add option to access original message (#2125)

* draft API to deal with uncut message texts

* add column mime_modified

* add mime_modified flag to MimeParser and save it in the database

* save mime_headers also when mime_modified is set

* cargo fmt

* set mime_modified on parsed html-texts and when there are multiple alternative-parts; add test for that

* prototype functions, add to repl and ffi

* use correct mime_modified flag

* basically parse Mime-Structure to HTML

* add basic tests for HTML-parsing

* convert text/plain to html for getting original

* respect charset for plain texts

* make test more specific

* fix handling non-utf-8 charsets for plain messages

* add test for plain_to_html()

* add failing test for plaintext linkify

* linkify urls in plain text

* fix regex

* plain text linkify: add failing test for encapsulated links as <https://domain.com>

* plain text linkify: make encapsulated links as <https://domain.com> work

* plain text linkify: require word boundary at beginning of link, add tests for that

* plain text linkify: linkify emails

* plain text: support format=flowed

* plain text: support quotes

* make clippy happy

* set mime-modified also when simplify() cuts non-html messages, add tests for that

* streamline mime recursion

* repl tool: write original html to file for further processing

* convert cid:- to data:-protocol

* add a test for cid: to data: conversion

* make clippy happy

* fix html-tests to work with windows-lineends

* clarify what the returned html-code may contain

* add some more detailed doc comments

* add mime_modified column only if not exist

this additional check is needed
as the column may added with another dbversion in
some shipped beta-versions.

* incorporate documentation suggestions from review

* rename get_original_mime_html() to more simple get_html()

* rename api is_mime_modified() to more simple has_html(); internally, mime_modified-flag stays as-is, however

* rename MimeS to MimeMultipartType

* do not set mime-modified flag for encrypted messages that need extra-handling for saved mime-structure

* fix typo

* move get_msg_html() to MsgId.get_html()

* incorporate more documentation suggestions from review

* remove unused return value from collect_texts_recursive()

* avoid mime_modified being mutable in write-parts-loop

* move 'use futures::future::FutureExt' atop of html.rs

* move attributes defining plain-text to a dedicated structure

* more PlainText to separate file

* escape cid when building regex

* let dc_get_msg_html() return NULL when calling with bad param

examples/repl/cmdline.rs

@@ -21,6 +21,7 @@ use deltachat::qr::*;
 use deltachat::sql;
 use deltachat::EventType;
 use deltachat::{config, provider};
+use std::fs;
 
 /// Reset database tables.
 /// Argument is a bitmask, executing single or multiple actions in one call.
@@ -185,7 +186,7 @@ async fn log_msg(context: &Context, prefix: impl AsRef<str>, msg: &Message) {
     let temp2 = dc_timestamp_to_str(msg.get_timestamp());
     let msgtext = msg.get_text();
     println!(
-        "{}{}{}{}: {} (Contact#{}): {} {}{}{}{}{} [{}]",
+        "{}{}{}{}: {} (Contact#{}): {} {}{}{}{}{}{} [{}]",
         prefix.as_ref(),
         msg.get_id(),
         if msg.get_showpadlock() { "🔒" } else { "" },
@@ -193,6 +194,7 @@ async fn log_msg(context: &Context, prefix: impl AsRef<str>, msg: &Message) {
         &contact_name,
         contact_id,
         msgtext.unwrap_or_default(),
+        if msg.has_html() { "[HAS-HTML]️" } else { "" },
         if msg.get_from_id() == 1 as libc::c_uint {
             ""
         } else if msg.get_state() == MessageState::InSeen {
@@ -384,6 +386,7 @@ pub async fn cmdline(context: Context, line: &str, chat_id: &mut ChatId) -> Resu
                  ===========================Message commands==\n\
                  listmsgs <query>\n\
                  msginfo <msg-id>\n\
+                 html <msg-id>\n\
                  listfresh\n\
                  forward <msg-id> <chat-id>\n\
                  markseen <msg-id>\n\
@@ -942,6 +945,16 @@ pub async fn cmdline(context: Context, line: &str, chat_id: &mut ChatId) -> Resu
             let res = message::get_msg_info(&context, id).await;
             println!("{}", res);
         }
+        "html" => {
+            ensure!(!arg1.is_empty(), "Argument <msg-id> missing.");
+            let id = MsgId::new(arg1.parse()?);
+            let file = dirs::home_dir()
+                .unwrap_or_default()
+                .join(format!("msg-{}.html", id.to_u32()));
+            let html = id.get_html(&context).await;
+            fs::write(&file, html)?;
+            println!("HTML written to: {:#?}", file);
+        }
         "listfresh" => {
             let msglist = context.get_fresh_msgs().await;