Upgrade html-to-markdown to v2.

Now that it supports tables, we can use it.

Also fixed a deprecation warning with goldmark 1.7.11
This commit is contained in:
Olivier Meunier
2025-05-07 20:09:08 +02:00
parent ec6e40cc89
commit b128753605
4 changed files with 64 additions and 68 deletions

5
go.mod
View File

@@ -6,8 +6,7 @@ toolchain go1.24.2
require (
github.com/CloudyKit/jet/v6 v6.3.1
github.com/JohannesKaufmann/html-to-markdown v1.6.0
github.com/PuerkitoBio/goquery v1.10.3
github.com/JohannesKaufmann/html-to-markdown/v2 v2.3.2
github.com/antchfx/htmlquery v1.3.4
github.com/antchfx/xmlquery v1.4.4
github.com/anthonynsimon/bild v0.14.0
@@ -53,6 +52,7 @@ require (
require (
github.com/CloudyKit/fastprinter v0.0.0-20200109182630-33d98a066a53 // indirect
github.com/JohannesKaufmann/dom v0.2.0 // indirect
github.com/andybalholm/cascadia v1.3.3 // indirect
github.com/antchfx/xpath v1.3.4 // indirect
github.com/beorn7/perks v1.0.1 // indirect
@@ -71,6 +71,7 @@ require (
github.com/jackc/pgpassfile v1.0.0 // indirect
github.com/jackc/pgservicefile v0.0.0-20240606120523-5a60cdf6a761 // indirect
github.com/jackc/puddle/v2 v2.2.2 // indirect
github.com/kr/text v0.1.0 // indirect
github.com/lib/pq v1.10.9 // indirect
github.com/mattn/go-sqlite3 v1.14.24 // indirect
github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect

28
go.sum
View File

@@ -4,14 +4,12 @@ github.com/CloudyKit/jet/v6 v6.3.1 h1:6IAo5Cx21xrHVaR8zzXN5gJatKV/wO7Nf6bfCnCSbU
github.com/CloudyKit/jet/v6 v6.3.1/go.mod h1:lf8ksdNsxZt7/yH/3n4vJQWA9RUq4wpaHtArHhGVMOw=
github.com/DATA-DOG/go-sqlmock v1.5.0 h1:Shsta01QNfFxHCfpW6YH2STWB0MudeXXEWMr20OEh60=
github.com/DATA-DOG/go-sqlmock v1.5.0/go.mod h1:f/Ixk793poVmq4qj/V1dPUg2JEAKC73Q5eFN3EC/SaM=
github.com/JohannesKaufmann/html-to-markdown v1.6.0 h1:04VXMiE50YYfCfLboJCLcgqF5x+rHJnb1ssNmqpLH/k=
github.com/JohannesKaufmann/html-to-markdown v1.6.0/go.mod h1:NUI78lGg/a7vpEJTz/0uOcYMaibytE4BUOQS8k78yPQ=
github.com/JohannesKaufmann/dom v0.2.0 h1:1bragmEb19K8lHAqgFgqCpiPCFEZMTXzOIEjuxkUfLQ=
github.com/JohannesKaufmann/dom v0.2.0/go.mod h1:57iSUl5RKric4bUkgos4zu6Xt5LMHUnw3TF1l5CbGZo=
github.com/JohannesKaufmann/html-to-markdown/v2 v2.3.2 h1:eeMLttqTjTgILD6no79Ge96V7Wv8pWDfMVn4jy+koIY=
github.com/JohannesKaufmann/html-to-markdown/v2 v2.3.2/go.mod h1:HtsP+1Fchp4dVvaiIsLHAl/yqL3H1YLwqLC9kNwqQEg=
github.com/Masterminds/semver/v3 v3.2.1 h1:RN9w6+7QoMeJVGyfmbcgs28Br8cvmnucEXnY0rYXWg0=
github.com/Masterminds/semver/v3 v3.2.1/go.mod h1:qvl/7zhW3nngYb5+80sSMF+FG2BjYrf8m9wsX0PNOMQ=
github.com/PuerkitoBio/goquery v1.9.2/go.mod h1:GHPCaP0ODyyxqcNoFGYlAprUFH81NuRPd0GX3Zu2Mvk=
github.com/PuerkitoBio/goquery v1.10.3 h1:pFYcNSqHxBD06Fpj/KsbStFRsgRATgnf3LeXiUkhzPo=
github.com/PuerkitoBio/goquery v1.10.3/go.mod h1:tMUX0zDMHXYlAQk6p35XxQMqMweEKB7iK7iLNd4RH4Y=
