq -Rsr 'fromurl | .user.username="token" | tourl' +$ echo -n "https://host.org" | fq -Rsr 'from_url | .user.username="token" | tourl' https://token@host.org # top 3 hosts in src or href attributes: # -d to decode as html, can't be probed as html5 parsers always produce some parse tree # [...] to start collect values into an array # .. | ."@src"?, ."@href"? | values, recurse and try (?) to get src and href attributes and filter out nulls -# fromurl.host | values, parse as url and filter out those without a host +# from_url.host | values, parse as url and filter out those without a host # count to count unique values, returns [[key, count], ...] # reverse sort by count and pick first 3 # map [key, count] tuples into {key: key, values: count} # from_entries, convert into object -$ curl -s https://www.discogs.com/ | fq -d html '[.. | ."@src"?, ."@href"? | values | fromurl.host | values] | count | sort_by(-.[1])[0:3] | map({key: .[0], value: .[1]}) | from_entries' +$ curl -s https://www.discogs.com/ | fq -d html '[.. | ."@src"?, ."@href"? | values | from_url.host | values] | count | sort_by(-.[1])[0:3] | map({key: .[0], value: .[1]}) | from_entries' { "blog.discogs.com": 9, "st.discogs.com": 10, @@ -488,7 +510,7 @@ $ fq -i . <(curl -sL https://github.com/stefangabos/world_countries/archive/mas # select from interesting xml file zip> .local_files[] | select(.file_name == "world_countries-master/data/countries/en/world.xml").uncompressed | repl # convert xml into jq value -> .local_files[95].uncompressed string> fromxml | repl +> .local_files[95].uncompressed string> from_xml | repl # sort countries by and select the first one >> object> .countries.country | sort_by(."@name") | first | repl # see what current input is @@ -500,7 +522,7 @@ zip> .local_files[] | select(.file_name == "world_countries-master/data/countrie "@name": "Afghanistan" } # remove "@" prefix from keys and convert to YAML and print it ->>> object> with_entries(.key |= .[1:]) | toyaml | print +>>> object> with_entries(.key |= .[1:]) | to_yaml | print alpha2: af alpha3: afg id: "4" @@ -512,21 +534,21 @@ name: Afghanistan zip> ^D ``` -- `fromxml`/`fromxml($opts)` Parse XML into jq value.
+- `from_xml`/`from_xml($opts)` Parse XML into jq value.
`{seq: true}` preserve element ordering if more than one sibling.
- `{array: true}` use nested `[name, attributes, children]` arrays to represent elements. Attributes will be `null` if none and children will be `[]` if none, this is to make it easier to work it. `toxml` does not require this.
-- `fromhtml`/`fromhtml($opts)` Parse HTML into jq value.
- Similar to `fromxml` but parses html5 in non-script mode. Will always have a `html` root with `head` and `body` elements.
+ `{array: true}` use nested `[name, attributes, children]` arrays to represent elements. Attributes will be `null` if none and children will be `[]` if none, this is to make it easier to work with as the array as 3 values. `to_xml` does not require this.
+- `from_html`/`from_html($opts)` Parse HTML into jq value.
+ Similar to `from_xml` but parses html5 in non-script mode. Will always have a `html` root with `head` and `body` elements.
`{array: true}` use nested arrays to represent elements.
`{seq: true}` preserve element ordering if more than one sibling.
-- `toxml`/`toxml($opts})` Serialize jq value into XML.
+- `to_xml`/`to_xml($opts})` Serialize jq value into XML.
`{indent: number}` indent child elements.
Assumes object representation if input is an object, and nested arrays if input is an array.
Will automatically add a root `doc` element if jq value has more then one root element.
If a `#seq` is found on at least one element all siblings will be sort by sequence number. Attributes are always sorted.
XML elements can be represented as jq value in two ways, as objects (inspired by [mxj](https://github.com/clbanning/mxj) and [xml.com's Converting Between XML and JSON -](https://www.xml.com/pub/a/2006/05/31/converting-between-xml-and-json.html)) or nested arrays. Both representations are lossy and might lose ordering of elements, text nodes and comments. In object representation `fromxml`, `fromhtml` and `toxml` support `{seq:true}` option to parse/serialize `{"#seq"=}` attributes to preserve element sibling ordering. +](https://www.xml.com/pub/a/2006/05/31/converting-between-xml-and-json.html)) or nested arrays. Both representations are lossy and might lose ordering of elements, text nodes and comments. In object representation `from_xml`, `from_html` and `to_xml` support `{seq:true}` option to parse/serialize `{"#seq"=}` attributes to preserve element sibling ordering. The object version is denser and convenient to query, the nested arrays version is probably easier to use when generating XML. @@ -546,9 +568,9 @@ zip> ^D - For explicit sibling ordering `#seq` keys with a number, can be negative, assumed zero if missing. - Child element with only text as `` key with text as value. - Child element with more than just text as `` key with value an object. - - Multiple child element sibling with same name as `name` key with value as array with strings and objects. + - Multiple child element siblings with same name as `name` key with value as array with strings and objects. ```jq - > $xml | fromxml + > $xml | from_xml { "doc": { "child": [ @@ -566,12 +588,12 @@ zip> ^D ``` With nested array representation, an array with these values `["", {attributes...}, [children...]]` - - Index 0 is element name. + - Index 0 is an element name. - Index 1 object attributes (including `#text` and `#comment` keys). - Index 2 array of child elements. # ```jq - > $xml | fromxml({array: true}) + > $xml | from_xml({array: true}) [ "doc", [ @@ -599,7 +621,7 @@ zip> ^D ``` Parse and include `#seq` attributes if needed: ```jq - > $xml | fromxml({seq:true}) + > $xml | from_xml({seq:true}) { "doc": { "child": [ @@ -622,7 +644,7 @@ zip> ^D ```` Select values in ``, remove ``, add a `` element, serialize to xml with 2 space indent and print the string ```jq - > $xml | fromxml.doc | del(.child) | .new = "abc" | {root: .} | toxml({indent: 2}) | println + > $xml | from_xml.doc | del(.child) | .new = "abc" | {root: .} | to_xml({indent: 2}) | println abc text @@ -633,45 +655,47 @@ JSON and jq-flavoured JSON - `fromjson` Parse JSON into jq value. - `tojson`/`tojson($opt)` Serialize jq value into JSON.
`{indent: number}` indent array/object values.
-- `fromjq` Parse jq-flavoured JSON into jq value. -- `tojq`/`tojq($opt)` Serialize jq value into jq-flavoured JSON
+- `from_jq` Parse jq-flavoured JSON into jq value. +- `to_jq`/`to_jq($opt)` Serialize jq value into jq-flavoured JSON
`{indent: number}` indent array/object values.
jq-flavoured JSON has optional key quotes, `#` comments and can have trailing comma in arrays. -- `fromjsonl` Parse JSON lines into jq array. -- `tojsonl` Serialize jq array into JSONL. +- `from_jsonl` Parse JSON lines into jq array. +- `to_jsonl` Serialize jq array into JSONL. + +Note that `fromjson` and `tojson` use different naming conventions as they originate from jq's standard library. YAML -- `fromyaml` Parse YAML into jq value. -- `toyaml` Serialize jq value into YAML. +- `from_yaml` Parse YAML into jq value. +- `to_yaml` Serialize jq value into YAML. TOML -- `fromtoml` Parse TOML into jq value. -- `totoml` Serialize jq value into TOML. +- `from_toml` Parse TOML into jq value. +- `to_toml` Serialize jq value into TOML. CSV -- `fromcsv`/`fromcvs($opts)` Parse CSV into jq value.
+- `from_csv`/`from_cvs($opts)` Parse CSV into jq value.
`{comma: string}` field separator, default ",".
`{comment: string}` comment line character, default "#".
To work with tab separated values you can use `fromcvs({comma: "\t"})` or `fq -d csv -o 'comma="\t"'` -- `tocsv`/`tocsv($opts)` Serialize jq value into CSV.
+- `to_csv`/`to_csv($opts)` Serialize jq value into CSV.
`{comma: string}` field separator, default ",".
XML encoding -- `fromxmlentities` Decode XML entities. -- `toxmlentities` Encode XML entities. +- `from_xmlentities` Decode XML entities. +- `to_xmlentities` Encode XML entities. URL parts and XML encodings -- `fromurlpath` Decode URL path component. -- `tourlpath` Encode URL path component. Whitespace as %20. -- `fromurlencode` Decode URL query encoding. -- `tourlencode` Encode URL to query encoding. Whitespace as "+". -- `fromurlquery` Decode URL query into object. For duplicates keys value will be an array. -- `tourlquery` Encode objet into query string. -- `fromurl` Decode URL into object. +- `from_urlpath` Decode URL path component. +- `to_urlpath` Encode URL path component. Whitespace as %20. +- `from_urlencode` Decode URL query encoding. +- `to_urlencode` Encode URL to query encoding. Whitespace as "+". +- `from_urlquery` Decode URL query into object. For duplicates keys value will be an array. +- `to_urlquery` Encode object into query string. +- `from_url` Decode URL into object. ```jq - > "schema://user:pass@host/path?key=value#fragment" | fromurl + > "schema://user:pass@host/path?key=value#fragment" | from_url { - "fragment": "fragement", + "fragment": "fragment", "host": "host", "path": "/path", "query": { @@ -685,50 +709,50 @@ URL parts and XML encodings } } ``` -- `tourl` Encode object into URL string. -- `fromhex` Decode hexstring to binary. +- `to_url` Encode object into URL string. Binary encodings like hex and base64 -- `tohex` Encode binay into hexstring. -- `frombase64`/`frombase64($opts)` Decode base64 encodings into binary.
+- `from_hex` Decode hex string to binary. +- `to_hex` Encode binary into hex string. +- `from_base64`/`from_base64($opts)` Decode base64 encodings into binary.
`{encoding:string}` encoding variant: `std` (default), `url`, `rawstd` or `rawurl` -- `tobase64`/`tobase64($opts)` Encode binary into base64 encodings.
+- `to_base64`/`to_base64($opts)` Encode binary into base64 encodings.