github.com/andybalholm/cascadia v1.3.2/go.mod h1:7gtRlve5FxPPgIgX36uWBX58OdBsSS6lUvCFb+h7KvU=
github.com/andybalholm/cascadia v1.3.3 h1:AG2YHrzJIm4BZ19iwJ/DAua6Btl3IwJX+VI4kktS1LM=
github.com/andybalholm/cascadia v1.3.3/go.mod h1:xNd9bqTn98Ln4DwST8/nG+H0yuB8Hmgu1YHNnWw0GeA=
github.com/antchfx/htmlquery v1.3.4 h1:Isd0srPkni2iNTWCwVj/72t7uCphFeor5Q8nCzj1jdQ=
@@ -108,7 +106,6 @@ github.com/klauspost/compress v1.18.0 h1:c/Cqfb0r+Yi+JtIEq73FWXVkRonBlf0CRNYc8Zt
github.com/klauspost/compress v1.18.0/go.mod h1:2Pp+KzxcywXVXMr50+X0Q/Lsb43OQHYWRCY2AiWywWQ=
github.com/komkom/toml v0.1.2 h1:SexwnY3JOR0kU9F/xxw/129BPCvuKi6/E89PZ4kSSBo=
github.com/komkom/toml v0.1.2/go.mod h1:cgnL/ntRyMHaZuDy9wREJHWY1Cb2HEINK7U0YhpcTa8=
github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
@@ -143,7 +140,6 @@ github.com/onsi/gomega v1.18.1 h1:M1GfJqGRrBrrGGsbxzV5dqM2U2ApXefZCQpkukxYRLE=
github.com/onsi/gomega v1.18.1/go.mod h1:0q+aL8jAiMXy9hbwj2mr5GziHiwhAIQpFmmtT5hitRs=
github.com/phsym/console-slog v0.3.1 h1:Fuzcrjr40xTc004S9Kni8XfNsk+qrptQmyR+wZw9/7A=
github.com/phsym/console-slog v0.3.1/go.mod h1:oJskjp/X6e6c0mGpfP8ELkfKUsrkDifYRAqJQgmdDS0=
github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
@@ -160,9 +156,8 @@ github.com/rivo/uniseg v0.1.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJ
github.com/rogpeppe/go-internal v1.10.0 h1:TMyTOH3F/DB16zRVcYyreMH6GnZZrwQVAoYjRBZyWFQ=
github.com/rogpeppe/go-internal v1.10.0/go.mod h1:UQnix2H7Ngw/k4C5ijL5+65zddjncjaFoBhdsK/akog=
github.com/scylladb/termtables v0.0.0-20191203121021-c4c0b6d42ff4/go.mod h1:C1a7PQSMz9NShzorzCiG2fk9+xuCgLkPeCvMHYR2OWg=
github.com/sebdah/goldie/v2 v2.5.3 h1:9ES/mNN+HNUbNWpVAlrzuZ7jE+Nrczbj8uFRjM7624Y=
github.com/sebdah/goldie/v2 v2.5.3/go.mod h1:oZ9fp0+se1eapSRjfYbsV/0Hqhbuu3bJVvKI/NNtssI=
github.com/sergi/go-diff v1.0.0/go.mod h1:0CfEIISq7TuYL3j771MWULgwwjU+GofnZX9QAmXWZgo=
github.com/sebdah/goldie/v2 v2.5.5 h1:rx1mwF95RxZ3/83sdS4Yp7t2C5TCokvWP4TBRbAyEWY=
github.com/sebdah/goldie/v2 v2.5.5/go.mod h1:oZ9fp0+se1eapSRjfYbsV/0Hqhbuu3bJVvKI/NNtssI=
github.com/sergi/go-diff v1.3.1 h1:xkr+Oxo4BOQKmkn/B9eMK0g5Kg/983T9DqqPHwYqD+8=
github.com/sergi/go-diff v1.3.1/go.mod h1:aMJSSKb2lpPvRNec0+w3fl7LP9IOFzdc9Pa4NFbPK1I=
github.com/skip2/go-qrcode v0.0.0-20200617195104-da1b6568686e h1:MRM5ITcdelLK2j1vwZ3Je0FKVCfqOLp5zO6trqMLYs0=
@@ -171,7 +166,6 @@ github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+
github.com/stretchr/objx v0.5.2 h1:xuMeJ0Sdp5ZMRXx/aWO6RZxdr3beISkG5/G/aIRr3pY=
github.com/stretchr/objx v0.5.2/go.mod h1:FRsXN1f5AsAjCGJKqEizvkpNtU+EGNCLh3NxZ/8L+MA=
github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
github.com/stretchr/testify v1.6.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