`{encoding:string}` encoding variant: `std` (default), `url`, `rawstd` or `rawurl` Hash functions -- `tomd4` Hash binary using md4. -- `tomd5` Hash binary using md5. -- `tosha1` Hash binary using sha1. -- `tosha256` Hash binary using sha256. -- `tosha512` Hash binary using sha512. -- `tosha3_224` Hash binary using sha3 224. -- `tosha3_256` Hash binary using sha3 256. -- `tosha3_384` Hash binary using sha3 384. -- `tosha3_512` Hash binary using sha3 512. +- `to_md4` Hash binary using md4. +- `to_md5` Hash binary using md5. +- `to_sha1` Hash binary using sha1. +- `to_sha256` Hash binary using sha256. +- `to_sha512` Hash binary using sha512. +- `to_sha3_224` Hash binary using sha3 224. +- `to_sha3_256` Hash binary using sha3 256. +- `to_sha3_384` Hash binary using sha3 384. +- `to_sha3_512` Hash binary using sha3 512. Text encodings -- `toiso8859_1` Decode binary as ISO8859-1 into string. -- `fromiso8859_1` Encode string as ISO8859-1 into binary. -- `toutf8` Encode string as UTF8 into binary. -- `fromutf8` Decode binary as UTF8 into string. -- `toutf16` Encode string as UTF16 into binary. -- `fromutf16` Decode binary as UTF16 into string. -- `toutf16le` Encode string as UTF16 little-endian into binary. -- `fromutf16le` Decode binary as UTF16 little-endian into string. -- `toutf16be` Encode string as UTF16 big-endian into binary. -- `fromutf16be` Decode binary as UTF16 big-endian into string. +- `to_iso8859_1` Decode binary as ISO8859-1 into string. +- `from_iso8859_1` Encode string as ISO8859-1 into binary. +- `to_utf8` Encode string as UTF8 into binary. +- `from_utf8` Decode binary as UTF8 into string. +- `to_utf16` Encode string as UTF16 into binary. +- `from_utf16` Decode binary as UTF16 into string. +- `to_utf16le` Encode string as UTF16 little-endian into binary. +- `from_utf16le` Decode binary as UTF16 little-endian into string. +- `to_utf16be` Encode string as UTF16 big-endian into binary. +- `from_utf16be` Decode binary as UTF16 big-endian into string. ## Options fq has some general options in addition to decode and decoders specific options. They all use the same `-o =` argument. -`` is fuzzily parsed based on the type of the option. Ex: a string can specified as `-o name=string` or `-o name="string"`. +`` is fuzzily parsed based on the type of the option. Ex: a string can be specified as `-o name=string` or `-o name="string"`. ### `bits_format` How to represent raw bits as JSON. -- `-o bits_foramt=string` String with raw bytes (zero bit padded). The string is binary safe internally in fq but bytes not represetable as UTF-8 will be lost if turn to JSON. +- `-o bits_foramt=string` String with raw bytes (zero bit padded). The string is binary safe internally in fq but bytes not representable as UTF-8 will be lost if turn to JSON. - `-o bits_format=md5` MD5 hex string (zero bit padded). - `-o bits_format=base64` Base64 string. - `-p bits_foramt=truncate` Truncated string. @@ -737,7 +761,7 @@ How to represent raw bits as JSON. ## Color and unicode output fq by default tries to use colors if possible, this can be disabled with `-M`. You can also -enable useage of unicode characters for improved output by setting the environment +enable usage of unicode characters for improved output by setting the environment variable `CLIUNICODE`. ## Configuration @@ -749,7 +773,7 @@ To add own functions you can use `init.fq` that will be read from ## Use as script interpreter -fq can be used as a scrip interpreter: +fq can be used as a script interpreter: `mp3_duration.jq`: ```jq @@ -761,9 +785,9 @@ fq can be used as a scrip interpreter: - [gojq's differences to jq](https://github.com/itchyny/gojq#difference-to-jq), notable is support for arbitrary-precision integers. -- Supports hexdecimal `0xab`, octal `0o77` and binary `0b101` integer literals. -- Try include `include "file?";` that don't fail if file is missing. -- Some values can act as a object with keys even when it's an array, number etc. +- Supports hexadecimal `0xab`, octal `0o77` and binary `0b101` integer literals. +- Try include `include "file?";` that doesn't fail if file is missing or has errors. +- Some values can act as an object with keys even when it's an array, number etc. - There can be keys hidden from `keys` and `[]`. - Some values are readonly and can't be updated. diff --git a/format/asn1/asn1_ber.md b/format/asn1/asn1_ber.md index 9cecf871..5a49f306 100644 --- a/format/asn1/asn1_ber.md +++ b/format/asn1/asn1_ber.md @@ -7,7 +7,7 @@ Supports decoding BER, CER and DER (X.690). ### Can be used to decode certificates etc ```sh -$ fq -d bytes 'frompem | asn1_ber | d' cert.pem +$ fq -d bytes 'from_pem | asn1_ber | d' cert.pem ``` ### Can decode nested values diff --git a/format/asn1/testdata/ed25519.cer.fqtest b/format/asn1/testdata/ed25519.cer.fqtest index ad4e3d44..1ae1672a 100644 --- a/format/asn1/testdata/ed25519.cer.fqtest +++ b/format/asn1/testdata/ed25519.cer.fqtest @@ -1,4 +1,4 @@ -$ fq -d bytes 'frompem | asn1_ber | dv' ed25519.cer +$ fq -d bytes 'from_pem | asn1_ber | dv' ed25519.cer |00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|.{}: (asn1_ber) 0x0-0x182.7 (387) 0x0000|30 |0 | class: "universal" (0) 0x0-0x0.1 (0.2) 0x0000|30 |0 | form: "constructed" (1) 0x0.2-0x0.2 (0.1) diff --git a/format/asn1/testdata/help_asn1_ber.fqtest b/format/asn1/testdata/help_asn1_ber.fqtest index 6d33b4b8..26a5bd22 100644 --- a/format/asn1/testdata/help_asn1_ber.fqtest +++ b/format/asn1/testdata/help_asn1_ber.fqtest @@ -18,7 +18,7 @@ Supports decoding BER, CER and DER (X.690). Can be used to decode certificates etc ====================================== - $ fq -d bytes 'frompem | asn1_ber | d' cert.pem + $ fq -d bytes 'from_pem | asn1_ber | d' cert.pem Can decode nested values ======================== diff --git a/format/asn1/testdata/letsencrypt-x3.cer.fqtest b/format/asn1/testdata/letsencrypt-x3.cer.fqtest index 668ae3e4..325eed01 100644 --- a/format/asn1/testdata/letsencrypt-x3.cer.fqtest +++ b/format/asn1/testdata/letsencrypt-x3.cer.fqtest @@ -1,4 +1,4 @@ -$ fq -d bytes 'frompem | asn1_ber | dv' letsencrypt-x3.cer +$ fq -d bytes 'from_pem | asn1_ber | dv' letsencrypt-x3.cer |00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|.{}: (asn1_ber) 0x0-0x495.7 (1174) 0x00000|30 |0 | class: "universal" (0) 0x0-0x0.1 (0.2) 0x00000|30 |0 | form: "constructed" (1) 0x0.2-0x0.2 (0.1) diff --git a/format/asn1/testdata/sig-p256-ber.p7m.fqtest b/format/asn1/testdata/sig-p256-ber.p7m.fqtest index 4cc24c5c..127cd06c 100644 --- a/format/asn1/testdata/sig-p256-ber.p7m.fqtest +++ b/format/asn1/testdata/sig-p256-ber.p7m.fqtest @@ -1,4 +1,4 @@ -$ fq -d bytes 'frompem | asn1_ber | dv' sig-p256-ber.p7m +$ fq -d bytes 'from_pem | asn1_ber | dv' sig-p256-ber.p7m |00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|.{}: (asn1_ber) 0x0-0x2aa1.7 (10914) 0x000000|30 |0 | class: "universal" (0) 0x0-0x0.1 (0.2) 0x000000|30 |0 | form: "constructed" (1) 0x0.2-0x0.2 (0.1) diff --git a/format/asn1/testdata/sig-p256-der.p7m.fqtest b/format/asn1/testdata/sig-p256-der.p7m.fqtest index 7a879ba5..0512c80b 100644 --- a/format/asn1/testdata/sig-p256-der.p7m.fqtest +++ b/format/asn1/testdata/sig-p256-der.p7m.fqtest @@ -1,4 +1,4 @@ -$ fq -d bytes 'frompem | asn1_ber | dv' sig-p256-der.p7m +$ fq -d bytes 'from_pem | asn1_ber | dv' sig-p256-der.p7m |00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|.{}: (asn1_ber) 0x0-0x2a77.7 (10872) 0x0000|30 |0 | class: "universal" (0) 0x0-0x0.1 (0.2) 0x0000|30 |0 | form: "constructed" (1) 0x0.2-0x0.2 (0.1) diff --git a/format/asn1/testdata/sig-rsa1024-sha1.p7s.fqtest b/format/asn1/testdata/sig-rsa1024-sha1.p7s.fqtest index f8b48de1..2dabbb76 100644 --- a/format/asn1/testdata/sig-rsa1024-sha1.p7s.fqtest +++ b/format/asn1/testdata/sig-rsa1024-sha1.p7s.fqtest @@ -1,4 +1,4 @@ -$ fq -d bytes 'frompem | asn1_ber | dv' sig-rsa1024-sha1.p7s +$ fq -d bytes 'from_pem | asn1_ber | dv' sig-rsa1024-sha1.p7s |00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|.