github.com/stretchr/testify v1.10.0 h1:Xv5erBjTwe/5IxqUQTdXv5kgmIvbHo3QQyRwhJsOfJA=
@@ -188,7 +182,6 @@ github.com/toorop/go-dkim v0.0.0-20250226130143-9025cce95817/go.mod h1:BzWtXXrXz
github.com/xhit/go-simple-mail/v2 v2.16.0 h1:ouGy/Ww4kuaqu2E2UrDw7SvLaziWTB60ICLkIkNVccA=
github.com/xhit/go-simple-mail/v2 v2.16.0/go.mod h1:b7P5ygho6SYE+VIqpxA6QkYfv4teeyG4MKqB3utRu98=
github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
github.com/yuin/goldmark v1.7.1/go.mod h1:uzxRWxtg69N339t3louHJ7+O03ezfj6PlliRlaOzY1E=
github.com/yuin/goldmark v1.7.11 h1:ZCxLyDMtz0nT2HFfsYG8WZ47Trip2+JyLysKcMYE5bo=
github.com/yuin/goldmark v1.7.11/go.mod h1:ip/1k0VRfGynBgxOz0yCqHrbZXhcjxyuS66Brc7iBKg=
github.com/yuin/goldmark-meta v1.1.0 h1:pWw+JLHGZe8Rk0EGsMVssiNb/AaPMHfSRszZeUeiOUc=
@@ -199,7 +192,6 @@ golang.org/x/crypto v0.0.0-20190605123033-f99c8df09eb5/go.mod h1:yigFU9vqHzYiE8U
golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
golang.org/x/crypto v0.13.0/go.mod h1:y6Z2r+Rw4iayiXXAIxJIDAJ1zMW4yaTpebo8fPOliYc=
golang.org/x/crypto v0.19.0/go.mod h1:Iy9bg/ha4yyC70EfRS8jz+B6ybOBKMaSxLj6P6oBDfU=
golang.org/x/crypto v0.22.0/go.mod h1:vr6Su+7cTlO45qkww3VDJlzDn0ctJvRgYbC2NvXHt+M=
golang.org/x/crypto v0.23.0/go.mod h1:CKFgDieR+mRhux2Lsu27y0fO304Db0wZe70UKqHu0v8=
golang.org/x/crypto v0.31.0/go.mod h1:kDsLvtWBEx7MV9tJOj9bnXsPbxwJQ6csT/x4KIN4Ssk=
golang.org/x/crypto v0.38.0 h1:jt+WWG8IZlBnVbomuhg2Mdq0+BBQaHbtqHEFEigjUV8=
@@ -217,11 +209,9 @@ golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLL
golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
golang.org/x/net v0.6.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
golang.org/x/net v0.9.0/go.mod h1:d48xBJpPfHeWQsugry2m+kC02ZBRGRgulfHnEXEuWns=
golang.org/x/net v0.10.0/go.mod h1:0qNGK6F8kojg2nk9dLZ2mShWaEBan6FAoqfSigmmuDg=
golang.org/x/net v0.15.0/go.mod h1:idbUs1IY1+zTqbi8yxTbhexhEEk5ur9LInksu6HrEpk=
golang.org/x/net v0.21.0/go.mod h1:bIjVDfnllIU7BJ2DNgfnXvpSvtn8VRwhlsaeUTyUS44=
golang.org/x/net v0.24.0/go.mod h1:2Q7sJY5mzlzWjKtYUEXSlBWCdyaioyXzRB2RtU8KVE8=
golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM=
golang.org/x/net v0.33.0/go.mod h1:HXLR5J+9DxmrqMwG9qjGCxZ+zKXxBru04zlTvWlWuN4=
golang.org/x/net v0.40.0 h1:79Xs7wF06Gbdcg4kdCCIQArK11Z1hr5POQ6+fIYHNuY=
@@ -242,11 +232,9 @@ golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBc
golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.7.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.12.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.17.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/sys v0.19.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/sys v0.20.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/sys v0.28.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/sys v0.33.0 h1:q3i8TbbEz+JRD9ywIRlyRAQbM0qF7hu24q3teo2hbuw=
@@ -255,11 +243,9 @@ golang.org/x/telemetry v0.0.0-20240228155512-f48c80bd79b2/go.mod h1:TeRTkGYfJXct
golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k=
golang.org/x/term v0.7.0/go.mod h1:P32HKFT3hSsZrRxla30E9HqToFYAQPCMs/zFMBUFqPY=
golang.org/x/term v0.8.0/go.mod h1:xPskH00ivmX89bAKVGSKKtLOWNx2+17Eiy94tnKShWo=
golang.org/x/term v0.12.0/go.mod h1:owVbMEjm3cBLCHdkQu9b1opXd4ETQWc3BhuQGKgXgvU=
golang.org/x/term v0.17.0/go.mod h1:lLRBjIVuehSbZlaOtGMbcMncT+aqLLLmKrsjNrUguwk=
golang.org/x/term v0.19.0/go.mod h1:2CuTdWZ7KHSQwUzKva0cbMg6q2DMI3Mmxp+gKJbskEk=
golang.org/x/term v0.20.0/go.mod h1:8UkIAJTvZgivsXaD6/pH6U9ecQzZ45awqEOzuCvwpFY=
golang.org/x/term v0.27.0/go.mod h1:iMsnZpn0cago0GOrHO2+Y7u7JPn5AylBrcoWkElMTSM=
golang.org/x/term v0.32.0 h1:DR4lr0TjUs3epypdhTOkMmuF5CDFJ/8pOnbzMZPQ7bg=
@@ -286,7 +272,6 @@ golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8T
google.golang.org/protobuf v1.36.6 h1:z1NpPI8ku2WgiWnf+t9wTPsn6eP1L7ksHUlkfLvd9xY=
google.golang.org/protobuf v1.36.6/go.mod h1:jduwjTPXsFjZGTmRluh+L6NjiWu7pchiJ2/5YcXBHnY=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
gopkg.in/hlandau/easymetric.v1 v1.0.0 h1:ZbfbH7W3giuVDjWUoFhDOjjv20hiPr5HZ2yMV5f9IeE=
@@ -297,7 +282,6 @@ gopkg.in/hlandau/passlib.v1 v1.0.11 h1:vKeHwGRdWBD9mm4bJ56GAAdBXpFUYvg/BYYkmphjn
gopkg.in/hlandau/passlib.v1 v1.0.11/go.mod h1:wxGAv2CtQHlzWY8NJp+p045yl4WHyX7v2T6XbOcmqjM=
gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7 h1:uRGJdciOHaEIrze2W8Q3AKkepLTh2hOroT7a+7czfdQ=
gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7/go.mod h1:dt/ZhP58zS4L8KSrWDmTeBkI65Dw0HsyUHuEVlX15mw=
gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
gopkg.in/yaml.v2 v2.4.0 h1:D8xgwECY7CYvx+Y2n4sBz93Jn9JRvxdiyyo8CTfuKaY=
gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ=
gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

View File

@@ -19,10 +19,12 @@ import (
"strings"
"time"
html2md "github.com/JohannesKaufmann/html-to-markdown"
"github.com/JohannesKaufmann/html-to-markdown/plugin"
"github.com/PuerkitoBio/goquery"
"github.com/JohannesKaufmann/html-to-markdown/v2/converter"
"github.com/JohannesKaufmann/html-to-markdown/v2/plugin/base"
"github.com/JohannesKaufmann/html-to-markdown/v2/plugin/commonmark"
"github.com/JohannesKaufmann/html-to-markdown/v2/plugin/table"
"github.com/gabriel-vasile/mimetype"
"golang.org/x/net/html"
"golang.org/x/net/idna"
"gopkg.in/yaml.v3"
@@ -31,6 +33,15 @@ import (
"codeberg.org/readeck/readeck/pkg/utils"
)
var html2md = converter.NewConverter(
converter.WithPlugins(
base.NewBasePlugin(),
commonmark.NewCommonmarkPlugin(),
table.NewTablePlugin(),
&html2mdAnnotationPlugin{},
),
)
// MarkdownExporter is an content exporter that produces markdown.