{}: (asn1_ber) 0x0-0x353.7 (852) 0x0000|30 |0 | class: "universal" (0) 0x0-0x0.1 (0.2) 0x0000|30 |0 | form: "constructed" (1) 0x0.2-0x0.2 (0.1) diff --git a/format/asn1/testdata/test.pem.fqtest b/format/asn1/testdata/test.pem.fqtest index 1fff3ced..6595cd20 100644 --- a/format/asn1/testdata/test.pem.fqtest +++ b/format/asn1/testdata/test.pem.fqtest @@ -1,4 +1,4 @@ -$ fq -d bytes 'frompem | asn1_ber | dv, torepr' test.pem +$ fq -d bytes 'from_pem | asn1_ber | dv, torepr' test.pem |00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|.{}: (asn1_ber) 0x0-0xa1.7 (162) 0x00|30 |0 | class: "universal" (0) 0x0-0x0.1 (0.2) 0x00|30 |0 | form: "constructed" (1) 0x0.2-0x0.2 (0.1) diff --git a/format/cbor/testdata/appendix_a.fqtest b/format/cbor/testdata/appendix_a.fqtest index 8d779f5c..1db7bebf 100644 --- a/format/cbor/testdata/appendix_a.fqtest +++ b/format/cbor/testdata/appendix_a.fqtest @@ -3,7 +3,7 @@ $ fq -i -d json . appendix_a.json json> length 82 -json> map(select(.decoded) | (.cbor | frombase64 | cbor | torepr) as $a | select( .decoded != $a) | {test: ., actual: $a}) +json> map(select(.decoded) | (.cbor | from_base64 | cbor | torepr) as $a | select( .decoded != $a) | {test: ., actual: $a}) [ { "actual": { @@ -32,7 +32,7 @@ json> map(select(.decoded) | (.cbor | frombase64 | cbor | torepr) as $a | select } } ] -json> .[] | select(.decoded) | .cbor | frombase64 | cbor | dv +json> .[] | select(.decoded) | .cbor | from_base64 | cbor | dv |00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|.{}: (cbor) 0x0-0x0.7 (1) 0x0|00| |.| | major_type: "positive_int" (0) 0x0-0x0.2 (0.3) 0x0|00| |.| | short_count: 0 0x0.3-0x0.7 (0.5) diff --git a/format/cbor/testdata/cbor.fqtest b/format/cbor/testdata/cbor.fqtest index dcaa0de9..0a0d4000 100644 --- a/format/cbor/testdata/cbor.fqtest +++ b/format/cbor/testdata/cbor.fqtest @@ -1,4 +1,4 @@ -$ fq -n '"v2NGdW71Y0FtdCH/" | frombase64 | cbor | torepr' +$ fq -n '"v2NGdW71Y0FtdCH/" | from_base64 | cbor | torepr' { "Amt": -2, "Fun": true diff --git a/format/crypto/hash.go b/format/crypto/hash.go index 40ef818b..8aeb9e89 100644 --- a/format/crypto/hash.go +++ b/format/crypto/hash.go @@ -23,7 +23,7 @@ import ( var hashFS embed.FS func init() { - interp.RegisterFunc1("_tohash", toHash) + interp.RegisterFunc1("_to_hash", toHash) interp.RegisterFS(hashFS) } diff --git a/format/crypto/hash.jq b/format/crypto/hash.jq index 0f7bfd2d..9e6b1344 100644 --- a/format/crypto/hash.jq +++ b/format/crypto/hash.jq @@ -1,9 +1,9 @@ -def tomd4: _tohash({name: "md4"}); -def tomd5: _tohash({name: "md5"}); -def tosha1: _tohash({name: "sha1"}); -def tosha256: _tohash({name: "sha256"}); -def tosha512: _tohash({name: "sha512"}); -def tosha3_224: _tohash({name: "sha3_224"}); -def tosha3_256: _tohash({name: "sha3_256"}); -def tosha3_384: _tohash({name: "sha3_384"}); -def tosha3_512: _tohash({name: "sha3_512"}); \ No newline at end of file +def to_md4: _to_hash({name: "md4"}); +def to_md5: _to_hash({name: "md5"}); +def to_sha1: _to_hash({name: "sha1"}); +def to_sha256: _to_hash({name: "sha256"}); +def to_sha512: _to_hash({name: "sha512"}); +def to_sha3_224: _to_hash({name: "sha3_224"}); +def to_sha3_256: _to_hash({name: "sha3_256"}); +def to_sha3_384: _to_hash({name: "sha3_384"}); +def to_sha3_512: _to_hash({name: "sha3_512"}); \ No newline at end of file diff --git a/format/crypto/pem.jq b/format/crypto/pem.jq index 914abc24..b99053dc 100644 --- a/format/crypto/pem.jq +++ b/format/crypto/pem.jq @@ -1,14 +1,14 @@ # https://en.wikipedia.org/wiki/Privacy-Enhanced_Mail -def frompem: +def from_pem: ( tobytes | tostring | capture("-----BEGIN(.*?)-----(?.*?)-----END(.*?)-----"; "mg").s - | _frombase64({encoding: "std"}) + | _from_base64({encoding: "std"}) ) // error("no pem header or footer found"); -def topem($label): +def to_pem($label): ( tobytes - | _tobase64({encoding: "std"}) + | _to_base64({encoding: "std"}) | ($label | if $label != "" then " " + $label end) as $label | [ "-----BEGIN\($label)-----" , . @@ -17,4 +17,4 @@ def topem($label): ] | join("\n") ); -def topem: topem(""); \ No newline at end of file +def to_pem: to_pem(""); \ No newline at end of file diff --git a/format/crypto/testdata/hash.fqtest b/format/crypto/testdata/hash.fqtest index 7815b405..95d5460a 100644 --- a/format/crypto/testdata/hash.fqtest +++ b/format/crypto/testdata/hash.fqtest @@ -1,5 +1,5 @@ $ fq -i -null> "test" | tomd4, tomd5, tosha1, tosha256, tosha512, tosha3_224, tosha3_256, tosha3_384, tosha3_512 | tohex +null> "test" | to_md4, to_md5, to_sha1, to_sha256, to_sha512, to_sha3_224, to_sha3_256, to_sha3_384, to_sha3_512 | to_hex "db346d691d7acc4dc2625db19f9e3f52" "098f6bcd4621d373cade4e832627b4f6" "a94a8fe5ccb19ba61c4c0873d391e987982fbbd3" @@ -9,7 +9,7 @@ null> "test" | tomd4, tomd5, tosha1, tosha256, tosha512, tosha3_224, tosha3_256, "36f028580bb02cc8272a9a020f4200e346e276ae664e45ee80745574e2f5ab80" "e516dabb23b6e30026863543282780a3ae0dccf05551cf0295178d7ff0f1b41eecb9db3ff219007c4e097260d58621bd" "9ece086e9bac491fac5c1d1046ca11d737b92a2b2ebd93f005d7b710110c0a678288166e7fbe796883a4f2e9b3ca9f484f521d0ce464345cc1aec96779149c14" -null> 0xf08 | tobits | .[:4,5,6,7,8,9] | tomd5 | tohex +null> 0xf08 | tobits | .[:4,5,6,7,8,9] | to_md5 | to_hex "8c493a43d8c1ef798860bb02b62e8e79" "8c493a43d8c1ef798860bb02b62e8e79" "8c493a43d8c1ef798860bb02b62e8e79" diff --git a/format/crypto/testdata/pem.fqtest b/format/crypto/testdata/pem.fqtest index fdac2972..bff23f41 100644 --- a/format/crypto/testdata/pem.fqtest +++ b/format/crypto/testdata/pem.fqtest @@ -1,7 +1,7 @@ $ fq -i -null> "abc" | topem +null> "abc" | to_pem "-----BEGIN-----\nYWJj\n-----END-----\n" -null> "abc" | topem | "before" + . + "between" + . + "after" | frompem | tostring +null> "abc" | to_pem | "before" + . + "between" + . + "after" | from_pem | tostring "abc" "abc" null> ^D diff --git a/format/csv/csv.go b/format/csv/csv.go index b3bf8761..b86ca748 100644 --- a/format/csv/csv.go +++ b/format/csv/csv.go @@ -33,7 +33,7 @@ func init() { Functions: []string{"_todisplay"}, }) interp.RegisterFS(csvFS) - interp.RegisterFunc1("_tocsv", toCSV) + interp.RegisterFunc1("_to_csv", toCSV) } func decodeCSV(d *decode.D, in any) any { diff --git a/format/csv/csv.jq b/format/csv/csv.jq index 184f7296..9b59b46d 100644 --- a/format/csv/csv.jq +++ b/format/csv/csv.jq @@ -1,3 +1,3 @@ -def tocsv($opts): _tocsv($opts); -def tocsv: _tocsv(null); +def to_csv($opts): _to_csv($opts); +def to_csv: _to_csv(null); def _csv__todisplay: tovalue; diff --git a/format/csv/csv.md b/format/csv/csv.md index dbde64fb..c4697e1c 100644 --- a/format/csv/csv.md +++ b/format/csv/csv.md @@ -1,7 +1,7 @@ ### TSV to CSV ```sh -$ fq -d csv -o comma="\t" tocsv file.tsv +$ fq -d csv -o comma="\t" to_csv file.tsv ``` ### Convert rows to objects based on header row diff --git a/format/csv/testdata/csv.fqtest b/format/csv/testdata/csv.fqtest index 49c9e274..e63ebfa7 100644 --- a/format/csv/testdata/csv.fqtest +++ b/format/csv/testdata/csv.fqtest @@ -9,7 +9,7 @@ $ fq -d csv . /test ] ] $ fq -i -null> "a,b,c,d" | fromcsv | ., tocsv +null> "a,b,c,d" | from_csv | ., to_csv [ [ "a", @@ -19,7 +19,7 @@ null> "a,b,c,d" | fromcsv | ., tocsv ] ] "a,b,c,d\n" -null> "a,\"b, c\",d" | fromcsv | ., tocsv +null> "a,\"b, c\",d" | from_csv | ., to_csv [ [ "a", @@ -28,7 +28,7 @@ null> "a,\"b, c\",d" | fromcsv | ., tocsv ] ] "a,\"b, c\",d\n" -null> "a\t\"b\t c\"\td" | fromcsv({comma:"\t"}) | ., tocsv({comma: "\t"}) +null> "a\t\"b\t c\"\td" | from_csv({comma:"\t"}) | ., to_csv({comma: "\t"}) [ [ "a", @@ -37,7 +37,7 @@ null> "a\t\"b\t c\"\td" | fromcsv({comma:"\t"}) | ., tocsv({comma: "\t"}) ] ] "a\t\"b\t c\"\td\n" -null> [[bsl(1;100)]] | tocsv | ., fromcsv +null> [[bsl(1;100)]] | to_csv | ., from_csv "1267650600228229401496703205376\n" [ [ diff --git a/format/csv/testdata/help_csv.fqtest b/format/csv/testdata/help_csv.fqtest index f5b85907..3a3e9811 100644 --- a/format/csv/testdata/help_csv.fqtest +++ b/format/csv/testdata/help_csv.fqtest @@ -22,7 +22,7 @@ Decode examples TSV to CSV ========== - $ fq -d csv -o comma="\t" tocsv file.tsv + $ fq -d csv -o comma="\t" to_csv file.tsv Convert rows to objects based on header row =========================================== diff --git a/format/json/jq.jq b/format/json/jq.jq index f7506c3c..7b239e24 100644 --- a/format/json/jq.jq +++ b/format/json/jq.jq @@ -1,5 +1,5 @@ # to jq-flavoured json -def _tojq($opts): +def _to_jq($opts): def _is_ident: test("^[a-zA-Z_][a-zA-Z_0-9]*$"); def _key: if _is_ident | not then tojson end; def _f($opts; $indent): @@ -45,8 +45,8 @@ def _tojq($opts): ( _f($opts; $opts.indent * " ") | if _is_array then flatten | join("") end ); -def tojq($opts): - _tojq( +def to_jq($opts): + _to_jq( ( { indent: 0, key_sep: ":", object_sep: ",", @@ -62,10 +62,10 @@ def tojq($opts): end ) ); -def tojq: tojq(null); +def to_jq: to_jq(null); # from jq-flavoured json -def fromjq: +def from_jq: def _f: ( . as $v | .term.type @@ -93,4 +93,4 @@ def fromjq: try (_query_fromstring | _f) catch - error("fromjq only supports constant literals"); + error("from_jq only supports constant literals"); diff --git a/format/json/json.go b/format/json/json.go index b1512aaf..881314c4 100644 --- a/format/json/json.go +++ b/format/json/json.go @@ -31,7 +31,7 @@ func init() { Functions: []string{"_todisplay"}, }) interp.RegisterFS(jsonFS) - interp.RegisterFunc1("_tojson", toJSON) + interp.RegisterFunc1("_to_json", toJSON) } func decodeJSONEx(d *decode.D, lines bool) any { diff --git a/format/json/json.jq b/format/json/json.jq index 82d51167..fdc29ebd 100644 --- a/format/json/json.jq +++ b/format/json/json.jq @@ -1,3 +1,8 @@ -def tojson($opts): _tojson($opts); -def tojson: _tojson(null); +# overrides jq's standard tojson +def tojson($opts): _to_json($opts); +def tojson: _to_json(null); +# overrides jq's standard fromjson +# NOTE: should be kept in sync with format_decode.jq +def fromjson: decode("json") | if ._error then error(._error.error) end; + def _json__todisplay: tovalue; diff --git a/format/json/jsonl.go b/format/json/jsonl.go index 8ff384d1..9ad6c08e 100644 --- a/format/json/jsonl.go +++ b/format/json/jsonl.go @@ -24,7 +24,7 @@ func init() { Functions: []string{"_todisplay"}, }) interp.RegisterFS(jsonlFS) - interp.RegisterFunc0("tojsonl", toJSONL) + interp.RegisterFunc0("to_jsonl", toJSONL) } func decodeJSONL(d *decode.D, _ any) any { diff --git a/format/json/testdata/bigint.fqtest b/format/json/testdata/bigint.fqtest index 35cd4460..317f4edb 100644 --- a/format/json/testdata/bigint.fqtest +++ b/format/json/testdata/bigint.fqtest @@ -1,4 +1,4 @@ -$ fq -n "{a: bsl(1;100)} | tojq | ., fromjq" +$ fq -n "{a: bsl(1;100)} | to_jq | ., from_jq" "{a:1267650600228229401496703205376}" { "a": 1267650600228229401496703205376 diff --git a/format/json/testdata/jq.fqtest b/format/json/testdata/jq.fqtest index bd897124..4ad4c6cc 100644 --- a/format/json/testdata/jq.fqtest +++ b/format/json/testdata/jq.fqtest @@ -1,4 +1,4 @@ -$ fq -rRs 'fromjson[] | (tojq | ., fromjq), "----", (tojq({indent:2}) | ., fromjq), "----"' variants.json +$ fq -rRs 'fromjson[] | (to_jq | ., from_jq), "----", (to_jq({indent:2}) | ., from_jq), "----"' variants.json null null ---- diff --git a/format/json/testdata/jsonl.fqtest b/format/json/testdata/jsonl.fqtest index e92a574e..f12d2514 100644 --- a/format/json/testdata/jsonl.fqtest +++ b/format/json/testdata/jsonl.fqtest @@ -35,9 +35,9 @@ $ fq -d jsonl . error.jsonl |00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|.{}: error.jsonl (jsonl) | | | error: jsonl: error at position 0xf: invalid character 'a' looking for beginning of value 0x0|7b 22 61 22 3a 20 31 32 33 7d 20 61 73 64 0a| |{"a": 123} asd.|| gap0: raw bits -$ fq -n '[{"a":123}, [123]] | tojsonl' +$ fq -n '[{"a":123}, [123]] | to_jsonl' "{\"a\":123}\n[123]\n" -$ fq -n '123 | tojsonl' +$ fq -n '123 | to_jsonl' exitcode: 5 stderr: -error: tojsonl cannot be applied to: number (123) +error: to_jsonl cannot be applied to: number (123) diff --git a/format/math/radix.jq b/format/math/radix.jq index 0764d10a..4884c2d4 100644 --- a/format/math/radix.jq +++ b/format/math/radix.jq @@ -1,5 +1,5 @@ -def fromradix($base; $table): - ( if _is_string | not then error("cannot fromradix convert: \(.)") end +def from_radix($base; $table): + ( if _is_string | not then error("cannot from_radix convert: \(.)") end | split("") | reverse | map($table[.]) @@ -12,8 +12,8 @@ def fromradix($base; $table): ) | .[1] ); -def fromradix($base): - fromradix($base; { +def from_radix($base): + from_radix($base; { "0": 0, "1": 1, "2": 2, "3": 3,"4": 4, "5": 5, "6": 6, "7": 7, "8": 8, "9": 9, "a": 10, "b": 11, "c": 12, "d": 13, "e": 14, "f": 15, "g": 16, "h": 17, "i": 18, "j": 19, "k": 20, "l": 21, "m": 22, "n": 23, @@ -26,8 +26,8 @@ def fromradix($base): "@": 62, "_": 63, }); -def toradix($base; $table): - ( if type != "number" then error("cannot toradix convert: \(.)") end +def to_radix($base; $table): + ( if type != "number" then error("cannot to_radix convert: \(.)") end | if . == 0 then "0" else ( [ recurse(if . > 0 then _intdiv(.; $base) else empty end) | . % $base] @@ -41,5 +41,5 @@ def toradix($base; $table): ) end ); -def toradix($base): - toradix($base; "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ@_"); \ No newline at end of file +def to_radix($base): + to_radix($base; "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ@_"); \ No newline at end of file diff --git a/format/math/testdata/radix.fqtest b/format/math/testdata/radix.fqtest index 6e149f9b..d094c8ab 100644 --- a/format/math/testdata/radix.fqtest +++ b/format/math/testdata/radix.fqtest @@ -1,5 +1,5 @@ $ fq -i -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 +null> (0,1,1024,99999999999999999999) as $n | (2,8,16,62,64) as $r | "\($r): \($n) \($n | to_radix($r)) \($n | to_radix($r) | from_radix($r))" | println 2: 0 0 0 8: 0 0 0 16: 0 0 0 diff --git a/format/mp4/mp4.md b/format/mp4/mp4.md index 4f42b398..0181ce3a 100644 --- a/format/mp4/mp4.md +++ b/format/mp4/mp4.md @@ -20,7 +20,7 @@ $ fq 'del(.tracks) | grep_by(.type=="mdat").data = "" | tovalue' file. ### Force decode a single box ```sh -$ fq -n '"AAAAHGVsc3QAAAAAAAAAAQAAADIAAAQAAAEAAA==" | frombase64 | mp4({force:true}) | d' +$ fq -n '"AAAAHGVsc3QAAAAAAAAAAQAAADIAAAQAAAEAAA==" | from_base64 | mp4({force:true}) | d' ``` ### Lookup mp4 box using a mp4 box path. diff --git a/format/mp4/testdata/help_mp4.fqtest b/format/mp4/testdata/help_mp4.fqtest index c18f2421..2af97f5a 100644 --- a/format/mp4/testdata/help_mp4.fqtest +++ b/format/mp4/testdata/help_mp4.fqtest @@ -38,7 +38,7 @@ Whole box tree as JSON (exclude mdat data and tracks) Force decode a single box ========================= - $ fq -n '"AAAAHGVsc3QAAAAAAAAAAQAAADIAAAQAAAEAAA==" | frombase64 | mp4({force:true}) | d' + $ fq -n '"AAAAHGVsc3QAAAAAAAAAAQAAADIAAAQAAAEAAA==" | from_base64 | mp4({force:true}) | d' Lookup mp4 box using a mp4 box path. ==================================== diff --git a/format/text/encoding.go b/format/text/encoding.go index 5142c6c5..ffaa0070 100644 --- a/format/text/encoding.go +++ b/format/text/encoding.go @@ -20,7 +20,7 @@ import ( var textFS embed.FS func init() { - interp.RegisterFunc0("fromhex", func(_ *interp.Interp, c string) any { + interp.RegisterFunc0("from_hex", func(_ *interp.Interp, c string) any { b, err := hex.DecodeString(c) if err != nil { return err @@ -31,7 +31,7 @@ func init() { } return bb }) - interp.RegisterFunc0("tohex", func(_ *interp.Interp, c string) any { + interp.RegisterFunc0("to_hex", func(_ *interp.Interp, c string) any { br, err := interp.ToBitReader(c) if err != nil { return err @@ -59,7 +59,7 @@ func init() { type fromBase64Opts struct { Encoding string } - interp.RegisterFunc1("_frombase64", func(_ *interp.Interp, c string, opts fromBase64Opts) any { + interp.RegisterFunc1("_from_base64", func(_ *interp.Interp, c string, opts fromBase64Opts) any { b, err := base64Encoding(opts.Encoding).DecodeString(c) if err != nil { return err @@ -73,7 +73,7 @@ func init() { type toBase64Opts struct { Encoding string } - interp.RegisterFunc1("_tobase64", func(_ *interp.Interp, c string, opts toBase64Opts) any { + interp.RegisterFunc1("_to_base64", func(_ *interp.Interp, c string, opts toBase64Opts) any { br, err := interp.ToBitReader(c) if err != nil { return err @@ -197,7 +197,7 @@ func init() { type toStrEncodingOpts struct { Encoding string } - interp.RegisterFunc1("_tostrencoding", func(_ *interp.Interp, c string, opts toStrEncodingOpts) any { + interp.RegisterFunc1("_to_strencoding", func(_ *interp.Interp, c string, opts toStrEncodingOpts) any { h := strEncoding(opts.Encoding) if h == nil { return fmt.Errorf("unknown string encoding %s", opts.Encoding) @@ -219,7 +219,7 @@ func init() { type fromStrEncodingOpts struct { Encoding string } - interp.RegisterFunc1("_fromstrencoding", func(_ *interp.Interp, c any, opts fromStrEncodingOpts) any { + interp.RegisterFunc1("_from_strencoding", func(_ *interp.Interp, c any, opts fromStrEncodingOpts) any { inBR, err := interp.ToBitReader(c) if err != nil { return err diff --git a/format/text/encoding.jq b/format/text/encoding.jq index a8b4a083..6620fd95 100644 --- a/format/text/encoding.jq +++ b/format/text/encoding.jq @@ -1,19 +1,21 @@ -def toiso8859_1: _tostrencoding({encoding: "ISO8859_1"}); -def fromiso8859_1: _fromstrencoding({encoding: "ISO8859_1"}); -def toutf8: _tostrencoding({encoding: "UTF8"}); -def fromutf8: _fromstrencoding({encoding: "UTF8"}); -def toutf16: _tostrencoding({encoding: "UTF16"}); -def fromutf16: _fromstrencoding({encoding: "UTF16"}); -def toutf16le: _tostrencoding({encoding: "UTF16LE"}); -def fromutf16le: _fromstrencoding({encoding: "UTF16LE"}); -def toutf16be: _tostrencoding({encoding: "UTF16BE"}); -def fromutf16be: _fromstrencoding({encoding: "UTF16BE"}); +def to_iso8859_1: _to_strencoding({encoding: "ISO8859_1"}); +def from_iso8859_1: _from_strencoding({encoding: "ISO8859_1"}); +def to_utf8: _to_strencoding({encoding: "UTF8"}); +def from_utf8: _from_strencoding({encoding: "UTF8"}); +def to_utf16: _to_strencoding({encoding: "UTF16"}); +def from_utf16: _from_strencoding({encoding: "UTF16"}); +def to_utf16le: _to_strencoding({encoding: "UTF16LE"}); +def from_utf16le: _from_strencoding({encoding: "UTF16LE"}); +def to_utf16be: _to_strencoding({encoding: "UTF16BE"}); +def from_utf16be: _from_strencoding({encoding: "UTF16BE"}); -def frombase64($opts): _frombase64({encoding: "std"} + $opts); -def frombase64: _frombase64(null); -def tobase64($opts): _tobase64({encoding: "std"} + $opts); -def tobase64: _tobase64(null); +def from_base64($opts): _from_base64({encoding: "std"} + $opts); +def from_base64: _from_base64(null); +def to_base64($opts): _to_base64({encoding: "std"} + $opts); +def to_base64: _to_base64(null); # TODO: compat: remove at some point -def hex: _binary_or_orig(tohex; fromhex); -def base64: _binary_or_orig(tobase64; frombase64); +def hex: _binary_or_orig(to_hex; from_hex); +def base64: _binary_or_orig(to_base64; from_base64); +def tohex: to_hex; +def fromhex: from_hex; diff --git a/format/text/testdata/base64.fqtest b/format/text/testdata/base64.fqtest index 909786c7..77b843d0 100644 --- a/format/text/testdata/base64.fqtest +++ b/format/text/testdata/base64.fqtest @@ -1,4 +1,4 @@ -$ fq -n '"ff7f00ff" | fromhex | ., ("", "std", "url", "rawstd", "rawurl") as $e | tobase64({encoding: $e}) | ., frombase64({encoding: $e})' +$ fq -n '"ff7f00ff" | from_hex | ., ("", "std", "url", "rawstd", "rawurl") as $e | to_base64({encoding: $e}) | ., from_base64({encoding: $e})' |00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef| 0x0|ff 7f 00 ff| |....| |.: raw bits 0x0-0x3.7 (4) "/38A/w==" diff --git a/format/text/testdata/encoding.fqtest b/format/text/testdata/encoding.fqtest index 8fa7960c..fc6c1af7 100644 --- a/format/text/testdata/encoding.fqtest +++ b/format/text/testdata/encoding.fqtest @@ -1,41 +1,41 @@ $ fq -i -null> "åäö" | toiso8859_1 | ., fromiso8859_1 +null> "åäö" | to_iso8859_1 | ., from_iso8859_1 |00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef| 0x0|e5 e4 f6| |...| |.: raw bits 0x0-0x2.7 (3) "åäö" -null> "åäö" | toutf8 | ., fromutf8 +null> "åäö" | to_utf8 | ., from_utf8 |00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef| 0x0|c3 a5 c3 a4 c3 b6| |......| |.: raw bits 0x0-0x5.7 (6) "åäö" -null> "åäö" | toutf16 | ., fromutf16 +null> "åäö" | to_utf16 | ., from_utf16 |00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef| 0x0|ff fe e5 00 e4 00 f6 00| |........| |.: raw bits 0x0-0x7.7 (8) "åäö" -null> "åäö" | toutf16le | ., fromutf16le +null> "åäö" | to_utf16le | ., from_utf16le |00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef| 0x0|e5 00 e4 00 f6 00| |......| |.: raw bits 0x0-0x5.7 (6) "åäö" -null> "åäö" | toutf16be | ., fromutf16be +null> "åäö" | to_utf16be | ., from_utf16be |00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef| 0x0|00 e5 00 e4 00 f6| |......| |.: raw bits 0x0-0x5.7 (6) "åäö" -null> [97,98,99] | fromiso8859_1 | ., toiso8859_1 +null> [97,98,99] | from_iso8859_1 | ., to_iso8859_1 "abc" |00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef| 0x0|61 62 63| |abc| |.: raw bits 0x0-0x2.7 (3) -null> [97,98,99] | fromutf8 | ., toutf8 +null> [97,98,99] | from_utf8 | ., to_utf8 "abc" |00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef| 0x0|61 62 63| |abc| |.: raw bits 0x0-0x2.7 (3) -null> [97,0,98,0,99,0] | fromutf16 | ., toutf16 +null> [97,0,98,0,99,0] | from_utf16 | ., to_utf16 "abc" |00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef| 0x0|ff fe 61 00 62 00 63 00| |..a.b.c.| |.: raw bits 0x0-0x7.7 (8) -null> [97,0,98,0,99,0] | fromutf16le | ., toutf16le +null> [97,0,98,0,99,0] | from_utf16le | ., to_utf16le "abc" |00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef| 0x0|61 00 62 00 63 00| |a.b.c.| |.: raw bits 0x0-0x5.7 (6) -null> [0,97,0,98,0,99] | fromutf16be | ., toutf16be +null> [0,97,0,98,0,99] | from_utf16be | ., to_utf16be "abc" |00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef| 0x0|00 61 00 62 00 63| |.a.b.c| |.: raw bits 0x0-0x5.7 (6) diff --git a/format/text/testdata/url.fqtest b/format/text/testdata/url.fqtest index e1189aa1..f1b546ad 100644 --- a/format/text/testdata/url.fqtest +++ b/format/text/testdata/url.fqtest @@ -1,5 +1,5 @@ $ fq -i -null> "schema://user:pass@host/path/a/b?a=1+2&b=2%20%33#fragment" | fromurl | ., tourl +null> "schema://user:pass@host/path/a/b?a=1+2&b=2%20%33#fragment" | from_url | ., to_url { "fragment": "fragment", "host": "host", @@ -16,7 +16,7 @@ null> "schema://user:pass@host/path/a/b?a=1+2&b=2%20%33#fragment" | fromurl | ., } } "schema://user:pass@host/path/a/b?a=1+2&b=2+3#fragment" -null> "schema://host?query" | fromurl | ., tourl +null> "schema://host?query" | from_url | ., to_url { "host": "host", "query": { @@ -26,7 +26,7 @@ null> "schema://host?query" | fromurl | ., tourl "scheme": "schema" } "schema://host?query=" -null> "schema://user@host" | fromurl | ., tourl +null> "schema://user@host" | from_url | ., to_url { "host": "host", "scheme": "schema", @@ -35,7 +35,7 @@ null> "schema://user@host" | fromurl | ., tourl } } "schema://user@host" -null> "schema://" | fromurl | ., tourl +null> "schema://" | from_url | ., to_url { "scheme": "schema" } diff --git a/format/text/testdata/urlencode.fqtest b/format/text/testdata/urlencode.fqtest index bb95d390..6bbe67c8 100644 --- a/format/text/testdata/urlencode.fqtest +++ b/format/text/testdata/urlencode.fqtest @@ -1,3 +1,3 @@ -$ fq -n '"2%20%33" | fromurlencode | ., tourlencode' +$ fq -n '"2%20%33" | from_urlencode | ., to_urlencode' "2 3" "2+3" diff --git a/format/text/testdata/urlpath.fqtest b/format/text/testdata/urlpath.fqtest index 966fd826..457f6b7a 100644 --- a/format/text/testdata/urlpath.fqtest +++ b/format/text/testdata/urlpath.fqtest @@ -1,3 +1,3 @@ -$ fq -n '"abc%2fdef" | fromurlpath | ., tourlpath' +$ fq -n '"abc%2fdef" | from_urlpath | ., to_urlpath' "abc/def" "abc%2Fdef" diff --git a/format/text/testdata/urlquery.fqtest b/format/text/testdata/urlquery.fqtest index 3ff6448c..10ae68dc 100644 --- a/format/text/testdata/urlquery.fqtest +++ b/format/text/testdata/urlquery.fqtest @@ -1,4 +1,4 @@ -$ fq -n '"a=1+2&b=2%20%33" | fromurlquery | ., tourlquery' +$ fq -n '"a=1+2&b=2%20%33" | from_urlquery | ., to_urlquery' { "a": "1 2", "b": "2 3" diff --git a/format/text/url.go b/format/text/url.go index 015a17cc..7c693efc 100644 --- a/format/text/url.go +++ b/format/text/url.go @@ -8,25 +8,25 @@ import ( ) func init() { - interp.RegisterFunc0("fromurlencode", func(_ *interp.Interp, c string) any { + interp.RegisterFunc0("from_urlencode", func(_ *interp.Interp, c string) any { u, err := url.QueryUnescape(c) if err != nil { return err } return u }) - interp.RegisterFunc0("tourlencode", func(_ *interp.Interp, c string) any { + interp.RegisterFunc0("to_urlencode", func(_ *interp.Interp, c string) any { return url.QueryEscape(c) }) - interp.RegisterFunc0("fromurlpath", func(_ *interp.Interp, c string) any { + interp.RegisterFunc0("from_urlpath", func(_ *interp.Interp, c string) any { u, err := url.PathUnescape(c) if err != nil { return err } return u }) - interp.RegisterFunc0("tourlpath", func(_ *interp.Interp, c string) any { + interp.RegisterFunc0("to_urlpath", func(_ *interp.Interp, c string) any { return url.PathEscape(c) }) @@ -46,7 +46,7 @@ func init() { return qm } - interp.RegisterFunc0("fromurlquery", func(_ *interp.Interp, c string) any { + interp.RegisterFunc0("from_urlquery", func(_ *interp.Interp, c string) any { q, err := url.ParseQuery(c) if err != nil { return err @@ -70,7 +70,7 @@ func init() { } return qv } - interp.RegisterFunc0("tourlquery", func(_ *interp.Interp, c map[string]any) any { + interp.RegisterFunc0("to_urlquery", func(_ *interp.Interp, c map[string]any) any { // TODO: nicer c, ok := gojqex.NormalizeToStrings(c).(map[string]any) if !ok { @@ -79,7 +79,7 @@ func init() { return toURLValues(c).Encode() }) - interp.RegisterFunc0("fromurl", func(_ *interp.Interp, c string) any { + interp.RegisterFunc0("from_url", func(_ *interp.Interp, c string) any { u, err := url.Parse(c) if err != nil { return err @@ -116,7 +116,7 @@ func init() { } return m }) - interp.RegisterFunc0("tourl", func(_ *interp.Interp, c map[string]any) any { + interp.RegisterFunc0("to_url", func(_ *interp.Interp, c map[string]any) any { // TODO: nicer c, ok := gojqex.NormalizeToStrings(c).(map[string]any) if !ok { diff --git a/format/tiff/testdata/infinite.fqtest b/format/tiff/testdata/infinite.fqtest index 62b70639..14cf76c0 100644 --- a/format/tiff/testdata/infinite.fqtest +++ b/format/tiff/testdata/infinite.fqtest @@ -1,4 +1,4 @@ -$ fq.go -n '"SUkqAAwAAAAwMDAwAQAwMDAwMDAwMDAwMDAhAAAAMDAwAAAhAAAA" | frombase64 | tiff' +$ fq.go -n '"SUkqAAwAAAAwMDAwAQAwMDAwMDAwMDAwMDAhAAAAMDAwAAAhAAAA" | from_base64 | tiff' |00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|.{}: (tiff) | | | error: tiff: error at position 0x27: ifd loop detected for 33 0x00|49 49 2a 00 |II*. | endian: "little-endian" (0x49492a00) diff --git a/format/toml/testdata/bigint.fqtest b/format/toml/testdata/bigint.fqtest index 04252faa..c3afb77c 100644 --- a/format/toml/testdata/bigint.fqtest +++ b/format/toml/testdata/bigint.fqtest @@ -1,4 +1,4 @@ -$ fq -n "{a: bsl(1;100)} | totoml | ., fromtoml" +$ fq -n "{a: bsl(1;100)} | to_toml | ., from_toml" "a = \"1267650600228229401496703205376\"\n" { "a": "1267650600228229401496703205376" diff --git a/format/toml/testdata/toml.fqtest b/format/toml/testdata/toml.fqtest index 14f30e09..f637f18b 100644 --- a/format/toml/testdata/toml.fqtest +++ b/format/toml/testdata/toml.fqtest @@ -9,8 +9,8 @@ $ fq . probe.toml } # toml does not support null in arrays # TODO: add uint64 norm test -$ fq -rRs 'fromjson[] | (walk(if type == "array" then map(select(. != null)) end) | try (totoml | ., fromtoml) catch .), "----"' variants.json -totoml cannot be applied to: null +$ fq -rRs 'fromjson[] | (walk(if type == "array" then map(select(. != null)) end) | try (to_toml | ., from_toml) catch .), "----"' variants.json +to_toml cannot be applied to: null ---- toml: top-level values must be Go maps or structs ---- @@ -65,7 +65,7 @@ toml: top-level values must be Go maps or structs error at position 0x0: root object has no values ---- -$ fq -n '"" | fromtoml' +$ fq -n '"" | from_toml' exitcode: 5 stderr: error: error at position 0x0: root object has no values diff --git a/format/toml/testdata/trailing.fqtest b/format/toml/testdata/trailing.fqtest index 3e0d216b..f345984f 100644 --- a/format/toml/testdata/trailing.fqtest +++ b/format/toml/testdata/trailing.fqtest @@ -1,4 +1,4 @@ -$ fq -n '"[a] trailing" | fromtoml._error.error' +$ fq -n '"[a] trailing" | from_toml._error.error' exitcode: 5 stderr: error: error at position 0xc: toml: line 1 (last key "a"): expected a top-level item to end with a newline, comment, or EOF, but got 't' instead diff --git a/format/toml/toml.go b/format/toml/toml.go index 4d315233..0698d872 100644 --- a/format/toml/toml.go +++ b/format/toml/toml.go @@ -26,7 +26,7 @@ func init() { Functions: []string{"_todisplay"}, }) interp.RegisterFS(tomlFS) - interp.RegisterFunc0("totoml", toTOML) + interp.RegisterFunc0("to_toml", toTOML) } func decodeTOML(d *decode.D, _ any) any { @@ -58,7 +58,7 @@ func decodeTOML(d *decode.D, _ any) any { func toTOML(_ *interp.Interp, c any) any { if c == nil { - return gojqex.FuncTypeError{Name: "totoml", V: c} + return gojqex.FuncTypeError{Name: "to_toml", V: c} } b := &bytes.Buffer{} diff --git a/format/vorbis/testdata/vorbis-comment-picture.fqtest b/format/vorbis/testdata/vorbis-comment-picture.fqtest index f907d205..ed338f68 100644 --- a/format/vorbis/testdata/vorbis-comment-picture.fqtest +++ b/format/vorbis/testdata/vorbis-comment-picture.fqtest @@ -1,6 +1,6 @@ # ffmpeg -f lavfi -i sine -f lavfi -i testsrc=s=4x4:r=1:d=1 -t 10ms -disposition:v attached_pic -f flac test.flac # ffmpeg -f lavfi -i sine -t 10ms -f ogg test.ogg -# vorbiscomment -a test.ogg -t METADATA_BLOCK_PICTURE=$(fq -r '.. | select(format=="flac_picture") | tobytes | frombase64' test.flac) +# vorbiscomment -a test.ogg -t METADATA_BLOCK_PICTURE=$(fq -r '.. | select(format=="flac_picture") | tobytes | from_base64' test.flac) # fq '.. | select(format=="vorbis_comment") | tobytes' test.ogg > vorbis-comment-picture $ fq -d vorbis_comment dv vorbis-comment-picture |00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f|0123456789abcdef|.{}: vorbis-comment-picture (vorbis_comment) 0x0-0x11f.7 (288) diff --git a/format/xml/html.md b/format/xml/html.md index 67c27158..1db9be99 100644 --- a/format/xml/html.md +++ b/format/xml/html.md @@ -2,7 +2,7 @@ HTML is decoded in HTML5 mode and will always include ``, `` and `1267650600228229401496703205376" { "a": "1267650600228229401496703205376" diff --git a/format/xml/testdata/help_html.fqtest b/format/xml/testdata/help_html.fqtest index 41639396..141500da 100644 --- a/format/xml/testdata/help_html.fqtest +++ b/format/xml/testdata/help_html.fqtest @@ -24,7 +24,7 @@ HTML is decoded in HTML5 mode and will always include , and See xml format for more examples and how to preserve element order and how to encode to xml. -There is no tohtml function, see toxml instead. +There is no to_html function, see to_xml instead. Element as object ================= diff --git a/format/xml/testdata/help_xml.fqtest b/format/xml/testdata/help_xml.fqtest index dfc3051a..3f9e9c92 100644 --- a/format/xml/testdata/help_xml.fqtest +++ b/format/xml/testdata/help_xml.fqtest @@ -24,7 +24,7 @@ XML can be decoded and encoded into jq values in two ways, elements as object or want to do. The object variant might be easier to query for a specific value but array might be easier to use to generate xml or to query after all elements of some kind etc. -Encoding is done using the toxml function and it will figure what variant that is used based on the input