type MarkdownExporter struct {
HTMLConverter
@@ -64,26 +75,20 @@ func NewMarkdownExporter(baseURL *url.URL, mediaBaseURL *url.URL) MarkdownExport
// If the request contains "Accept: multipart/alternative", it returns a multipart response
// that contains images for the exported bookmarks.
func (e MarkdownExporter) Export(ctx context.Context, w io.Writer, r *http.Request, bookmarks []*bookmarks.Bookmark) error {
converter := html2md.NewConverter("", true, nil)
converter.Use(plugin.Strikethrough(""))
converter.Use(plugin.Table())
converter.Use(plugin.GitHubFlavored())
converter.Use(mdAnnotation())
ctx = WithAnnotationTag(ctx, "rd-annotation", nil)
accepted := accept.NegotiateContentType(r.Header, []string{"text/markdown", "application/zip", "multipart/alternative"}, "text/markdown")
switch accepted {
case "application/zip":
return e.exportZip(ctx, w, converter, bookmarks)
return e.exportZip(ctx, w, bookmarks)
case "multipart/alternative":
return e.exportMultipart(ctx, w, converter, bookmarks)
return e.exportMultipart(ctx, w, bookmarks)
default:
return e.exportTextOnly(ctx, w, converter, bookmarks)
return e.exportTextOnly(ctx, w, bookmarks)
}
}
func (e MarkdownExporter) exportTextOnly(ctx context.Context, w io.Writer, converter *html2md.Converter, bookmarks []*bookmarks.Bookmark) error {
func (e MarkdownExporter) exportTextOnly(ctx context.Context, w io.Writer, bookmarks []*bookmarks.Bookmark) error {
if w, ok := w.(http.ResponseWriter); ok {
w.Header().Set("Content-Type", "text/markdown; charset=utf-8")
}
@@ -95,14 +100,14 @@ func (e MarkdownExporter) exportTextOnly(ctx context.Context, w io.Writer, conve
if i > 0 {
fmt.Fprint(w, "\n------------------------------------------------------------\nn") //nolint:errcheck
}
if err := e.writeArticle(c, w, converter, b, len(bookmarks) == 1); err != nil {
if err := e.writeArticle(c, w, b, len(bookmarks) == 1); err != nil {
slog.Error("export", slog.Any("err", err))
}
}
return nil
}
func (e MarkdownExporter) exportMultipart(ctx context.Context, w io.Writer, converter *html2md.Converter, bookmarks []*bookmarks.Bookmark) error {
func (e MarkdownExporter) exportMultipart(ctx context.Context, w io.Writer, bookmarks []*bookmarks.Bookmark) error {
mp := multipart.NewWriter(w)
defer mp.Close() //nolint:errcheck
if w, ok := w.(http.ResponseWriter); ok {
@@ -125,7 +130,7 @@ func (e MarkdownExporter) exportMultipart(ctx context.Context, w io.Writer, conv
if err != nil {
return err
}
if err := e.writeArticle(ctx, part, converter, b, true); err != nil {
if err := e.writeArticle(ctx, part, b, true); err != nil {
return err
}
@@ -162,7 +167,7 @@ func (e MarkdownExporter) exportMultipart(ctx context.Context, w io.Writer, conv
return nil
}
func (e MarkdownExporter) exportZip(ctx context.Context, w io.Writer, converter *html2md.Converter, bookmarks []*bookmarks.Bookmark) error {
func (e MarkdownExporter) exportZip(ctx context.Context, w io.Writer, bookmarks []*bookmarks.Bookmark) error {
zw := zip.NewWriter(w)
defer zw.Close() //nolint:errcheck