value. Is has two optional +Encoding is done using the to_xml function and it will figure what variant that is used based on the input value. Is has two optional options indent and attribute_prefix. Elements as object @@ -67,7 +67,7 @@ order might be lost. "ccc" # decode to object and encode to xml - $ echo 'bbbccc' | fq -r -d xml -o seq=true 'toxml({indent:2})' + $ echo 'bbbccc' | fq -r -d xml -o seq=true 'to_xml({indent:2})' bbb @@ -109,7 +109,7 @@ Elements are arrays of the shape ["#text": "body text", "attr_name", {key: "attr ] # decode to array and encode to xml - $ echo 'bbbccc' | fq -r -d xml -o array=true -o seq=true 'toxml({indent:2})' + $ echo 'bbbccc' | fq -r -d xml -o array=true -o seq=true 'to_xml({indent:2})' bbb diff --git a/format/xml/testdata/html.fqtest b/format/xml/testdata/html.fqtest index a099ca54..2ab8528c 100644 --- a/format/xml/testdata/html.fqtest +++ b/format/xml/testdata/html.fqtest @@ -9,7 +9,7 @@ $ fq -d html . /test } $ fq -d bytes -ni . all.xml multi_diff.xml multi_same.xml ns.xml simple.xml escape.xml noscript.html null> inputs | {name: input_filename, str: tostring} | slurp("files") -null> spew("files") | .name, (.str | fromhtml | ., (toxml({indent: 2}) | println)) +null> spew("files") | .name, (.str | from_html | ., (to_xml({indent: 2}) | println)) "all.xml" { "html": { @@ -174,7 +174,7 @@ null> spew("files") | .name, (.str | fromhtml | ., (toxml({indent: 2}) | println -null> spew("files") | .name, (.str | fromhtml({seq: true}) | ., (toxml({indent: 2}) | println)) +null> spew("files") | .name, (.str | from_html({seq: true}) | ., (to_xml({indent: 2}) | println)) "all.xml" { "html": { @@ -380,7 +380,7 @@ null> spew("files") | .name, (.str | fromhtml({seq: true}) | ., (toxml({indent: text -null> spew("files") | .name, (.str | fromhtml({array: true}) | ., (toxml({indent: 2}) | println)) +null> spew("files") | .name, (.str | from_html({array: true}) | ., (to_xml({indent: 2}) | println)) "all.xml" [ "html", diff --git a/format/xml/testdata/seq.fqtest b/format/xml/testdata/seq.fqtest index a521e0e3..287786d6 100644 --- a/format/xml/testdata/seq.fqtest +++ b/format/xml/testdata/seq.fqtest @@ -1,2 +1,2 @@ -$ fq -n '{r: {c: {"#seq":1}, b: {"#seq":0}, a: {"#seq":-1}}} | toxml' +$ fq -n '{r: {c: {"#seq":1}, b: {"#seq":0}, a: {"#seq":-1}}} | to_xml' "" diff --git a/format/xml/testdata/test.svg.fqtest b/format/xml/testdata/test.svg.fqtest index df828dcd..d51e3617 100644 --- a/format/xml/testdata/test.svg.fqtest +++ b/format/xml/testdata/test.svg.fqtest @@ -1,4 +1,4 @@ -$ fq -r '. as $a | ., (toxml({indent: 2}) | ., (fromxml | ., (diff($a; .) // "no diff")))' test.svg +$ fq -r '. as $a | ., (to_xml({indent: 2}) | ., (from_xml | ., (diff($a; .) // "no diff")))' test.svg { "svg": { "@height": "2500", @@ -50,7 +50,7 @@ $ fq -r '. as $a | ., (toxml({indent: 2}) | ., (fromxml | ., (diff($a; .) // "no } } no diff -$ fq -r -o array=true '. as $a | ., (toxml({indent: 2}) | ., (fromxml | ., (diff($a; .) // "no diff")))' test.svg +$ fq -r -o array=true '. as $a | ., (to_xml({indent: 2}) | ., (from_xml | ., (diff($a; .) // "no diff")))' test.svg [ "svg", { diff --git a/format/xml/testdata/trailing.fqtest b/format/xml/testdata/trailing.fqtest index d7d46c42..aabe8863 100644 --- a/format/xml/testdata/trailing.fqtest +++ b/format/xml/testdata/trailing.fqtest @@ -1,12 +1,12 @@ -$ fq -n '" trailing" | fromxml' +$ fq -n '" trailing" | from_xml' exitcode: 5 stderr: error: error at position 0x7: root element has trailing non-whitespace " trailing" -$ fq -n '" " | fromxml' +$ fq -n '" " | from_xml' exitcode: 5 stderr: error: error at position 0x8: root element has trailing element -$ fq -n '" " | fromxml' +$ fq -n '" " | from_xml' { "a": "" } diff --git a/format/xml/testdata/xml.fqtest b/format/xml/testdata/xml.fqtest index a71c354e..db43facd 100644 --- a/format/xml/testdata/xml.fqtest +++ b/format/xml/testdata/xml.fqtest @@ -6,7 +6,7 @@ $ fq . probe.xml } $ fq -d bytes -ni . all.xml decl.xml multi_diff.xml multi_same.xml ns.xml simple.xml escape.xml null> inputs | {name: input_filename, str: tostring} | slurp("files") -null> spew("files") | .name, try (.str | fromxml | ., (toxml({indent: 2}) | println)) catch . +null> spew("files") | .name, try (.str | from_xml | ., (to_xml({indent: 2}) | println)) catch . "all.xml" { "elm": { @@ -85,7 +85,7 @@ null> spew("files") | .name, try (.str | fromxml | ., (toxml({indent: 2}) | prin } } &<> -null> spew("files") | .name, try (.str | fromxml({seq: true}) | ., (toxml({indent: 2}) | println)) catch . +null> spew("files") | .name, try (.str | from_xml({seq: true}) | ., (to_xml({indent: 2}) | println)) catch . "all.xml" { "elm": { @@ -177,7 +177,7 @@ null> spew("files") | .name, try (.str | fromxml({seq: true}) | ., (toxml({inden } } &<> -null> spew("files") | .name, try (.str | fromxml({array: true}) | ., (toxml({indent: 2}) | println)) catch . +null> spew("files") | .name, try (.str | from_xml({array: true}) | ., (to_xml({indent: 2}) | println)) catch . "all.xml" [ "elm", @@ -308,7 +308,7 @@ null> spew("files") | .name, try (.str | fromxml({array: true}) | ., (toxml({ind [] ] &<> -null> {doc: {a: "", "#text": "text", "#comment": "comment", "@attr": "value"}} | toxml, toxml({indent: 1}), toxml({indent: 8}) | println +null> {doc: {a: "", "#text": "text", "#comment": "comment", "@attr": "value"}} | to_xml, to_xml({indent: 1}), to_xml({indent: 8}) | println text text @@ -318,7 +318,7 @@ null> {doc: {a: "", "#text": "text", "#comment": "comment", "@attr": "value"}} | -null> ["doc", {"#text": "text", "#comment": "comment", attr: "value"}, [["a"]]] | toxml, toxml({indent: 1}), toxml({indent: 8}) | println +null> ["doc", {"#text": "text", "#comment": "comment", attr: "value"}, [["a"]]] | to_xml, to_xml({indent: 1}), to_xml({indent: 8}) | println text text @@ -328,16 +328,16 @@ null> ["doc", {"#text": "text", "#comment": "comment", attr: "value"}, [["a"]]] -null> {a: ""} | toxml +null> {a: ""} | to_xml "" -null> {a: [""]} | toxml +null> {a: [""]} | to_xml "" -null> {a: {"@attr": "value", "#text": "text", "#comment": "comment"}} | toxml +null> {a: {"@attr": "value", "#text": "text", "#comment": "comment"}} | to_xml "text" -null> {a: ["b", "c"]} | toxml +null> {a: ["b", "c"]} | to_xml "bc" -null> {a: [123, null, true, false]} | toxml +null> {a: [123, null, true, false]} | to_xml "123truefalse" -null> 123 | toxml -error: toxml cannot be applied to: number (123) +null> 123 | to_xml +error: to_xml cannot be applied to: number (123) null> ^D diff --git a/format/xml/testdata/xmlentities.fqtest b/format/xml/testdata/xmlentities.fqtest index 5b764ecb..c0d3d7d8 100644 --- a/format/xml/testdata/xmlentities.fqtest +++ b/format/xml/testdata/xmlentities.fqtest @@ -1,3 +1,3 @@ -$ fq -n '"abc&<>" | fromxmlentities | ., toxmlentities' +$ fq -n '"abc&<>" | from_xmlentities | ., to_xmlentities' "abc&<>" "abc&<>" diff --git a/format/xml/xml.go b/format/xml/xml.go index bd040266..4d839150 100644 --- a/format/xml/xml.go +++ b/format/xml/xml.go @@ -47,11 +47,11 @@ func init() { Functions: []string{"_todisplay"}, }) interp.RegisterFS(xmlFS) - interp.RegisterFunc1("toxml", toXML) - interp.RegisterFunc0("fromxmlentities", func(_ *interp.Interp, c string) any { + interp.RegisterFunc1("to_xml", toXML) + interp.RegisterFunc0("from_xmlentities", func(_ *interp.Interp, c string) any { return html.UnescapeString(c) }) - interp.RegisterFunc0("toxmlentities", func(_ *interp.Interp, c string) any { + interp.RegisterFunc0("to_xmlentities", func(_ *interp.Interp, c string) any { return html.EscapeString(c) }) } @@ -488,12 +488,12 @@ func toXMLFromArray(c any, opts ToXMLOpts) any { ca, ok := c.([]any) if !ok { - return gojqex.FuncTypeError{Name: "toxml", V: c} + return gojqex.FuncTypeError{Name: "to_xml", V: c} } n, ok := f(ca) if !ok { // TODO: better error - return gojqex.FuncTypeError{Name: "toxml", V: c} + return gojqex.FuncTypeError{Name: "to_xml", V: c} } bb := &bytes.Buffer{} e := xml.NewEncoder(bb) @@ -514,5 +514,5 @@ func toXML(_ *interp.Interp, c any, opts ToXMLOpts) any { } else if v, ok := gojqex.Cast[[]any](c); ok { return toXMLFromArray(gojqex.NormalizeToStrings(v), opts) } - return gojqex.FuncTypeError{Name: "toxml", V: c} + return gojqex.FuncTypeError{Name: "to_xml", V: c} } diff --git a/format/xml/xml.jq b/format/xml/xml.jq index 4b7407a9..d6649a8d 100644 --- a/format/xml/xml.jq +++ b/format/xml/xml.jq @@ -1,2 +1,2 @@ -def toxml: toxml(null); +def to_xml: to_xml(null); def _xml__todisplay: tovalue; diff --git a/format/xml/xml.md b/format/xml/xml.md index 9dfc4470..43984427 100644 --- a/format/xml/xml.md +++ b/format/xml/xml.md @@ -3,7 +3,7 @@ Which variant to use depends a bit what you want to do. The object variant might to query for a specific value but array might be easier to use to generate xml or to query after all elements of some kind etc. -Encoding is done using the `toxml` function and it will figure what variant that is used based on the input value. +Encoding is done using the `to_xml` function and it will figure what variant that is used based on the input value. Is has two optional options `indent` and `attribute_prefix`. ### Elements as object @@ -46,7 +46,7 @@ $ echo 'bbbccc' | fq '.a.c["#text"]' "ccc" # decode to object and encode to xml -$ echo 'bbbccc' | fq -r -d xml -o seq=true 'toxml({indent:2})' +$ echo 'bbbccc' | fq -r -d xml -o seq=true 'to_xml({indent:2})' bbb @@ -89,7 +89,7 @@ $ echo 'bbbccc' | fq -d xml -o array=true ] # decode to array and encode to xml -$ echo 'bbbccc' | fq -r -d xml -o array=true -o seq=true 'toxml({indent:2})' +$ echo 'bbbccc' | fq -r -d xml -o array=true -o seq=true 'to_xml({indent:2})' bbb diff --git a/format/yaml/testdata/bigint.fqtest b/format/yaml/testdata/bigint.fqtest index 82a1c874..7c2e0a2f 100644 --- a/format/yaml/testdata/bigint.fqtest +++ b/format/yaml/testdata/bigint.fqtest @@ -1,4 +1,4 @@ -$ fq -n "{a: bsl(1;100)} | toyaml | ., fromyaml" +$ fq -n "{a: bsl(1;100)} | to_yaml | ., from_yaml" "a: \"1267650600228229401496703205376\"\n" { "a": "1267650600228229401496703205376" diff --git a/format/yaml/testdata/trailing.fqtest b/format/yaml/testdata/trailing.fqtest index a0ad25aa..c0a818b9 100644 --- a/format/yaml/testdata/trailing.fqtest +++ b/format/yaml/testdata/trailing.fqtest @@ -1,8 +1,8 @@ -$ fq -n '"- a\ntrailing" | fromyaml._error.error' +$ fq -n '"- a\ntrailing" | from_yaml._error.error' exitcode: 5 stderr: error: error at position 0xc: yaml: line 2: could not find expected ':' -$ fq -n '`{"a":123}{"b":444}` | fromyaml' +$ fq -n '`{"a":123}{"b":444}` | from_yaml' exitcode: 5 stderr: error: error at position 0x12: trialing data after top-level value diff --git a/format/yaml/testdata/yaml.fqtest b/format/yaml/testdata/yaml.fqtest index aaae28a1..2703e2f2 100644 --- a/format/yaml/testdata/yaml.fqtest +++ b/format/yaml/testdata/yaml.fqtest @@ -8,7 +8,7 @@ $ fq . probe.yaml } } # TODO: add uint64 norm test -$ fq -rRs 'fromjson[] | (try (toyaml | ., fromyaml) catch .), "----"' variants.json +$ fq -rRs 'fromjson[] | (try (to_yaml | ., from_yaml) catch .), "----"' variants.json null error at position 0x5: root not object or array diff --git a/format/yaml/yaml.go b/format/yaml/yaml.go index 9d517a5b..3174c858 100644 --- a/format/yaml/yaml.go +++ b/format/yaml/yaml.go @@ -29,7 +29,7 @@ func init() { Functions: []string{"_todisplay"}, }) interp.RegisterFS(yamlFS) - interp.RegisterFunc0("toyaml", toYAML) + interp.RegisterFunc0("to_yaml", toYAML) } func decodeYAML(d *decode.D, _ any) any { diff --git a/pkg/interp/.jq-lsp.jq b/pkg/interp/.jq-lsp.jq index f7e95f57..2398c4a1 100644 --- a/pkg/interp/.jq-lsp.jq +++ b/pkg/interp/.jq-lsp.jq @@ -26,6 +26,6 @@ def open: empty; def scope: empty; # used by help.jq -def tojq: empty; +def to_jq: empty; # used by funcs.jq iprint -def toradix($base): empty; \ No newline at end of file +def to_radix($base): empty; \ No newline at end of file diff --git a/pkg/interp/format_decode.jq b/pkg/interp/format_decode.jq index 46ec79c0..cc3c4e5f 100644 --- a/pkg/interp/format_decode.jq +++ b/pkg/interp/format_decode.jq @@ -1,15 +1,18 @@ # note this is a "dynamic" include, output string will be used as source -# generates decode functions -# frommp3 and mp3 calls decode("mp3") +# generates decode functions, ex: +# mp3/0 calls decode("mp3"; {}) +# mp3/1 calls decode("mp3"; $opts) +# from_mp3/* same but throws error on decode error [ _registry as $r | $r.groups | to_entries[] # TODO: nicer way to skip "all" which also would override builtin all/* +# skip_decode_function is used to skip bits/bytes as they are special tobits/tobytes | select(.key != "all" and ($r.formats[.key].skip_decode_function | not)) | "def \(.key)($opts): decode(\(.key | tojson); $opts);" , "def \(.key): decode(\(.key | tojson); {});" -, "def from\(.key)($opts): decode(\(.key | tojson); $opts) | if ._error then error(._error.error) end;" -, "def from\(.key): from\(.key)({});" +, "def from_\(.key)($opts): decode(\(.key | tojson); $opts) | if ._error then error(._error.error) end;" +, "def from_\(.key): from_\(.key)({});" ] | join("\n") diff --git a/pkg/interp/funcs.jq b/pkg/interp/funcs.jq index b35ceca7..88d79ac0 100644 --- a/pkg/interp/funcs.jq +++ b/pkg/interp/funcs.jq @@ -109,10 +109,10 @@ def table(colmap; render): # TODO: move? def iprint: { - bin: "0b\(toradix(2))", - oct: "0o\(toradix(8))", + bin: "0b\(to_radix(2))", + oct: "0o\(to_radix(8))", dec: "\(.)", - hex: "0x\(toradix(16))", + hex: "0x\(to_radix(16))", str: (try ([.] | implode) catch null), }; diff --git a/pkg/interp/help.jq b/pkg/interp/help.jq index 4ce339b1..16c71c57 100644 --- a/pkg/interp/help.jq +++ b/pkg/interp/help.jq @@ -70,7 +70,7 @@ def _help_format_enrich($arg0; $f; $include_basic): , shell: "\($arg0) -d \($f.name)\($f.decode_in_arg | to_entries | map(" -o ", .key, "=", (.value | tojson)) | join("")) . file" } , { comment: "Decode value as \($f.name)" - , expr: "\($f.name)(\($f.decode_in_arg | tojq))" + , expr: "\($f.name)(\($f.decode_in_arg | to_jq))" } ] end @@ -85,7 +85,7 @@ def _help($arg0; $topic): , " fq . file" , " fq d file" , " fq tovalue file" - , " fq -r totoml file.yml" + , " fq -r to_toml file.yml" , " fq -s -d html 'map(.html.head.title?)' *.html" , " cat file.cbor | fq -d cbor torepr" , " fq 'grep(\"^main$\") | parent' /bin/ls" diff --git a/pkg/interp/jqtest.jq b/pkg/interp/jqtest.jq index 162a37f3..740bc34c 100644 --- a/pkg/interp/jqtest.jq +++ b/pkg/interp/jqtest.jq @@ -6,7 +6,7 @@ # + # ... # -def fromjqtest: +def from_jqtest: [ foreach (split("\n")[], "") as $l ( { current_line: 0 , nr: 1 @@ -60,7 +60,7 @@ def fromjqtest: def run_tests: def _f: - ( fromjqtest[] + ( from_jqtest[] | . as $c | try if .error | not then diff --git a/pkg/interp/testdata/args.fqtest b/pkg/interp/testdata/args.fqtest index 62f9d0df..62617f9b 100644 --- a/pkg/interp/testdata/args.fqtest +++ b/pkg/interp/testdata/args.fqtest @@ -17,7 +17,7 @@ Example usages: fq . file fq d file fq tovalue file - fq -r totoml file.yml + fq -r to_toml file.yml fq -s -d html 'map(.html.head.title?)' *.html cat file.cbor | fq -d cbor torepr fq 'grep("^main$") | parent' /bin/ls diff --git a/pkg/interp/testdata/gojq.fqtest b/pkg/interp/testdata/gojq.fqtest index 7753c15e..c8aac5cb 100644 --- a/pkg/interp/testdata/gojq.fqtest +++ b/pkg/interp/testdata/gojq.fqtest @@ -1,5 +1,5 @@ # 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) +# 0xf_ffff_ffff_fffff_fffff-1 | to_radix(2,8,16) $ fq -n '0b1111111111111111111111111111111111111111111111111111111111111111111111111110, 0o17777777777777777777777776, 0xffffffffffffffffffe' 75557863725914323419134 75557863725914323419134 @@ -255,7 +255,7 @@ $ fq -d mp3 '.frames[0] | to_entries[].key' test.mp3 "crc_calculated" # xml, csv does string normalization, make sure it works with nested JQValue:s # TODO: move this test as it depends on xml -$ fq -r '.headers[0] | toxml({indent: 2})' test.mp3 +$ fq -r '.headers[0] | to_xml({indent: 2})' test.mp3 false