@@ -215,7 +220,7 @@ func (e MarkdownExporter) exportZip(ctx context.Context, w io.Writer, converter
if err != nil {
return err
}
if err := e.writeArticle(ctx, fd, converter, b, true); err != nil {
if err := e.writeArticle(ctx, fd, b, true); err != nil {
return err
}
@@ -258,17 +263,12 @@ func (e MarkdownExporter) getImageURL(ctx context.Context, b *bookmarks.Bookmark
return e.mediaBaseURL.JoinPath(b.FilePath, "img", path.Base(name)).String()
}
func (e MarkdownExporter) writeArticle(ctx context.Context, w io.Writer, converter *html2md.Converter, b *bookmarks.Bookmark, withMeta bool) error {
func (e MarkdownExporter) writeArticle(ctx context.Context, w io.Writer, b *bookmarks.Bookmark, withMeta bool) error {
r, err := e.GetArticle(ctx, b)
if err != nil {
return err
}
buf, err := converter.ConvertReader(r)
if err != nil {
return err
}
intro := new(bytes.Buffer)
if withMeta {
fmt.Fprintln(intro, "---")
@@ -301,7 +301,12 @@ func (e MarkdownExporter) writeArticle(ctx context.Context, w io.Writer, convert
fmt.Fprintf(intro, "[Video on %s](%s)\n\n", b.SiteName, b.URL)
}
_, err = io.Copy(w, io.MultiReader(intro, &buf))
md, err := html2md.ConvertReader(r)
if err != nil {
return err
}
_, err = io.Copy(w, io.MultiReader(intro, bytes.NewReader(md)))
return err
}
@@ -333,23 +338,29 @@ func (e MarkdownExporter) writeResource(mp *multipart.Writer, resource *zip.File
return err
}
// mdAnnotation is an html-to-markdown plugin that converts rd-annotation tags
// html2mdAnnotationPlugin is an html-to-markdown plugin that converts rd-annotation tags
// to "=={content}==" form, that's compatible with at least Obsidian.
func mdAnnotation() html2md.Plugin {
return func(_ *html2md.Converter) []html2md.Rule {
return []html2md.Rule{
{
Filter: []string{"rd-annotation"},
Replacement: func(content string, selec *goquery.Selection, _ *html2md.Options) *string {
content = strings.TrimSpace(content)
if content == "" {
return &content
}
content = "==" + content + "=="
content = html2md.AddSpaceIfNessesary(selec, content)
return &content
},
},
}
}
type html2mdAnnotationPlugin struct{}
func (s *html2mdAnnotationPlugin) Name() string {
return "annotation"
}
func (s *html2mdAnnotationPlugin) Init(conv *converter.Converter) error {
conv.Register.RendererFor("rd-annotation", converter.TagTypeInline, s.render, converter.PriorityStandard)
return nil
}
func (s *html2mdAnnotationPlugin) render(ctx converter.Context, w converter.Writer, n *html.Node) converter.RenderStatus {
buf := new(bytes.Buffer)
ctx.RenderChildNodes(ctx, buf, n)
content := buf.String()
if strings.TrimSpace(content) == "" {
w.WriteString(content) // nolint:errcheck
return converter.RenderSuccess
}
w.WriteString("==" + content + "==") // nolint:errcheck
return converter.RenderSuccess
}

View File

@@ -99,7 +99,7 @@ func (t *titleExtract) Transform(doc *ast.Document, reader text.Reader, ctx pars
if !ok || n.Level != 1 {
return ast.WalkContinue, nil
}
ctx.Set(ctxTitleKey, string(n.Text(reader.Source())))
ctx.Set(ctxTitleKey, string(n.Lines().Value(reader.Source())))
return ast.WalkStop, nil
})